Search results for: mortality prediction

Authors: Oluwaponmile David Alao

Abstract:

Due to an increase in the death rate as a result of heart attack. There is need to develop a system that can be useful in the diagnosis of the disease at the medical centre. This system will help in preventing misdiagnosis that may occur from the medical practitioner or the physicians. In this research work, heart disease dataset obtained from UCI repository has been used to develop an intelligent prediction diagnosis system. The system is modeled on a feedforwad neural network and trained with back propagation neural network. A recognition rate of 86% is obtained from the testing of the network.

Keywords: heart disease, artificial neural network, diagnosis, prediction system

Procedia PDF Downloads 421

Authors: JingWei Yu, Hong Yang Yu

Abstract:

At present, the increasingly serious air pollution in various cities of China has made people pay more attention to the air quality index(hereinafter referred to as AQI) of their living areas. To face this situation, it is of great significance to predict air pollution in heavily polluted areas. In this paper, based on the time series model of LSTM, a spatiotemporal prediction model of PM2.5 concentration in Mianyang, Sichuan Province, is established. The model fully considers the temporal variability and spatial distribution characteristics of PM2.5 concentration. The spatial correlation of air quality at different locations is based on the Air quality status of other nearby monitoring stations, including AQI and meteorological data to predict the air quality of a monitoring station. The experimental results show that the method has good prediction accuracy that the fitting degree with the actual measured data reaches more than 0.7, which can be applied to the modeling and prediction of the spatial and temporal distribution of regional PM2.5 concentration.

Keywords: LSTM, PM2.5, neural networks, spatio-temporal prediction

Procedia PDF Downloads 98

Authors: Sadaf Sahar, Usman Qamar, Sadaf Ayaz

Abstract:

In the software development lifecycle, the quality prediction techniques hold a prime importance in order to minimize future design errors and expensive maintenance. There are many techniques proposed by various researchers, but with the increasing complexity of the software lifecycle model, it is crucial to develop a flexible system which can cater for the factors which in result have an impact on the quality of the end product. These factors include properties of the software development process and the product along with its operation conditions. In this paper, a neural network (perceptron) based software quality prediction technique is proposed. Using this technique, the stakeholders can predict the quality of the resulting software during the early phases of the lifecycle saving time and resources on future elimination of design errors and costly maintenance. This technique can be brought into practical use using successful training.

Keywords: software quality, fuzzy logic, perception, prediction

Procedia PDF Downloads 283

Authors: Njabulo Ncube, Elena Kulinskaya, Nicholas Steel, Dmitry Pshezhetskiy

Abstract:

Life expectancy in the United Kingdom (UK) has been near constant since 2010, particularly for the individuals of 65 years and older. This trend has been also noted in several other countries. This slowdown in the increase of life expectancy was concurrent with the increase in the number of deaths caused by non-communicable diseases. Of particular concern is the world-wide exponential increase in the number of diabetes related deaths. Previous studies have reported increased mortality hazards among diabetics compared to non-diabetics, and on the differing effects of antidiabetic drugs on mortality hazards. This study aimed to estimate the all-cause mortality hazards and related life expectancies among type 2 diabetes (T2DM) patients in the UK using the time-variant Gompertz-Cox model with frailty. The study also aimed to understand the major causes of the change in life expectancy growth in the last decade. A total of 221 182 (30.8% T2DM, 57.6% Males) individuals aged 50 years and above, born between 1930 and 1960, inclusive, and diagnosed between 2000 and 2016, were selected from The Health Improvement Network (THIN) database of the UK primary care data and followed up to 31 December 2016. About 13.4% of participants died during the follow-up period. The overall all-cause mortality hazard ratio of T2DM compared to non-diabetic controls was 1.467 (1.381-1.558) and 1.38 (1.307-1.457) when diagnosed between 50 to 59 years and 60 to 74 years, respectively. The estimated life expectancies among T2DM individuals without further comorbidities diagnosed at the age of 60 years were 2.43 (1930-1939 birth cohort), 2.53 (1940-1949 birth cohort) and 3.28 (1950-1960 birth cohort) years less than those of non-diabetic controls. However, the 1950-1960 birth cohort had a steeper hazard function compared to the 1940-1949 birth cohort for both T2DM and non-diabetic individuals. In conclusion, mortality hazards for people with T2DM continue to be higher than for non-diabetics. The steeper mortality hazard slope for the 1950-1960 birth cohort might indicate the sub-population contributing to a slowdown in the growth of the life expectancy.

Keywords: T2DM, Gompetz-Cox model with frailty, all-cause mortality, life expectancy

Procedia PDF Downloads 97

Authors: Gonzalez Carlos, Martinez Fransisco

Abstract:

There are various types of analysis that allow us to involve seismic phenomena that cause strong requirements for structures that are designed by society; one of them is a probabilistic analysis which works from prediction equations that have been created based on metadata seismic compiled in different regions. These equations form models that are used to describe the 5% damped pseudo spectra response for the various zones considering some easily known input parameters. The biggest problem for the creation of these models requires data with great robust statistics that support the results, and there are several places where this type of information is not available, for which the use of alternative methodologies helps to achieve adjustments to different models of seismic prediction.

