Search results for: data driven diagnosis
24695 Digital Advance Care Planning and Directives: Early Observations of Adoption Statistics and Responses from an All-Digital Consumer-Driven Approach
Authors: Robert L. Fine, Zhiyong Yang, Christy Spivey, Bonnie Boardman, Maureen Courtney
Abstract:
Importance: Barriers to traditional advance care planning (ACP) and advance directive (AD) creation have limited the promise of ACP/AD for individuals and families, the healthcare team, and society. Reengineering ACP by using a web-based, consumer-driven process has recently been suggested. We report early experience with such a process. Objective: Begin to analyze the potential of the creation and use of ACP/ADs as generated by a consumer-friendly, digital process by 1) assessing the likelihood that consumers would create ACP/ADs without structured intervention by medical or legal professionals, and 2) analyzing the responses to determine if the plans can help doctors better understand a person’s goals, preferences, and priorities for their medical treatments and the naming of healthcare agents. Design: The authors chose 900 users of MyDirectives.com, a digital ACP/AD tool, solely based on their state of residence in order to achieve proportional representation of all 50 states by population size and then reviewed their responses, summarizing these through descriptive statistics including treatment preferences, demographics, and revision of preferences. Setting: General United States population. Participants: The 900 participants had an average age of 50.8 years (SD = 16.6); 84.3% of the men and 91% of the women were in self-reported good health when signing their ADs. Main measures: Preferences regarding the use of life-sustaining treatments, where to spend final days, consulting a supportive and palliative care team, attempted cardiopulmonary resuscitation (CPR), autopsy, and organ and tissue donation. Results: Nearly 85% of respondents prefer cessation of life-sustaining treatments during their final days whenever those may be, 76% prefer to spend their final days at home or in a hospice facility, and 94% wanted their future doctors to consult a supportive and palliative care team. 70% would accept attempted CPR in certain limited circumstances. Most respondents would want an autopsy under certain conditions, and 62% would like to donate their organs. Conclusions and relevance: Analysis of early experience with an all-digital web-based ACP/AD platform demonstrates that individuals from a wide range of ages and conditions can engage in an interrogatory process about values, goals, preferences, and priorities for their medical treatments by developing advance directives and easily make changes to the AD created. Online creation, storage, and retrieval of advance directives has the potential to remove barriers to ACP/AD and, thus, to further improve patient-centered end-of-life care.Keywords: Advance Care Plan, Advance Decisions, Advance Directives, Consumer; Digital, End of Life Care, Goals, Living Wills, Prefences, Universal Advance Directive, Statements
Procedia PDF Downloads 31924694 Molecular Epidemiology of Anthrax in Georgia
Authors: N. G. Vepkhvadze, T. Enukidze
Abstract:
Anthrax is a fatal disease caused by strains of Bacillus anthracis, a spore-forming gram-positive bacillus that causes the disease anthrax in animals and humans. Anthrax is a zoonotic disease that is also well-recognized as a potential agent of bioterrorism. Infection in humans is extremely rare in the developed world and is generally due to contact with infected animals or contaminated animal products. Testing of this zoonotic disease began in 1907 in Georgia and is still being tested routinely to provide accurate information and efficient testing results at the State Laboratory of Agriculture of Georgia. Each clinical sample is analyzed by RT-PCR and bacteriology methods; this study used Real-Time PCR assays for the detection of B. anthracis that rely on plasmid-encoded targets with a chromosomal marker to correctly differentiate pathogenic strains from non-anthracis Bacillus species. During the period of 2015-2022, the State Laboratory of Agriculture (SLA) tested 250 clinical and environmental (soil) samples from several different regions in Georgia. In total, 61 out of the 250 samples were positive during this period. Based on the results, Anthrax cases are mostly present in Eastern Georgia, with a high density of the population of livestock, specifically in the regions of Kakheti and Kvemo Kartli. All laboratory activities are being performed in accordance with International Quality standards, adhering to biosafety and biosecurity rules by qualified and experienced personnel handling pathogenic agents. Laboratory testing plays the largest role in diagnosing animals with anthrax, which helps pertinent institutions to quickly confirm a diagnosis of anthrax and evaluate the epidemiological situation that generates important data for further responses.Keywords: animal disease, baccilus anthracis, edp, laboratory molecular diagnostics
Procedia PDF Downloads 8124693 Mapping Iron Content in the Brain with Magnetic Resonance Imaging and Machine Learning
Authors: Gabrielle Robertson, Matthew Downs, Joseph Dagher
Abstract:
Iron deposition in the brain has been linked with a host of neurological disorders such as Alzheimer’s, Parkinson’s, and Multiple Sclerosis. While some treatment options exist, there are no objective measurement tools that allow for the monitoring of iron levels in the brain in vivo. An emerging Magnetic Resonance Imaging (MRI) method has been recently proposed to deduce iron concentration through quantitative measurement of magnetic susceptibility. This is a multi-step process that involves repeated modeling of physical processes via approximate numerical solutions. For example, the last two steps of this Quantitative Susceptibility Mapping (QSM) method involve I) mapping magnetic field into magnetic susceptibility and II) mapping magnetic susceptibility into iron concentration. Process I involves solving an ill-posed inverse problem by using regularization via injection of prior belief. The end result from Process II highly depends on the model used to describe the molecular content of each voxel (type of iron, water fraction, etc.) Due to these factors, the accuracy and repeatability of QSM have been an active area of research in the MRI and medical imaging community. This work aims to estimate iron concentration in the brain via a single step. A synthetic numerical model of the human head was created by automatically and manually segmenting the human head on a high-resolution grid (640x640x640, 0.4mm³) yielding detailed structures such as microvasculature and subcortical regions as well as bone, soft tissue, Cerebral Spinal Fluid, sinuses, arteries, and eyes. Each segmented region was then assigned tissue properties such as relaxation rates, proton density, electromagnetic tissue properties and iron concentration. These tissue property values were randomly selected from a Probability Distribution Function derived from a thorough literature review. In addition to having unique tissue property values, different synthetic head realizations also possess unique structural geometry created by morphing the boundary regions of different areas within normal physical constraints. This model of the human brain is then used to create synthetic MRI measurements. This is repeated thousands of times, for different head