Keywords: GMPM, 5% damped pseudo-response spectra, models of seismic prediction, PSHA

Procedia PDF Downloads 50

Authors: Shervin Alaei, Reza Moradi

Abstract:

Trading in financial markets is subject to risks due to their high volatilities. Here, using an LSTM neural network, and by doing some risk-based feature engineering tasks, we developed a method that can accurately predict trends of the Tehran stock exchange market index from a few days ago. Our test results have shown that the proposed method with an average prediction accuracy of more than 94% is superior to the other common machine learning algorithms. To the best of our knowledge, this is the first work incorporating deep learning and risk factors to accurately predict market trends.

Keywords: deep learning, LSTM, trend prediction, risk management, artificial neural networks

Procedia PDF Downloads 113

Authors: Shiva Kumar, G. S. Vijay, Srinivas Pai P., Shrinivasa Rao B. R.

Abstract:

In the present study RBF neural networks were used for predicting the performance and emission parameters of a biodiesel engine. Engine experiments were carried out in a 4 stroke diesel engine using blends of diesel and Honge methyl ester as the fuel. Performance parameters like BTE, BSEC, Tech and emissions from the engine were measured. These experimental results were used for ANN modeling. RBF center initialization was done by random selection and by using Clustered techniques. Network was trained by using fixed and varying widths for the RBF units. It was observed that RBF results were having a good agreement with the experimental results. Networks trained by using clustering technique gave better results than using random selection of centers in terms of reduced MRE and increased prediction accuracy. The average MRE for the performance parameters was 3.25% with the prediction accuracy of 98% and for emissions it was 10.4% with a prediction accuracy of 80%.

Keywords: radial basis function networks, emissions, performance parameters, fuzzy c means

Procedia PDF Downloads 528

Authors: A. Jatau, Q. Majeed, H. M. Bandiya

Abstract:

The efficacy of five local spices, namely; Hot pepper (Capsicum annum L.), Black pepper (Piper guinese Schum and Thonn), Sweet basil (Occimum canum Sim), African nut-meg (Monodora myristica Dunal), and Ginger (Zingiber officianale Ross) with conventional insecticide against the D. maculatus was studied under ambient laboratory conditions. The plants were pulverized into powders and applied at the rate of 1.0, 2.0 and 3.0g per 25g of disinfected dried fish. The same amount of fish (25g) was treated with 5ml of 1.0, 2.0 and 3.0 percent solution of conventional insecticide (dichlorvos) and air dried for 2hrs. Ten newly hatched 1st instar larvae (24hrs old) were introduced into each powdered smoked fish in separate beakers. Untreated control was also set up. Observation on the mortality and development were recorded daily until the larvae pupated. Each of the treated smoked fish showed significant (p<0.05) effect on the larval mortality and development when compared with the control. The Piper guinense was as efficacious as dichlorvos in killing all the larvae (100%) at all concentrations before pupation. Ocimum Canunm gave the second best results (50.00, 63.33 and 100%), while the other three spices resulted in less than 50% mortalities at all rate of application. The spice powders were also observed to have extended the larval developmental period. Thus, the spices tested can be recommended for the control of D. maculatus.

Keywords: development, dermestes maculatus, insecticide, local spices, mortality

Procedia PDF Downloads 227

Authors: Najade Sheriff, Malaz Elsaddig, Kevin Jones

Abstract:

Background: Death in the first month of life accounts for an increasing proportion of under-five mortality. Advancement to reduce this number is being made across the globe; however, progress is slowest in sub-Saharan Africa. Objectives: The study aims to identify differences between neonatal deaths of inpatient babies born in a hospital facility in rural Uganda to those of neonates admitted from the community and to explore whether they can be used to risk stratify neonatal admissions. Results: A retrospective chart review was conducted on records for neonates admitted to the Special Care Baby Unit (SCBU) Kitovu Hospital from 1st July 2016 to 21st July 2017. A total of 442 babies were admitted and the overall neonatal mortality was 24.8% (40% inpatient, 37% community, 23% hospital referrals). 40% of deaths occurred within 24 hours of admission and the majority were male (63%). 43% of babies were hypothermic upon admission, a significantly greater proportion of which were inpatient babies born in labour ward (P=0.0025). Intrapartum related death accounted for ½ of all inpatient babies whereas complications of prematurity were the predominant cause of death in the community group (37%). Severe infection does not seem like a significant factor of mortality for inpatients (2%) as it does for community admissions (29%). Furthermore, with 52.5% of community admissions weighing < 1500g, very low birth weight (VLBW) may be a significant risk factor for community neonatal death. Conclusion: The neonatal mortality rate in this study is high, and the leading causes of death are all largely preventable. A high rate of inpatient birth asphyxiation indicates the need for good quality facility-based perinatal care as well as a greater focus on the management of hypothermia, such as Kangaroo care. Moreover, a reduction in preterm deliveries is necessary to reduce associated comorbidities, and monitoring for signs of infection is especially important for community admissions.

Keywords: community, mortality, newborn, Uganda

Procedia PDF Downloads 165

Authors: Mohammadreza Mohebbi, Masoumeh Sanagou

Abstract:

The ability to predict clinical outcomes is of great importance to physicians and clinicians. A number of different methods have been used in an effort to accurately predict these outcomes. These methods include the development of scoring systems based on multivariate statistical modelling, and models involving the use of classification and regression trees. The process usually consists of two consecutive phases, namely model development and external validation. The model development phase consists of building a multivariate model and evaluating its predictive performance by examining calibration and discrimination, and internal validation. External validation tests the predictive performance of a model by assessing its calibration and discrimination in different but plausibly related patients. A motivate example focuses on prediction modeling using a sample of patients undergone coronary artery bypass graft (CABG) has been used for illustrative purpose and a set of primary considerations for evaluating prediction model studies using specific quality indicators as criteria to help stakeholders evaluate the quality of a prediction model study has been proposed.

Keywords: clinical prediction models, clinical decision rule, prognosis, external validation, model calibration, biostatistics

Procedia PDF Downloads 267

Authors: Sumaira Ashraf, Elisabete G.S. Félix, Zélia Serrasqueiro

Abstract:

Traditional financial distress prediction models performed well to predict bankrupt and insolvent firms of the developed markets. Previous studies particularly focused on the predictability of financial distress, financial failure, and bankruptcy of firms. This paper contributes to the literature by extending the definition of financial distress with the inclusion of early warning signs related to quotation of face value, dividend/bonus declaration, annual general meeting, and listing fee. The study used five well-known distress prediction models to see if they have the ability to predict early warning signs of financial distress. Results showed that the predictive ability of the models varies over time and decreases specifically for the sample with early warning signs of financial distress. Furthermore, the study checked the differences in the predictive ability of the models with respect to the financial crisis. The results conclude that the predictive ability of the traditional financial distress prediction models decreases for the firms with early warning signs of financial distress and during the time of financial crisis. The study developed a new model comprising significant variables from the five models and one new variable earning response. This new model outperforms the old distress prediction models before, during and after the financial crisis. Thus, it can be used by researchers, organizations and all other concerned parties to indicate early warning signs for the emerging markets.

Keywords: financial distress, emerging market, prediction models, Z-Score, logit analysis, probit model

Procedia PDF Downloads 219

Authors: P. Aarumugam, N. Krishnamoorthy, K. Gunasekaran

Abstract:

The mosquitoes with loss of minimum three legs especially the hind legs have the negative impact on the survival hood of mosquitoes. Three days old unfed adult female laboratory strain was selected in each generation against sublethal dosages (0.004%, 0.005%, 0.007% and 0.01%) of deltamethrin upto 40 generations. Impregnated papers with acetone were used for control. Every fourth generation, survived mosquitoes were observed for functional mortality. Hind legs lost were significantly (P< 0.05) higher in treated than the controls up to generation 24, thereafter no significant lost. In contrary, no significant forelegs lost among exposed mosquitoes. Middle legs lost were also not significant in the exposed mosquitoes except first generation (F1). The field strain (Chennai) did not show any significant loss of legs (fore or mid or hind) compared to the control. The selection pressure on mosquito population influences strong natural selection to develop various adaptive mechanisms.

Keywords: Anopheles stephensi, deltamethrin, functional mortality, synthetic pyrethroids

Procedia PDF Downloads 367

Authors: Mary Farrell, Maria Soubra, Sandra Vega, Dorothy Kakraba, Joanne Fontanilla, Moira Kendra, Danielle Tonzola, Stephanie Chiu

Abstract:

Pneumonia is the most common infectious cause of hospitalizations in the United States, with more than one million admissions annually and costs of $10 billion every year, making it the 8th leading cause of death. Aspiration pneumonia is an aggressive type of pneumonia that results from inhalation of oropharyngeal secretions and/or gastric contents and is preventable. The authors hypothesized that an evidence-based aspiration pneumonia clinical care pathway could reduce 30-day hospital readmissions and mortality rates, while improving the overall care of patients. We conducted a retrospective chart review on 979 patients discharged with aspiration pneumonia from January 2021 to December 2022 at Overlook Medical Center. The authors identified patients who were coded with aspiration pneumonia and/or stable sepsis. Secondarily, we identified 30-day readmission rates for aspiration pneumonia from a SNF. The Aspiration Pneumonia Clinical Care Pathway starts in the emergency department (ED) with the initiation of antimicrobials within 4 hours of admission and early recognition of aspiration. Once this is identified, a swallow test is initiated by the bedside nurse, and if the patient demonstrates dysphagia, they are maintained on strict nothing by mouth (NPO) followed by a speech and language pathologist (SLP) referral for an appropriate modified diet recommendation. Aspiration prevention techniques included the avoidance of straws, 45-degree positioning, no talking during meals, taking small bites, placement of the aspiration wrist band, and consuming meals out of the bed in a chair. Nursing education was conducted with a newly created online learning module about aspiration pneumonia. The authors identified 979 patients, with an average age of 73.5 years old, who were diagnosed with aspiration pneumonia on the index hospitalization. These patients were reviewed for a 30-day readmission for aspiration pneumonia or stable sepsis, and mortality rates from January 2021 to December 2022 at Overlook Medical Center (OMC). The 30-day readmission rates were significantly lower in the cohort that received the clinical care pathway (35.0% vs. 27.5%, p = 0.011). When evaluating the mortality rates in the pre and post intervention cohort the authors discovered the mortality rates were lower in the post intervention cohort (23.7% vs 22.4%, p = 0.61) Mortality among non-white (self-reported as non-white) patients were lower in the post intervention cohort (34.4% vs. 21.0% , p = 0.05). Patients who reported as a current smoker/vaper in the pre and post cohorts had increased mortality rates (5.9% vs 22%). There was a decrease in mortality for the male population but an increase in mortality for women in the pre and post cohorts (19% vs. 25%). The authors attributed this increase in mortality in the post intervention cohort to more active smokers, more former smokers, and more being admitted from a SNF. This research identified that implementation of an Aspiration Pneumonia Clinical Care Pathway showed a statistically significant decrease in readmission rates and mortality rates in non-whites. The 30-day readmission rates were lower in the cohort that received the clinical care pathway (35.0% vs. 27.5%, p = 0.011).