shapes, volume, tissue properties and noise realizations. Collectively, this constitutes a training-set that is similar to in vivo data, but larger than datasets available from clinical measurements. This 3D convolutional U-Net neural network architecture was used to train data-driven Deep Learning models to solve for iron concentrations from raw MRI measurements. The performance was then tested on both synthetic data not used in training as well as real in vivo data. Results showed that the model trained on synthetic MRI measurements is able to directly learn iron concentrations in areas of interest more effectively than other existing QSM reconstruction methods. For comparison, models trained on random geometric shapes (as proposed in the Deep QSM method) are less effective than models trained on realistic synthetic head models. Such an accurate method for the quantitative measurement of iron deposits in the brain would be of important value in clinical studies aiming to understand the role of iron in neurological disease.Keywords: magnetic resonance imaging, MRI, iron deposition, machine learning, quantitative susceptibility mapping
Procedia PDF Downloads 12624692 Characteristics and Prevalence of Anaemia among Mothers and Young Children in Rural Uganda
Authors: Pamela E. Mukaire
Abstract:
Anemia and chronic energy deficiency are significant manifestations of poor nutritional health. Anaemia and nutritional status screening are practical ways for assessing the prevalence of iron deficiency anemia in the food insecure populations with large groups of childbearing women and children. The objective of the study was to assess anemia prevalence and other clinical manifestations of malnutrition among pairs of mothers and young children in rural Uganda. This community cross-sectional study used consecutive sampling to select 214 mothers and 214 children for the study. Data was generated using structured questionnaire, anthropometric measurements and on site analysis for anemia. Bivariable and multivariable analyses were used to assess the effect of different factors on anaemia. Of the 214 mothers, 54.2% were 25-34 years of age, 76.7% unmarried, 63% low income, and 55% had more than four children. Of the 214 children, 57% were female, 50% between 1 to 3 years of age and 35% under one year, and. Overall, 38% of the households had more 4 children under the age of 12. The prevalence of anemia was 48% for mothers and 72% for children; 20.6% of mothers had moderate to severe chronic energy deficiency, 39% had moderately-severe anaemia (10 to 7.1 g/dL). Among children, 53% had moderately-severe anaemia, and 18.2% had severe anaemia. Parity X2 =20, p < .037, number of children under 12 years living in a household X2 =10, p < .015, and child’s gender X2 =6.5, p < .038, had a significant relationship with maternal anaemia. There was a significant relationship between household income X2 =10, p < .005, marital status X2 =9, p < .011, owing a piece of land X2 =18, p < .000, owing home X2 =7, p < .036, and anaemia in children. The prevalence of anemia was high in both mothers and children. Income, marital status, owing a piece of land, owing home, number of children under age 12 in a household were associated with anaemia. Hence, efforts should be made for early diagnosis and management of anaemia deficiencies with special emphasis on those households with large number of children under age 12.Keywords: anemia, maternal-child, nutrition, rural population
Procedia PDF Downloads 27724691 Spectrum and Prevalence of Candida Infection in Diabetic Foot Ulcers
Authors: Seyed Reza Aghili, Tahereh Shokohi, Lotfollah Davoodi, Zahra Kashi, Azam Moslemi, Mahdi Abastabar, Iman Haghani, Sabah Mayahi, Asoudeh A.
Abstract:
Introduction: In diabetic foot ulcers, if fungal agents such as Candida species penetrate into the cutaneous or depth of ulcer, can increase the degree of the wound and cause Candia infection and make it more difficult to heal. Material & Methods: A cross-sectional study was performed on 100 diabetic foot ulcer patients in 2020 in Sari, Iran. patient's data and wound grade were recorded in a questionnaire. Candida infection was diagnosed with direct microscopic examination and culture of samples. Colony-PCR molecular method was used for ITS region of DNA and then PCR-RFLP with Msp1 enzyme and using HWP1 specific gene to determine species of Candida agent. Results: Of 100 patients, the mean age 62.1 ± 10.8 years, 95% type 2 diabetes, 83%>10 years duration diabetes, 59% male, 66%> poor education level, 99% married, 52% rural, 95% neuropathic symptoms, 88% using antibiotics, 69%HbA1C >9%, and mean ulcer degree 2.6±1.05 were. Candida infection was seen in 13% of the deep tissue of the wound and 7% cutaneous around the wound. The predominant Candida isolated was C. parapsilosis (71.5%), C .albicans (14.3%). Fungal infections caused by mold fungi were not detected. There was a statistically significant relationship between yeast infection and gender, rural, HbA1C and ulcer degree. Conclusion: Mycological evaluations often are ignored. Candida parapsilosis is the most common infectious agent in these patients and may require specific treatment. Therefore, more attention of physicians to Candida infections particularly, early diagnosis and effective treatment can help faster recovery and prevent amputation.Keywords: diabetic foot ulcer, candida infection, risk factors, c. parapsilosis
Procedia PDF Downloads 18724690 A Machine Learning Model for Dynamic Prediction of Chronic Kidney Disease Risk Using Laboratory Data, Non-Laboratory Data, and Metabolic Indices
Authors: Amadou Wurry Jallow, Adama N. S. Bah, Karamo Bah, Shih-Ye Wang, Kuo-Chung Chu, Chien-Yeh Hsu
Abstract:
Chronic kidney disease (CKD) is a major public health challenge with high prevalence, rising incidence, and serious adverse consequences. Developing effective risk prediction models is a cost-effective approach to predicting and preventing complications of chronic kidney disease (CKD). This study aimed to develop an accurate machine learning model that can dynamically identify individuals at risk of CKD using various kinds of diagnostic data, with or without laboratory data, at different follow-up points. Creatinine is a key component used to predict CKD. These models will enable affordable and effective screening for CKD even with incomplete patient data, such as the absence of creatinine testing. This retrospective cohort study included data on 19,429 adults provided by a private research institute and screening laboratory in Taiwan, gathered between 2001 and 2015. Univariate Cox proportional hazard regression analyses were performed to determine the variables with high prognostic values for predicting CKD. We then identified interacting variables and grouped them according to diagnostic data categories. Our models used three types of data gathered at three points in time: non-laboratory, laboratory, and metabolic indices data. Next, we used subgroups of variables within each category to train two machine learning models (Random Forest and XGBoost). Our machine learning models can dynamically discriminate individuals at risk for developing CKD. All the models performed well using all three kinds of data, with or without laboratory data. Using only non-laboratory-based data (such as age, sex, body mass index (BMI), and waist circumference), both models predict chronic kidney disease as accurately as models using laboratory and metabolic indices data. Our machine learning models have demonstrated the use of different categories of diagnostic data for CKD prediction, with or without laboratory data. The machine learning models are simple to use and flexible because they work even with incomplete data and can be applied in any clinical setting, including settings where laboratory data is difficult to obtain.Keywords: chronic kidney disease, glomerular filtration rate, creatinine, novel metabolic indices, machine learning, risk prediction