Keywords: aspiration pneumonia, mortality, quality improvement, 30-day pneumonia readmissions

Procedia PDF Downloads 26

Authors: Haoming Ma, Guo Yu, Peiru Zhou

Abstract:

Background: Previous studies show that dysglycemia, mostly hyperglycemia, hypoglycemia and glycemic variability(GV), are associated with excess mortality in critically ill patients, especially those without diabetes. Glycemic variability is an increasingly important measure of glucose control in the intensive care unit (ICU) due to this association. However, there is limited data pertaining to the relationship between different clinical factors and glycemic variability and clinical outcomes categorized by their DM status. This retrospective study of 958 intensive care unit(ICU) patients was conducted to investigate the relationship between GV and outcome in critically ill patients and further to determine the significant factors that contribute to the glycemic variability. Aim: We hypothesize that the factors contributing to mortality and the glycemic variability are different from critically ill patients with or without diabetes. And the primary aim of this study was to determine which dysglycemia (hyperglycemia\hypoglycemia\glycemic variability) is independently associated with an increase in mortality among critically ill patients in different groups (DM/Non-DM). Secondary objectives were to further investigate any factors affecting the glycemic variability in two groups. Method: A total of 958 diabetic and non-diabetic patients with severe diseases in the ICU were selected for this retrospective analysis. The glycemic variability was defined as the coefficient of variation (CV) of blood glucose. The main outcome was death during hospitalization. The secondary outcome was GV. The logistic regression model was used to identify factors associated with mortality. The relationships between GV and other variables were investigated using linear regression analysis. Results: Information on age, APACHE II score, GV, gender, in-ICU treatment and nutrition was available for 958 subjects. Predictors remaining in the final logistic regression model for mortality were significantly different in DM/Non-DM groups. Glycemic variability was associated with an increase in mortality in both DM(odds ratio 1.05; 95%CI:1.03-1.08,p＜0.001) or Non-DM group(odds ratio 1.07; 95%CI:1.03-1.11,p=0.002). For critically ill patients without diabetes, factors associated with glycemic variability included APACHE II score(regression coefficient, 95%CI:0.29,0.22-0.36,p＜0.001), Mean BG(0.73,0.46-1.01,p＜0.001), total parenteral nutrition(2.87,1.57-4.17,p＜0.001), serum albumin(-0.18,-0.271 to -0.082,p＜0.001), insulin treatment(2.18,0.81-3.55,p=0.002) and duration of ventilation(0.006,0.002-1.010,p=0.003).However, for diabetes patients, APACHE II score(0.203,0.096-0.310,p＜0.001), mean BG(0.503,0.138-0.869,p=0.007) and duration of diabetes(0.167,0.033-0.301,p=0.015) remained as independent risk factors of GV. Conclusion: We found that the relation between dysglycemia and mortality is different in the diabetes and non-diabetes groups. And we confirm that GV was associated with excess mortality in DM or Non-DM patients. Furthermore, APACHE II score, Mean BG, total parenteral nutrition, serum albumin, insulin treatment and duration of ventilation were significantly associated with an increase in GV in Non-DM patients. While APACHE II score, mean BG and duration of diabetes (years) remained as independent risk factors of increased GV in DM patients. These findings provide important context for further prospective trials investigating the effect of different clinical factors in critically ill patients with or without diabetes.

Keywords: diabetes, glycemic variability, predictors, severe disease

Procedia PDF Downloads 153

Authors: Li Kewen, Su Zhaoxin, Wang Xingmou, Zhu Jian Bing

Abstract:

Conventional reservoir prediction methods ar not sufficient to explore the implicit relation between seismic attributes, and thus data utilization is low. In order to improve the predictive classification accuracy of reservoir lithology, this paper proposes a deep learning lithology prediction method based on ResNet (Residual Neural Network) and SENet (Squeeze-and-Excitation Neural Network). The neural network model is built and trained by using seismic attribute data and lithology data of Shengli oilfield, and the nonlinear mapping relationship between seismic attribute and lithology marker is established. The experimental results show that this method can significantly improve the classification effect of reservoir lithology, and the classification accuracy is close to 70%. This study can effectively predict the lithology of undrilled area and provide support for exploration and development.

Keywords: convolutional neural network, lithology, prediction of reservoir, seismic attributes

Procedia PDF Downloads 145

Authors: Trupti Diwan

Abstract:

Predicting student failure at school has changed into a difficult challenge due to both the large number of factors that can affect the reduced performance of students and the imbalanced nature of these kinds of data sets. This paper surveys the two elements needed to make prediction on Students’ Academic Performances which are parameters and methods. This paper also proposes a framework for predicting the performance of engineering students. Genetic programming can be used to predict student failure/success. Ranking algorithm is used to rank students according to their credit points. The framework can be used as a basis for the system implementation & prediction of students’ Academic Performance in Higher Learning Institute.

Keywords: classification, educational data mining, student failure, grammar-based genetic programming

Procedia PDF Downloads 399

Authors: Gunjan Srivastava, Shamila Kalia

Abstract:

Dalbergia sissoo Roxb., (Family- Leguminosae; Subfamily- Papilionoideae), is an economically and ecologically important tree species having medicinal value. Of the rich complex of insect fauna, ten have been recognized as potential pests of nurseries and plantations. Present study was conducted to explore an effective ecofriendly control of Dichomeris eridantis Meyrick, an important defoliator pest of D. sissoo. Health and environmental concerns demanded devising a bio-intensive pest management strategy and employing ecofriendly measures. In the present laboratory bioassay two entomopathogenic fungi Acremonium perscinum and Beauveria bassiana were tested and compared for evaluating the efficacy of their seven different concentrations (besides control) against the 3rd, 4th and 5th instar larvae of D. eridantis, on the basis of mean percent mortality data recorded and tabulated for seven days after treatment application. Analysis showed that both treatments vary significantly among themselves. Also, variations amongst instars and duration with respect to their mortality were highly significant (p < .001). All their interactions were found to vary significantly. B. bassiana at 0.25x107 spores / ml spore concentration caused maximum mean percent mortality (62.38%) followed by mean percent mortality at its 0.25x106 spores / ml concentration (56.67%). Mean percent mortality at maximum spore concentration (0.054x107 spores / ml) and next highest spore concentration (0.054 x106 spores / ml) due to A. perscinum treatment were far less effective (mean percent mortality of 45.40% and 31.29%, respectively). At 168 hours mean percent mortality of larval instars due to both fungal treatment applications reached its maximum (52.99%) whereas, at 24 hours mean percent mortality remained least (5.70%). In both cases, treatments were most effective against 3rd instar larvae and least effective against 5th instar larvae. A comparative acccount of efficacy of B. bassiana and A. perscinum on the 3rd, 4th and 5th instar larvae of D. eridantis on 5th, 6th and 7th post treatment observation days after their application, on the basis of their median lethal concentrations (LC50) proved B. bassiana to be more potential microbial pathogen of the two fungal microbes, for all the three instars (3rd, 4th and 5th) of D. eridantis, on all the three days (5th, 6th and 7th post observation days after application of both treatments). Percent mortality of D. eridantis increased in a dose dependent manner. Koch’s Postulates tested positive, thus confirming the pathogenicity of B. bassiana against the larval instars of D. eridantis. LC90 values of 0.280x1011 spores/ml, 0.301x108 spores/ml and 0.262x108 spores/ml concentrations of B. bassiana were standardized which can effectively cause mortality of all the larval instars of D. eridantis in the field after 5th, 6th and 7th day of their application, respectively. Therefore, these concentrations can be safely used in nurseries as well as plantations of D. sissoo for effective control of D. eridantis larvae.

Keywords: Acremonium perscinum, Beauveria bassiana, Dalbergia sissoo, Dichomeris eridantis

Procedia PDF Downloads 201

Authors: Smail Tigani, Mohamed Ouzzif

Abstract:

This work presents a discrete quantitative state prediction algorithm with intelligent behavior making it able to self-improve some performance aspects. The specificity of this algorithm is the capacity of self-rectification of the prediction strategy before the final decision. The auto-rectification mechanism is based on two parallel mathematical models. In one hand, the algorithm predicts the next state based on event transition matrix updated after each observation. In the other hand, the algorithm extracts its residues trend with a linear regression representing historical residues data-points in order to rectify the first decision if needs. For a normal distribution, the interactivity between the two models allows the algorithm to self-optimize its performance and then make better prediction. Designed key performance indicator, computed during a Monte Carlo simulation, shows the advantages of the proposed approach compared with traditional one.

Keywords: discrete state, Markov Chains, linear regression, auto-adaptive systems, decision making, Monte Carlo Simulation

Procedia PDF Downloads 475

Authors: Pei Yi Lin

Abstract:

Objective: The objective of this study is to use machine learning methods to build an early prediction classifier model for acute delirium to improve the quality of medical care for intensive care patients. Background: Delirium is a common acute and sudden disturbance of consciousness in critically ill patients. After the occurrence, it is easy to prolong the length of hospital stay and increase medical costs and mortality. In 2021, the incidence of delirium in the intensive care unit of internal medicine was as high as 59.78%, which indirectly prolonged the average length of hospital stay by 8.28 days, and the mortality rate is about 2.22% in the past three years. Therefore, it is expected to build a delirium prediction classifier through big data analysis and machine learning methods to detect delirium early. Method: This study is a retrospective study, using the artificial intelligence big data database to extract the characteristic factors related to delirium in intensive care unit patients and let the machine learn. The study included patients aged over 20 years old who were admitted to the intensive care unit between May 1, 2022, and December 31, 2022, excluding GCS assessment <4 points, admission to ICU for less than 24 hours, and CAM-ICU evaluation. The CAMICU delirium assessment results every 8 hours within 30 days of hospitalization are regarded as an event, and the cumulative data from ICU admission to the prediction time point are extracted to predict the possibility of delirium occurring in the next 8 hours, and collect a total of 63,754 research case data, extract 12 feature selections to train the model, including age, sex, average ICU stay hours, visual and auditory abnormalities, RASS assessment score, APACHE-II Score score, number of invasive catheters indwelling, restraint and sedative and hypnotic drugs. Through feature data cleaning, processing and KNN interpolation method supplementation, a total of 54595 research case events were extracted to provide machine learning model analysis, using the research events from May 01 to November 30, 2022, as the model training data, 80% of which is the training set for model training, and 20% for the internal verification of the verification set, and then from December 01 to December 2022 The CU research event on the 31st is an external verification set data, and finally the model inference and performance evaluation are performed, and then the model has trained again by adjusting the model parameters. Results: In this study, XG Boost, Random Forest, Logistic Regression, and Decision Tree were used to analyze and compare four machine learning models. The average accuracy rate of internal verification was highest in Random Forest (AUC=0.86), and the average accuracy rate of external verification was in Random Forest and XG Boost was the highest, AUC was 0.86, and the average accuracy of cross-validation was the highest in Random Forest (ACC=0.77). Conclusion: Clinically, medical staff usually conduct CAM-ICU assessments at the bedside of critically ill patients in clinical practice, but there is a lack of machine learning classification methods to assist ICU patients in real-time assessment, resulting in the inability to provide more objective and continuous monitoring data to assist Clinical staff can more accurately identify and predict the occurrence of delirium in patients. It is hoped that the development and construction of predictive models through machine learning can predict delirium early and immediately, make clinical decisions at the best time, and cooperate with PADIS delirium care measures to provide individualized non-drug interventional care measures to maintain patient safety, and then Improve the quality of care.

Keywords: critically ill patients, machine learning methods, delirium prediction, classifier model

Procedia PDF Downloads 36

Authors: Seyed Esmail Seyedi Bariran, Khairul Salleh Mohamed Sahari

Abstract:

In multi-echelon supply chain networks, optimal supplier selection significantly depends on the accuracy of suppliers’ performance prediction. Different methods of multi criteria decision making such as ANN, GA, Fuzzy, AHP, etc have been previously used to predict the supplier performance but the “black-box” characteristic of these methods is yet a major concern to be resolved. Therefore, the primary objective in this paper is to implement an artificial intelligence-based gene expression programming (GEP) model to compare the prediction accuracy with that of ANN. A full factorial design with %95 confidence interval is initially applied to determine the appropriate set of criteria for supplier performance evaluation. A test-train approach is then utilized for the ANN and GEP exclusively. The training results are used to find the optimal network architecture and the testing data will determine the prediction accuracy of each method based on measures of root mean square error (RMSE) and correlation coefficient (R2). The results of a case study conducted in Supplying Automotive Parts Co. (SAPCO) with more than 100 local and foreign supply chain members revealed that, in comparison with ANN, gene expression programming has a significant preference in predicting supplier performance by referring to the respective RMSE and R-squared values. Moreover, using GEP, a mathematical function was also derived to solve the issue of ANN black-box structure in modeling the performance prediction.

Keywords: Supplier Performance Prediction, ANN, GEP, Automotive, SAPCO

Procedia PDF Downloads 391

Authors: Hervice Roméo Fogno Fotsoa, Germaine Djuidje Kenmoe, Claude Vidal Aloyem Kazé

Abstract:

One of the main applications of machine learning is the prediction of time series. But a more accurate prediction requires a more optimal model of machine learning. Several optimization techniques have been developed, but without considering the input variables disposition of the system. Thus, this work aims to present a new machine learning architecture optimization technique based on their optimal input variables disposition. The validations are done on the prediction of wind time series, using data collected in Cameroon. The number of possible dispositions with four input variables is determined, i.e., twenty-four. Each of the dispositions is used to perform the prediction, with the main criteria being the training and prediction performances. The results obtained from a static architecture and a dynamic architecture of neural networks have shown that these performances are a function of the input variable's disposition, and this is in a different way from the architectures. This analysis revealed that it is necessary to take into account the input variable's disposition for the development of a more optimal neural network model. Thus, a new neural network training algorithm is proposed by introducing the search for the optimal input variables disposition in the traditional back-propagation algorithm. The results of the application of this new optimization approach on the two single neural network architectures are compared with the previously obtained results step by step. Moreover, this proposed approach is validated in a collaborative optimization method with a single objective optimization technique, i.e., genetic algorithm back-propagation neural networks. From these comparisons, it is concluded that each proposed model outperforms its traditional model in terms of training and prediction performance of time series. Thus the proposed optimization approach can be useful in improving the accuracy of time series forecasts. This proves that the proposed optimization approach can be useful in improving the accuracy of time series prediction based on machine learning.