Procedia PDF Downloads 9824689 The Antecedents of Internet Addiction toward Smartphone Usage
Authors: Pui-Lai To, Chechen Liao, Hen-Yi Huang
Abstract:
Twenty years after Internet development, scholars have started to identify the negative impacts brought by the Internet. Overuse of Internet could develop Internet dependency and in turn cause addiction behavior. Therefore understanding the phenomenon of Internet addiction is important. With the joint efforts of experts and scholars, Internet addiction has been officially listed as a symptom that affects public health, and the diagnosis, causes and treatment of the symptom have also been explored. On the other hand, in the area of smartphone Internet usage, most studies are still focusing on the motivation factors of smartphone usage. Not much research has been done on smartphone Internet addiction. In view of the increasing adoption of smartphones, this paper is intended to find out whether smartphone Internet addiction exists in modern society or not. This study adopted the research methodology of online survey targeting users with smartphone Internet experience. A total of 434 effective samples were recovered. In terms of data analysis, Partial Least Square (PLS) in Structural Equation Modeling (SEM) is used for sample analysis and research model testing. Software chosen for statistical analysis is SPSS 20.0 for windows and SmartPLS 2.0. The research result successfully proved that smartphone users who access Internet service via smartphone could also develop smartphone Internet addiction. Factors including flow experience, depression, virtual social support, smartphone Internet affinity and maladaptive cognition all have significant and positive influence on smartphone Internet addiction. In the scenario of smartphone Internet use, descriptive norm has a positive and significant influence on perceived playfulness, while perceived playfulness also has a significant and positive influence on flow experience. Depression, on the other hand, is negatively influenced by actual social support and positive influenced by the virtual social support.Keywords: internet addiction, smartphone usage, social support, perceived playfulness
Procedia PDF Downloads 23924688 Nanotechnolgy for Energy Harvesting Applications
Authors: Eiman Nour
Abstract:
The rising interest in harvesting power is because of the capabilities application of expanding self-powered systems based on nanostructures. Using renewable and self-powered sources is necessary for the growth of green electronics and could be of the capability to wireless sensor networks. The ambient mechanical power is among the ample sources for various power harvesting device configurations that are published. In this work, we design and fabricate a paper-based nanogenerator (NG) utilizing piezoelectric zinc oxide (ZnO) nanowires (NWs) grown hydrothermally on a paper substrate. The fabricated NG can harvest ambient mechanical energy from various kinds of human motions, such as handwriting. The fabricated NG from a single ZnO NWs/PVDF-TrFE NG has been used firstly as handwriting-driven NG. The mechanical pressure applied on the paper platform while handwriting is harvested by the NG to deliver electrical energy; depending on the mode of handwriting, a maximum harvested voltage of 4.8 V was obtained.Keywords: nanostructure, zinc oxide, nanogenerator, energy harvesting
Procedia PDF Downloads 5524687 Students’ Experiential Knowledge Production in the Teaching-Learning Process of Universities
Authors: Didiosky Benítez-Erice, Frederik Questier, Dalgys Pérez-Luján
Abstract:
This paper aims to present two models around the production of students’ experiential knowledge in the teaching-learning process of higher education: the teacher-centered production model and the student-centered production model. From a range of knowledge management and experiential learning theories, the paper elaborates into the nature of students’ experiential knowledge and proposes further adjustments of existing second-generation knowledge management theories taking into account the particularities of higher education. Despite its theoretical nature the paper can be relevant for future studies that stress student-driven improvement and innovation at higher education institutions.Keywords: experiential knowledge, higher education, knowledge management, teaching-learning process
Procedia PDF Downloads 43524686 Road Accidents Bigdata Mining and Visualization Using Support Vector Machines
Authors: Usha Lokala, Srinivas Nowduri, Prabhakar K. Sharma
Abstract:
Useful information has been extracted from the road accident data in United Kingdom (UK), using data analytics method, for avoiding possible accidents in rural and urban areas. This analysis make use of several methodologies such as data integration, support vector machines (SVM), correlation machines and multinomial goodness. The entire datasets have been imported from the traffic department of UK with due permission. The information extracted from these huge datasets forms a basis for several predictions, which in turn avoid unnecessary memory lapses. Since data is expected to grow continuously over a period of time, this work primarily proposes a new framework model which can be trained and adapt itself to new data and make accurate predictions. This work also throws some light on use of SVM’s methodology for text classifiers from the obtained traffic data. Finally, it emphasizes the uniqueness and adaptability of SVMs methodology appropriate for this kind of research work.Keywords: support vector mechanism (SVM), machine learning (ML), support vector machines (SVM), department of transportation (DFT)
Procedia PDF Downloads 26524685 A Relational Data Base for Radiation Therapy
Authors: Raffaele Danilo Esposito, Domingo Planes Meseguer, Maria Del Pilar Dorado Rodriguez
Abstract:
As far as we know, it is still unavailable a commercial solution which would allow to manage, openly and configurable up to user needs, the huge amount of data generated in a modern Radiation Oncology Department. Currently, available information management systems are mainly focused on Record & Verify and clinical data, and only to a small extent on physical data. Thus, results in a partial and limited use of the actually available information. In the present work we describe the implementation at our department of a centralized information management system based on a web server. Our system manages both information generated during patient planning and treatment, and information of general interest for the whole department (i.e. treatment protocols, quality assurance protocols etc.). Our objective it to be able to analyze in a simple and efficient way all the available data and thus to obtain quantitative evaluations of our treatments. This would allow us to improve our work flow and protocols. To this end we have implemented a relational data base which would allow us to use in a practical and efficient way all the available information. As always we only use license free software.Keywords: information management system, radiation oncology, medical physics, free software