Keywords: input variable disposition, machine learning, optimization, performance, time series prediction

Procedia PDF Downloads 67

Authors: Belkacem Selma, Boumediene Selma, Tourkia Guerzou, Abbes Labdelli

Abstract:

Natural disasters have occurred and will continue to cause human and material damage. Therefore, the idea of "preventing" natural disasters will never be possible. However, their prediction is possible with the advancement of technology. Even if natural disasters are effectively inevitable, their consequences may be partly controlled. The rapid growth and progress of artificial intelligence (AI) had a major impact on the prediction of natural disasters and risk assessment which are necessary for effective disaster reduction. The Earthquakes prediction to prevent the loss of human lives and even property damage is an important factor; that is why it is crucial to develop techniques for predicting this natural disaster. This present study aims to analyze the ability of artificial neural networks (ANNs) to predict earthquakes that occur in a given area. The used data describe the problem of high energy (higher than 10^4J) seismic bumps forecasting in a coal mine using two long walls as an example. For this purpose, seismic bumps data obtained from mines has been analyzed. The results obtained show that the ANN with high accuracy was able to predict earthquake parameters; the classification accuracy through neural networks is more than 94%, and that the models developed are efficient and robust and depend only weakly on the initial database.

Keywords: earthquake prediction, ANN, seismic bumps

Procedia PDF Downloads 95

Authors: The Danh Phan

Abstract:

House price forecasting is a main topic in the real estate market research. Effective house price prediction models could not only allow home buyers and real estate agents to make better data-driven decisions but may also be beneficial for the property policymaking process. This study investigates the housing market by using machine learning techniques to analyze real historical house sale transactions in Australia. It seeks useful models which could be deployed as an application for house buyers and sellers. Data analytics show a high discrepancy between the house price in the most expensive suburbs and the most affordable suburbs in the city of Melbourne. In addition, experiments demonstrate that the combination of Stepwise and Support Vector Machine (SVM), based on the Mean Squared Error (MSE) measurement, consistently outperforms other models in terms of prediction accuracy.

Keywords: house price prediction, regression trees, neural network, support vector machine, stepwise

Procedia PDF Downloads 187

Authors: S. Madhusudhan, G. V. Vaniprabha

Abstract:

Worldwide statistics have shown that smoking contributes significantly to mortality, with nicotine, being more addictive. Smoking causes more than 7,00,000 deaths/year in India. Compared to the general population, the prevalence of smoking is found to be much higher among people with psychotic disorders and, more so in schizophrenia. Schizophrenic patients who smoke tend to have higher frequency of heavy smoking, with rates ranging from 60% to as high as 80%. Hence, smokers with psychiatric disorders suffer higher rates of morbidity and mortality secondary to smoking related illnesses.

Keywords: brief intervention, nicotine dependence, schizophrenia

Procedia PDF Downloads 356

Authors: Jitka Rychtarikova

Abstract:

Regional differences in mortality in the Czech Republic (CR) may be moderate from a broader European perspective, but important discrepancies in life expectancy can be found between smaller territorial units. In this study territorial units are based on Administrative Districts of Municipalities with Extended Powers (MEP). This definition came into force January 1, 2003. There are 205 units and the city of Prague. MEP represents the smallest unit for which mortality patterns based on life tables can be investigated and the Czech Statistical Office has been calculating such life tables (every five-years) since 2004. MEP life tables from 2009-2013 for males and females allowed the investigation of three main life cycles with the use of temporary life expectancies between the exact ages of 0 and 35; 35 and 65; and the life expectancy at exact age 65. The results showed regional survival inequalities primarily in adult and older ages. Consequently, only mortality indicators for adult and elderly population were related to census 2011 unlinked data for the same age groups. The most relevant socio-economic factors taken from the census are: having a partner, educational level and unemployment rate. The unemployment rate was measured for adults aged 35-64 completed years. Exploratory spatial data analysis methods were used to detect regional patterns in spatially contiguous units of MEP. The presence of spatial non-stationarity (spatial autocorrelation) of mortality levels for male and female adults (35-64), and elderly males and females (65+) was tested using global Moran’s I. Spatial autocorrelation of mortality patterns was mapped using local Moran’s I with the intention to depict clusters of low or high mortality and spatial outliers for two age groups (35-64 and 65+). The highest Moran’s I was observed for male temporary life expectancy between exact ages 35 and 65 (0.52) and the lowest was among women with life expectancy of 65 (0.26). Generally, men showed stronger spatial autocorrelation compared to women. The relationship between mortality indicators such as life expectancies and socio-economic factors like the percentage of males/females having a partner; percentage of males/females with at least higher secondary education; and percentage of unemployed males/females from economically active population aged 35-64 years, was evaluated using multiple regression (OLS). The results were then compared to outputs from geographically weighted regression (GWR). In the Czech Republic, there are two broader territories North-West Bohemia (NWB) and North Moravia (NM), in which excess mortality is well established. Results of the t-test of spatial regression showed that for males aged 30-64 the association between mortality and unemployment (when adjusted for education and partnership) was stronger in NM compared to NWB, while educational level impacted the length of survival more in NWB. Geographic variation and relationships in mortality of the CR MEP will also be tested using the spatial Durbin approach. The calculations were conducted by means of ArcGIS 10.6 and SAS 9.4.