Procedia PDF Downloads 23024684 A Study of Safety of Data Storage Devices of Graduate Students at Suan Sunandha Rajabhat University
Authors: Komol Phaisarn, Natcha Wattanaprapa
Abstract:
This research is a survey research with an objective to study the safety of data storage devices of graduate students of academic year 2013, Suan Sunandha Rajabhat University. Data were collected by questionnaire on the safety of data storage devices according to CIA principle. A sample size of 81 was drawn from population by purposive sampling method. The results show that most of the graduate students of academic year 2013 at Suan Sunandha Rajabhat University use handy drive to store their data and the safety level of the devices is at good level.Keywords: security, safety, storage devices, graduate students
Procedia PDF Downloads 34624683 A Goal-Driven Crime Scripting Framework
Authors: Hashem Dehghanniri
Abstract:
Crime scripting is a simple and effective crime modeling technique that aims to improve understanding of security analysts about security and crime incidents. Low-quality scripts provide a wrong, incomplete, or sophisticated understanding of the crime commission process, which oppose the purpose of their application, e.g., identifying effective and cost-efficient situational crime prevention (SCP) measures. One important and overlooked factor in generating quality scripts is the crime scripting method. This study investigates the problems within the existing crime scripting practices and proposes a crime scripting approach that contributes to generating quality crime scripts. It was validated by experienced crime scripters. This framework helps analysts develop better crime scripts and contributes to their effective application, e.g., SCP measures identification or policy-making.Keywords: attack modelling, crime commission process, crime script, situational crime prevention
Procedia PDF Downloads 12324682 Exploring the Effectiveness of Robotic Companions Through the Use of Symbiotic Autonomous Plant Care Robots
Authors: Angelos Kaminis, Dakotah Stirnweis
Abstract:
Advances in robotic technology have driven the development of improved robotic companions in the last couple decades. However, commercially available robotic companions lack the ability to create an emotional connection with their user. By developing a companion robot that has a symbiotic relationship with a plant, an element of co-dependency is introduced into the human companion robot dynamic. This companion robot, while theoretically capable of providing most of the plant’s needs, still requires human interaction for watering, moving obstacles, and solar panel cleaning. To facilitate the interaction between human and robot, the robot is capable of limited auditory and visual communication to help express its and the plant’s needs. This paper seeks to fully describe the Autonomous Plant Care Robot system and its symbiotic relationship with its botanical ward and the plant and robot’s dependent relationship with their owner.Keywords: symbiotic, robotics, autonomous, plant-care, companion
Procedia PDF Downloads 13524681 Simulation of a Cost Model Response Requests for Replication in Data Grid Environment
Authors: Kaddi Mohammed, A. Benatiallah, D. Benatiallah
Abstract:
Data grid is a technology that has full emergence of new challenges, such as the heterogeneity and availability of various resources and geographically distributed, fast data access, minimizing latency and fault tolerance. Researchers interested in this technology address the problems of the various systems related to the industry such as task scheduling, load balancing and replication. The latter is an effective solution to achieve good performance in terms of data access and grid resources and better availability of data cost. In a system with duplication, a coherence protocol is used to impose some degree of synchronization between the various copies and impose some order on updates. In this project, we present an approach for placing replicas to minimize the cost of response of requests to read or write, and we implement our model in a simulation environment. The placement techniques are based on a cost model which depends on several factors, such as bandwidth, data size and storage nodes.Keywords: response time, query, consistency, bandwidth, storage capacity, CERN
Procedia PDF Downloads 26224680 Trial of Faecal Microbial Transplantation for the Prevention of Canine Atopic Dermatitis
Authors: Caroline F. Moeser
Abstract:
The skin-gut axis defines the relationship between the intestinal microbiota and the development of pathological skin diseases. Low diversity within the gut can predispose to the development of allergic skin conditions, and a greater diversity of the gastrointestinal microflora has been associated with a reduction of skin flares in people with atopic dermatitis. Manipulation of the gut microflora has been used as a treatment option for several conditions in people, but there is limited data available on the use of faecal transplantation as a preventative measure in either people or dogs. Six, 4-month-old pups from a litter of ten were presented for diarrhea and/or signs of skin disease (chronic scratching, otitis externa). Of these pups, two were given probiotics with a resultant resolution of diarrhea. The other four pups were given faecal transplantation, either as a sole treatment or in combination with other treatments. Follow-up on the litter of ten pups was performed at 18 months of age. At this stage, the four pups that had received faecal transplantation had resolved all clinical signs and had no recurrence of either skin or gastrointestinal symptoms. Of the remaining six pups from the litter, all had developed at least one episode of Malassezia otitis externa within the period of 5 months to 18 months of age. Two pups had developed two Malassezia otitis infections, and one had developed three Malassezia otitis infections during this period. Favrot’s criteria for the diagnosis of canine atopic dermatitis include chronic or recurrent Malassezia infections by the age of three years. Early results from this litter predict a reduction in the development of canine atopic disease in dogs given faecal microbial transplantation. Follow-up studies at three years of age and within a larger population of dogs can enhance understanding of the impact of early faecal transplantation in the prevention of canine atopic dermatitis.Keywords: canine atopic dermatitis, faecal microbial transplant, skin-gut axis, otitis
Procedia PDF Downloads 14824679 Differences in Patient Satisfaction Observed between Female Japanese Breast Cancer Patients Who Receive Breast-Conserving Surgery or Total Mastectomy
Authors: Keiko Yamauchi, Motoyuki Nakao, Yoko Ishihara
Abstract:
The increase in the number of women with breast cancer in Japan has required hospitals to provide a higher quality of medicine so that patients are satisfied with the treatment they receive. However, patients’ satisfaction following breast cancer treatment has not been sufficiently studied. Hence, we investigated the factors influencing patient satisfaction following breast cancer treatment among Japanese women. These women underwent either breast-conserving surgery (BCS) (n = 380) or total mastectomy (TM) (n = 247). In March 2016, we conducted a cross-sectional internet survey of Japanese women with breast cancer in Japan. We assessed the following factors: socioeconomic status, cancer-related information, the role of medical decision-making, the degree of satisfaction regarding the treatments received, and the regret arising from the medical decision-making processes. We performed logistic regression analyses with the following dependent variables: extreme satisfaction with the treatments received, and regret regarding the medical decision-making process. For both types of surgery, the odds ratio (OR) of being extremely satisfied with the cancer treatment was significantly higher among patients who did not have any regrets compared to patients who had. Also, the OR tended to be higher among patients who chose to play a wanted role in the medical decision-making process, compared with patients who did not. In the BCS group, the OR of being extremely satisfied with the treatment was higher if, at diagnosis, the patient’s youngest child was older than 19 years, compared with patients with no children. The OR was also higher if patient considered the stage and characteristics of their cancer significant. The OR of being extremely satisfied with the treatments was lower among patients who were not employed on full-time basis, and among patients who considered the second medical opinions and medical expenses to be significant. These associations were not observed in the TM group. The OR of having regrets regarding the medical decision-making process was higher among patients who chose to play a role in the decision-making process as they preferred, and was also higher in patients who were employed on either a part-time or contractual basis. For both types of surgery, the OR was higher among patients who considered a second medical opinion to be significant. Regardless of surgical type, regret regarding the medical decision-making process decreases treatment satisfaction. Patients who received breast-conserving surgery were more likely to have regrets concerning the medical decision-making process if they could not play a role in the process as they preferred. In addition, factors associated with the satisfaction with treatment in BCS group but not TM group included the second medical opinion, medical expenses, employment status, and age of the youngest child at diagnosis.Keywords: medical decision making, breast-conserving surgery, total mastectomy, Japanese
Procedia PDF Downloads 14324678 A Generative Pretrained Transformer-Based Question-Answer Chatbot and Phantom-Less Quantitative Computed Tomography Bone Mineral Density Measurement System for Osteoporosis
Authors: Mian Huang, Chi Ma, Junyu Lin, William Lu
Abstract:
Introduction: Bone health attracts more attention recently and an intelligent question and answer (QA) chatbot for osteoporosis is helpful for science popularization. With Generative Pretrained Transformer (GPT) technology developing, we build an osteoporosis corpus dataset and then fine-tune LLaMA, a famous open-source GPT foundation large language model(LLM), on our self-constructed osteoporosis corpus. Evaluated by clinical orthopedic experts, our fine-tuned model outperforms vanilla LLaMA on osteoporosis QA task in Chinese. Three-dimensional quantitative computed tomography (QCT) measured bone mineral density (BMD) is considered as more accurate than DXA for BMD measurement in recent years. We develop an automatic Phantom-less QCT(PL-QCT) that is more efficient for BMD measurement since no need of an external phantom for calibration. Combined with LLM on osteoporosis, our PL-QCT provides efficient and accurate BMD measurement for our chatbot users. Material and Methods: We build an osteoporosis corpus containing about 30,000 Chinese literatures whose titles are related to osteoporosis. The whole process is done automatically, including crawling literatures in .pdf format, localizing text/figure/table region by layout segmentation algorithm and recognizing text by OCR algorithm. We train our model by continuous pre-training with Low-rank Adaptation (LoRA, rank=10) technology to adapt LLaMA-7B model to osteoporosis domain, whose basic principle is to mask the next word in the text and make the model predict that word. The loss function is defined as cross-entropy between the predicted and ground-truth word. Experiment is implemented on single NVIDIA A800 GPU for 15 days. Our automatic PL-QCT BMD measurement adopt AI-associated region-of-interest (ROI) generation algorithm for localizing vertebrae-parallel cylinder in cancellous bone. Due to no phantom for BMD calibration, we calculate ROI BMD by CT-BMD of personal muscle and fat. Results & Discussion: Clinical orthopaedic experts are invited to design 5 osteoporosis questions in Chinese, evaluating performance of vanilla LLaMA and our fine-tuned model. Our model outperforms LLaMA on over 80% of these questions, understanding ‘Expert Consensus on Osteoporosis’, ‘QCT for osteoporosis diagnosis’ and ‘Effect of age on osteoporosis’. Detailed results are shown in appendix. Future work may be done by training a larger LLM on the whole orthopaedics with more high-quality domain data, or a multi-modal GPT combining and understanding X-ray and medical text for orthopaedic computer-aided-diagnosis. However, GPT model gives unexpected outputs sometimes, such as repetitive text or seemingly normal but wrong answer (called ‘hallucination’). Even though GPT give correct answers, it cannot be considered as valid clinical diagnoses instead of clinical doctors. The PL-QCT BMD system provided by Bone’s QCT(Bone’s Technology(Shenzhen) Limited) achieves 0.1448mg/cm2(spine) and 0.0002 mg/cm2(hip) mean absolute error(MAE) and linear correlation coefficient R2=0.9970(spine) and R2=0.9991(hip)(compared to QCT-Pro(Mindways)) on 155 patients in three-center clinical trial in Guangzhou, China. Conclusion: This study builds a Chinese osteoporosis corpus and develops a fine-tuned and domain-adapted LLM as well as a PL-QCT BMD measurement system. Our fine-tuned GPT model shows better capability than LLaMA model on most testing questions on osteoporosis. Combined with our PL-QCT BMD system, we are looking forward to providing science popularization and early morning screening for potential osteoporotic patients.Keywords: GPT, phantom-less QCT, large language model, osteoporosis
Procedia PDF Downloads 6224677 Prompt Design for Code Generation in Data Analysis Using Large Language Models
Authors: Lu Song Ma Li Zhi
Abstract:
With the rapid advancement of artificial intelligence technology, large language models (LLMs) have become a milestone in the field of natural language processing, demonstrating remarkable capabilities in semantic understanding, intelligent question answering, and text generation. These models are gradually penetrating various industries, particularly showcasing significant application potential in the data analysis domain. However, retraining or fine-tuning these models requires substantial computational resources and ample downstream task datasets, which poses a significant challenge for many enterprises and research institutions. Without modifying the internal parameters of the large models, prompt engineering techniques can rapidly adapt these models to new domains. This paper proposes a prompt design strategy aimed at leveraging the capabilities of large language models to automate the generation of data analysis code. By carefully designing prompts, data analysis requirements can be described in natural language, which the large language model can then understand and convert into executable data analysis code, thereby greatly enhancing the efficiency and convenience of data analysis. This strategy not only lowers the threshold for using large models but also significantly improves the accuracy and efficiency of data analysis. Our approach includes requirements for the precision of natural language descriptions, coverage of diverse data analysis needs, and mechanisms for immediate feedback and adjustment. Experimental results show that with this prompt design strategy, large language models perform exceptionally well in multiple data analysis tasks, generating high-quality code and significantly shortening the data analysis cycle. This method provides an efficient and convenient tool for the data analysis field and demonstrates the enormous potential of large language models in practical applications.Keywords: large language models, prompt design, data analysis, code generation
Procedia PDF Downloads 1924676 Comparison of Different Methods to Produce Fuzzy Tolerance Relations for Rainfall Data Classification in the Region of Central Greece
Authors: N. Samarinas, C. Evangelides, C. Vrekos
Abstract:
The aim of this paper is the comparison of three different methods, in order to produce fuzzy tolerance relations for rainfall data classification. More specifically, the three methods are correlation coefficient, cosine amplitude and max-min method. The data were obtained from seven rainfall stations in the region of central Greece and refers to 20-year time series of monthly rainfall height average. Three methods were used to express these data as a fuzzy relation. This specific fuzzy tolerance relation is reformed into an equivalence relation with max-min composition for all three methods. From the equivalence relation, the rainfall stations were categorized and classified according to the degree of confidence. The classification shows the similarities among the rainfall stations. Stations with high similarity can be utilized in water resource management scenarios interchangeably or to augment data from one to another. Due to the complexity of calculations, it is important to find out which of the methods is computationally simpler and needs fewer compositions in order to give reliable results.Keywords: classification, fuzzy logic, tolerance relations, rainfall data
Procedia PDF Downloads 30924675 Code-Switching as a Bilingual Phenomenon among Students in Prishtina International Schools
Authors: Festa Shabani
Abstract:
This paper aims at investigating bilingual speech in the International Schools of Prishtina. More particularly, it seeks to analyze bilingual phenomena among adolescent students highly exposed to English with the latter as the language of instruction at school in naturally-occurring conversations within school environment. Adolescence was deliberately chosen since it is regarded as an age when peer influence on language choice is the greatest. Driven by daily unsystematic observation and prior research already undertaken, the hypothesis stated is that Albanian continues to be the dominant language among Prishtina international schools’ students with a lot of code-switched items from the English. Furthermore, they will also use lexical borrowings - words already adapted in the receiving language, from the language they have been in contact with, in their speech often in the lack of existing equivalents in Albanian or for other reasons. This is done owing to the fact that the language of instruction at school is English, and any topic related to the language they have been exposed to will trigger them to use English. Therefore, this needs special attention in an attempt to identify patterns of their speech; in this way, linguistic and socio-pragmatic factors will be considered when analyzing the motivations behind their language choice. Methodology for collecting data include participant systematic observation and tape-recording. While observing them in their natural conversations, the fieldworker also took notes, which helped transcribe details better. The paper starts by raising the question of whether code-switching is occurring among Prishtina International Schools’ students highly exposed to English. The data gathered from students in informal settings suggests that there are well-founded grounds for an affirmative answer. The participants in this study are observed to be code-switching, although showing differences in degree. However, a generalization cannot be made on the basis of the findings except in so far it appears that English has, in turn, became a language to which they turn when identifying with the group when discussing about particular school topics. Particularly, participants seemed to use intra-sentential CS in cases when they seem to find an English expression rather easier than an Albanian one when repeating or emphasizing a point when urged to talk about educational issues with English being their language of instruction, and inter-sentential code-switching, particularly when quoting others. Concerning the grammatical aspect of code-switching, the intrasentential CS is used more than the intersentetial one. Speaking of gender, the results show that there were really no significant differences in regards quantity between male and female participants. However, the slight tendency for men to code switch intrasententially more than women was manifested. Similarly, a slight tendency again for a difference to emerge is on intersentential switching, which contributes 21% to the total number of switches for women, but 11% to the total number of switches for men.Keywords: Albanian, code-switching contact linguistics, bilingual phenomena, lexical borrowing, English
Procedia PDF Downloads 11624674 Customer Satisfaction and Effective HRM Policies: Customer and Employee Satisfaction
Authors: S. Anastasiou, C. Nathanailides
Abstract:
The purpose of this study is to examine the possible link between employee and customer satisfaction. The service provided by employees, help to build a good relationship with customers and can help at increasing their loyalty. Published data for job satisfaction and indicators of customer services were gathered from relevant published works which included data from five different countries. The reviewed data indicate a significant correlation between indicators of customer and employee satisfaction in the Banking sector. There was a significant correlation between the two parameters (Pearson correlation R2=0.52 P<0.05) The reviewed data provide evidence that there is some practical evidence which links these two parameters.Keywords: job satisfaction, job performance, customer’ service, banks, human resources management
Procedia PDF Downloads 31524673 Performance of an Absorption Refrigerator Using a Solar Thermal Collector
Authors: Abir Hmida, Nihel Chekir, Ammar Ben Brahim
Abstract:
In the present paper, we investigate the feasibility of a thermal solar driven cold room in Gabes, southern region of Tunisia. The cold room of 109 m3 is refrigerated using an ammonia absorption machine. It is destined to preserve dates during the hot months of the year. A detailed study of the cold room leads previously to the estimation of the cooling load of the proposed storage room in the operating conditions of the region. The next step consists of the estimation of the required heat in the generator of the absorption machine to ensure the desired cold temperature. A thermodynamic analysis was accomplished and complete description of the system is determined. We propose, here, to provide the needed heat thermally from the sun by using vacuum tube collectors. We found that at least 21m² of solar collectors are necessary to accomplish the work of the solar cold room.Keywords: absorption, ammonia, cold room, solar collector, vacuum tube