Keywords: Czech Republic, mortality, municipality, socio-economic factors, spatial analysis

Procedia PDF Downloads 92

Authors: Yong Zhao, Jian He, Cheng Zhang

Abstract:

Cardiovascular diseases caused by hypertension are extremely threatening to human health, and early diagnosis of hypertension can save a large number of lives. Traditional hypertension detection methods require special equipment and are difficult to detect continuous blood pressure changes. In this regard, this paper first analyzes the principle of heart rate variability (HRV) and introduces sliding window and power spectral density (PSD) to analyze the time domain features and frequency domain features of HRV, and secondly, designs an HRV-based hypertension prediction network by combining Resnet, attention mechanism, and multilayer perceptron, which extracts the frequency domain through the improved ResNet18 features through a modified ResNet18, its fusion with time-domain features through an attention mechanism, and the auxiliary prediction of hypertension through a multilayer perceptron. Finally, the network was trained and tested using the publicly available SHAREE dataset on PhysioNet, and the test results showed that this network achieved 92.06% prediction accuracy for hypertension and outperformed K Near Neighbor(KNN), Bayes, Logistic, and traditional Convolutional Neural Network(CNN) models in prediction performance.

Keywords: feature extraction, heart rate variability, hypertension, residual networks

Procedia PDF Downloads 63

Authors: Gagandeep Singh Grover, Vini Mahajan, Bhagmal, Priti Thaware, Jaspreet Takkar

Abstract:

Dengue is a mosquito-borne viral disease endemic in many countries in the tropics and sub-tropics. The state of Punjab in India shows cyclical and seasonal variation in dengue cases. The Case Fatality Rate of Dengue has ranged from 0.6 to 1.0 in the past years. The department has initiated a review of the cases that have died due to dengue in order to know the exact cause of the death in a case of dengue. The study has been undertaken to know the other associated co-morbidities and factors causing death in a case of dengue. The study used the predesigned proforma on which the records (medical and Lab) were recorded and reviewed by the expert committee of the doctors. This study has revealed that cases of dengue having co-morbidities have a longer stay in the hospital. Fluid overload and co-morbidities have been found as major factors leading to death, however, in a confirmed case of dengue hepatorenal shutdown was found to be a major cause of mortality. The data obtained will help in sensitizing the treating physicians in order to decrease the mortality due to dengue in future.

Keywords: dengue, death, morbidities, DHF, DSS

Procedia PDF Downloads 270

Authors: Mo-Se Lee, Cheol-Hwi Ahn, Kee-Young Kwahk, Hyunchul Ahn

Abstract:

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN (Convolutional Neural Network), which is known as effective solution for recognizing and classifying images, has been popularly applied to classification and prediction problems in various fields. In this study, we try to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. In specific, we propose to apply CNN as the binary classifier that predicts stock market direction (up or down) by using a graph as its input. That is, our proposal is to build a machine learning algorithm that mimics a person who looks at the graph and predicts whether the trend will go up or down. Our proposed model consists of four steps. In the first step, it divides the dataset into 5 days, 10 days, 15 days, and 20 days. And then, it creates graphs for each interval in step 2. In the next step, CNN classifiers are trained using the graphs generated in the previous step. In step 4, it optimizes the hyper parameters of the trained model by using the validation dataset. To validate our model, we will apply it to the prediction of KOSPI200 for 1,986 days in eight years (from 2009 to 2016). The experimental dataset will include 14 technical indicators such as CCI, Momentum, ROC and daily closing price of KOSPI200 of Korean stock market.

Keywords: convolutional neural network, deep learning, Korean stock market, stock market prediction

Procedia PDF Downloads 406

Authors: Afroze Ibrahim Baqapuri, Ilya Trofimov

Abstract:

Sponsored search is a multi-billion dollar industry and makes up a major source of revenue for search engines (SE). Click-through-rate (CTR) estimation plays a crucial role for ads selection, and greatly affects the SE revenue, advertiser traffic and user experience. We propose a novel architecture of solving CTR prediction problem by combining artificial neural networks (ANN) with decision trees. First, we compare ANN with respect to other popular machine learning models being used for this task. Then we go on to combine ANN with MatrixNet (proprietary implementation of boosted trees) and evaluate the performance of the system as a whole. The results show that our approach provides a significant improvement over existing models.

Keywords: neural networks, sponsored search, web advertisement, click prediction, click-through rate

Procedia PDF Downloads 547

Authors: Nelson Rotimi Osungbemiro, Sanni Rafiu Olugbenga, Abayomi Olufemi Olajuyigbe

Abstract:

Ninety Fingerlings of Clarias gariepinus were exposed to the pathogenic Flavobacterium columnare a Gram Negative bacteria responsible for high mortality in fish pond raised young fish (fries and fingerlings) of Clarias sp. in Southwestern Nigeria. After feeding with 40% crude protein pelletized fish feed for 5 days, the fishes were divided into two groups, one group was treated with extracts from Calendula officinalis flowers, while the second group was not treated (control). The results indicated that, at day 5, colony formation had been manifesting and at day 7, skin lesion occurred and at the 8th day, first mortality of fish occurred, and this continued steadily on the 9th-12th day when all the fishes were dead. Whereas, in the group that was treated with Calendula sp., no single mortality was recorded. This research shows that plant extract from Calendula flowers is an effective antimicrobial agent against the virulent pathogenic Flavobacterium columnare disease.

Keywords: antimicrobial, Flavobacterium columnare, Clarias gariepinus, fish

Procedia PDF Downloads 572