Procedia PDF Downloads 16524672 Tumor Detection Using Convolutional Neural Networks (CNN) Based Neural Network
Authors: Vinai K. Singh
Abstract:
In Neural Network-based Learning techniques, there are several models of Convolutional Networks. Whenever the methods are deployed with large datasets, only then can their applicability and appropriateness be determined. Clinical and pathological pictures of lobular carcinoma are thought to exhibit a large number of random formations and textures. Working with such pictures is a difficult problem in machine learning. Focusing on wet laboratories and following the outcomes, numerous studies have been published with fresh commentaries in the investigation. In this research, we provide a framework that can operate effectively on raw photos of various resolutions while easing the issues caused by the existence of patterns and texturing. The suggested approach produces very good findings that may be used to make decisions in the diagnosis of cancer.Keywords: lobular carcinoma, convolutional neural networks (CNN), deep learning, histopathological imagery scans
Procedia PDF Downloads 12924671 Evaluation of Australian Open Banking Regulation: Balancing Customer Data Privacy and Innovation
Authors: Suman Podder
Abstract:
As Australian ‘Open Banking’ allows customers to share their financial data with accredited Third-Party Providers (‘TPPs’), it is necessary to evaluate whether the regulators have achieved the balance between protecting customer data privacy and promoting data-related innovation. Recognising the need to increase customers’ influence on their own data, and the benefits of data-related innovation, the Australian Government introduced ‘Consumer Data Right’ (‘CDR’) to the banking sector through Open Banking regulation. Under Open Banking, TPPs can access customers’ banking data that allows the TPPs to tailor their products and services to meet customer needs at a more competitive price. This facilitated access and use of customer data will promote innovation by providing opportunities for new products and business models to emerge and grow. However, the success of Open Banking depends on the willingness of the customers to share their data, so the regulators have augmented the protection of data by introducing new privacy safeguards to instill confidence and trust in the system. The dilemma in policymaking is that, on the one hand, lenient data privacy laws will help the flow of information, but at the risk of individuals’ loss of privacy, on the other hand, stringent laws that adequately protect privacy may dissuade innovation. Using theoretical and doctrinal methods, this paper examines whether the privacy safeguards under Open Banking will add to the compliance burden of the participating financial institutions, resulting in the undesirable effect of stifling other policy objectives such as innovation. The contribution of this research is three-fold. In the emerging field of customer data sharing, this research is one of the few academic studies on the objectives and impact of Open Banking in the Australian context. Additionally, Open Banking is still in the early stages of implementation, so this research traces the evolution of Open Banking through policy debates regarding the desirability of customer data-sharing. Finally, the research focuses not only on the customers’ data privacy and juxtaposes it with another important objective of promoting innovation, but it also highlights the critical issues facing the data-sharing regime. This paper argues that while it is challenging to develop a regulatory framework for protecting data privacy without impeding innovation and jeopardising yet unknown opportunities, data privacy and innovation promote different aspects of customer welfare. This paper concludes that if a regulation is appropriately designed and implemented, the benefits of data-sharing will outweigh the cost of compliance with the CDR.Keywords: consumer data right, innovation, open banking, privacy safeguards
Procedia PDF Downloads 13624670 Resistance towards Education System through Street Library Movement: A Study in Sukabumi, Indonesia
Authors: M. Inbar Daeribi, Vara Leoni
Abstract:
Street Library Movement has been established and started to grow in some cities in Indonesia as a social movement. In the beginning, this movement emerged as a response to Indonesian lack of reading culture. Nevertheless, this study found out that street library movement is not only a literacy movement for developing reading culture. Furthermore, this movement is also a resistance towards education system in Indonesia. Street library movement is a critical consciousness driven by autonomous working group (community) as counter-public form towards Indonesia’s education condition legitimated by the government. This study, conducted in qualitative method with street library movement in Sukabumi, West Java, Indonesia as the object of study, will examine resistance forms of this movement and its social impacts. By studying this paper, it can be explained how street library movement served as an engine for social development.Keywords: street library movement, social movement, resistance, education system
Procedia PDF Downloads 32224669 A Single Cell Omics Experiments as Tool for Benchmarking Bioinformatics Oncology Data Analysis Tools
Authors: Maddalena Arigoni, Maria Luisa Ratto, Raffaele A. Calogero, Luca Alessandri
Abstract:
The presence of tumor heterogeneity, where distinct cancer cells exhibit diverse morphological and phenotypic profiles, including gene expression, metabolism, and proliferation, poses challenges for molecular prognostic markers and patient classification for targeted therapies. Understanding the causes and progression of cancer requires research efforts aimed at characterizing heterogeneity, which can be facilitated by evolving single-cell sequencing technologies. However, analyzing single-cell data necessitates computational methods that often lack objective validation. Therefore, the establishment of benchmarking datasets is necessary to provide a controlled environment for validating bioinformatics tools in the field of single-cell oncology. Benchmarking bioinformatics tools for single-cell experiments can be costly due to the high expense involved. Therefore, datasets used for benchmarking are typically sourced from publicly available experiments, which often lack a comprehensive cell annotation. This limitation can affect the accuracy and effectiveness of such experiments as benchmarking tools. To address this issue, we introduce omics benchmark experiments designed to evaluate bioinformatics tools to depict the heterogeneity in single-cell tumor experiments. We conducted single-cell RNA sequencing on six lung cancer tumor cell lines that display resistant clones upon treatment of EGFR mutated tumors and are characterized by driver genes, namely ROS1, ALK, HER2, MET, KRAS, and BRAF. These driver genes are associated with downstream networks controlled by EGFR mutations, such as JAK-STAT, PI3K-AKT-mTOR, and MEK-ERK. The experiment also featured an EGFR-mutated cell line. Using 10XGenomics platform with cellplex technology, we analyzed the seven cell lines together with a pseudo-immunological microenvironment consisting of PBMC cells labeled with the Biolegend TotalSeq™-B Human Universal Cocktail (CITEseq). This technology allowed for independent labeling of each cell line and single-cell analysis of the pooled seven cell lines and the pseudo-microenvironment. The data generated from the aforementioned experiments are available as part of an online tool, which allows users to define cell heterogeneity and generates count tables as an output. The tool provides the cell line derivation for each cell and cell annotations for the pseudo-microenvironment based on CITEseq data by an experienced immunologist. Additionally, we created a range of pseudo-tumor tissues using different ratios of the aforementioned cells embedded in matrigel. These tissues were analyzed using 10XGenomics (FFPE samples) and Curio Bioscience (fresh frozen samples) platforms for spatial transcriptomics, further expanding the scope of our benchmark experiments. The benchmark experiments we conducted provide a unique opportunity to evaluate the performance of bioinformatics tools for detecting and characterizing tumor heterogeneity at the single-cell level. Overall, our experiments provide a controlled and standardized environment for assessing the accuracy and robustness of bioinformatics tools for studying tumor heterogeneity at the single-cell level, which can ultimately lead to more precise and effective cancer diagnosis and treatment.Keywords: single cell omics, benchmark, spatial transcriptomics, CITEseq
Procedia PDF Downloads 10424668 Generation of Automated Alarms for Plantwide Process Monitoring
Authors: Hyun-Woo Cho
Abstract:
Earlier detection of incipient abnormal operations in terms of plant-wide process management is quite necessary in order to improve product quality and process safety. And generating warning signals or alarms for operating personnel plays an important role in process automation and intelligent plant health monitoring. Various methodologies have been developed and utilized in this area such as expert systems, mathematical model-based approaches, multivariate statistical approaches, and so on. This work presents a nonlinear empirical monitoring methodology based on the real-time analysis of massive process data. Unfortunately, the big data includes measurement noises and unwanted variations unrelated to true process behavior. Thus the elimination of such unnecessary patterns of the data is executed in data processing step to enhance detection speed and accuracy. The performance of the methodology was demonstrated using simulated process data. The case study showed that the detection speed and performance was improved significantly irrespective of the size and the location of abnormal events.Keywords: detection, monitoring, process data, noise
Procedia PDF Downloads 24224667 Meanings and Concepts of Standardization in Systems Medicine
Authors: Imme Petersen, Wiebke Sick, Regine Kollek
Abstract:
In systems medicine, high-throughput technologies produce large amounts of data on different biological and pathological processes, including (disturbed) gene expressions, metabolic pathways and signaling. The large volume of data of different types, stored in separate databases and often located at different geographical sites have posed new challenges regarding data handling and processing. Tools based on bioinformatics have been developed to resolve the upcoming problems of systematizing, standardizing and integrating the various data. However, the heterogeneity of data gathered at different levels of biological complexity is still a major challenge in data analysis. To build multilayer disease modules, large and heterogeneous data of disease-related information (e.g., genotype, phenotype, environmental factors) are correlated. Therefore, a great deal of attention in systems medicine has been put on data standardization, primarily to retrieve and combine large, heterogeneous datasets into standardized and incorporated forms and structures. However, this data-centred concept of standardization in systems medicine is contrary to the debate in science and technology studies (STS) on standardization that rather emphasizes the dynamics, contexts and negotiations of standard operating procedures. Based on empirical work on research consortia that explore the molecular profile of diseases to establish systems medical approaches in the clinic in Germany, we trace how standardized data are processed and shaped by bioinformatics tools, how scientists using such data in research perceive such standard operating procedures and which consequences for knowledge production (e.g. modeling) arise from it. Hence, different concepts and meanings of standardization are explored to get a deeper insight into standard operating procedures not only in systems medicine, but also beyond.Keywords: data, science and technology studies (STS), standardization, systems medicine
Procedia PDF Downloads 33324666 Integrated On-Board Diagnostic-II and Direct Controller Area Network Access for Vehicle Monitoring System
Authors: Kavian Khosravinia, Mohd Khair Hassan, Ribhan Zafira Abdul Rahman, Syed Abdul Rahman Al-Haddad
Abstract:
The CAN (controller area network) bus is introduced as a multi-master, message broadcast system. The messages sent on the CAN are used to communicate state information, referred as a signal between different ECUs, which provides data consistency in every node of the system. OBD-II Dongles that are based on request and response method is the wide-spread solution for extracting sensor data from cars among researchers. Unfortunately, most of the past researches do not consider resolution and quantity of their input data extracted through OBD-II technology. The maximum feasible scan rate is only 9 queries per second which provide 8 data points per second with using ELM327 as well-known OBD-II dongle. This study aims to develop and design a programmable, and latency-sensitive vehicle data acquisition system that improves the modularity and flexibility to extract exact, trustworthy, and fresh car sensor data with higher frequency rates. Furthermore, the researcher must break apart, thoroughly inspect, and observe the internal network of the vehicle, which may cause severe damages to the expensive ECUs of the vehicle due to intrinsic vulnerabilities of the CAN bus during initial research. Desired sensors data were collected from various vehicles utilizing Raspberry Pi3 as computing and processing unit with using OBD (request-response) and direct CAN method at the same time. Two types of data were collected for this study. The first, CAN bus frame data that illustrates data collected for each line of hex data sent from an ECU and the second type is the OBD data that represents some limited data that is requested from ECU under standard condition. The proposed system is reconfigurable, human-readable and multi-task telematics device that can be fitted into any vehicle with minimum effort and minimum time lag in the data extraction process. The standard operational procedure experimental vehicle network test bench is developed and can be used for future vehicle network testing experiment.Keywords: CAN bus, OBD-II, vehicle data acquisition, connected cars, telemetry, Raspberry Pi3
Procedia PDF Downloads 191