Search results for: neural pathways

Authors: Diogo José Morgado Rebelo, Francisco António Carneiro Pacheco de Andrade, Paulo Jorge Freitas de Oliveira Novais

Abstract:

Not everything in AI-power consumer credit scoring turns out to be a wonder. When using AI in Creditworthiness Assessment (CWA), opacity and unfairness ‘sins’ must be considered to the task be deemed Responsible. AI software is not always 100% accurate, which can lead to misclassification. Discrimination of some groups can be exponentiated. A hetero personalized identity can be imposed on the individual(s) affected. Also, autonomous CWA sometimes lacks transparency when using black box models. However, for this intended purpose, human analysts ‘on-the-loop’ might not be the best remedy consumers are looking for in credit. This study seeks to explore the legality of implementing a Multi-Agent System (MAS) framework in consumer CWA to ensure compliance with the regulation outlined in Article 14(4) of the Proposal for an Artificial Intelligence Act (AIA), dated 21 April 2021 (as per the last corrigendum by the European Parliament on 19 April 2024), Especially with the adoption of Art. 18(8)(9) of the EU Directive 2023/2225, of 18 October, which will go into effect on 20 November 2026, there should be more emphasis on the need for hybrid oversight in AI-driven scoring to ensure fairness and transparency. In fact, the range of EU regulations on AI-based consumer credit will soon impact the AI lending industry locally and globally, as shown by the broad territorial scope of AIA’s Art. 2. Consequently, engineering the law of consumer’s CWA is imperative. Generally, the proposed MAS framework consists of several layers arranged in a specific sequence, as follows: firstly, the Data Layer gathers legitimate predictor sets from traditional sources; then, the Decision Support System Layer, whose Neural Network model is trained using k-fold Cross Validation, provides recommendations based on the feeder data; the eXplainability (XAI) multi-structure comprises Three-Step-Agents; and, lastly, the Oversight Layer has a 'Bottom Stop' for analysts to intervene in a timely manner. From the analysis, one can assure a vital component of this software is the XAY layer. It appears as a transparent curtain covering the AI’s decision-making process, enabling comprehension, reflection, and further feasible oversight. Local Interpretable Model-agnostic Explanations (LIME) might act as a pillar by offering counterfactual insights. SHapley Additive exPlanation (SHAP), another agent in the XAI layer, could address potential discrimination issues, identifying the contribution of each feature to the prediction. Alternatively, for thin or no file consumers, the Suggestion Agent can promote financial inclusion. It uses lawful alternative sources such as the share of wallet, among others, to search for more advantageous solutions to incomplete evaluation appraisals based on genetic programming. Overall, this research aspires to bring the concept of Machine-Centered Anthropocentrism to the table of EU policymaking. It acknowledges that, when put into service, credit analysts no longer exert full control over the data-driven entities programmers have given ‘birth’ to. With similar explanatory agents under supervision, AI itself can become self-accountable, prioritizing human concerns and values. AI decisions should not be vilified inherently. The issue lies in how they are integrated into decision-making and whether they align with non-discrimination principles and transparency rules.

Keywords: creditworthiness assessment, hybrid oversight, machine-centered anthropocentrism, EU policymaking

Procedia PDF Downloads 33

Authors: Anjalika Fernando, Banuka Athuraliya

Abstract:

This paper presents a comprehensive approach for converting Sinhala Sign Language (SSL) into grammatically correct sentences using Natural Language Processing (NLP) techniques in real-time. While previous studies have explored various aspects of SSL translation, the research gap lies in the absence of grammar checking for SSL. This work aims to bridge this gap by proposing a two-stage methodology that leverages deep learning models to detect signs and translate them into coherent sentences, ensuring grammatical accuracy. The first stage of the approach involves the utilization of a Long Short-Term Memory (LSTM) deep learning model to recognize and interpret SSL signs. By training the LSTM model on a dataset of SSL gestures, it learns to accurately classify and translate these signs into textual representations. The LSTM model achieves a commendable accuracy rate of 94%, demonstrating its effectiveness in accurately recognizing and translating SSL gestures. Building upon the successful recognition and translation of SSL signs, the second stage of the methodology focuses on improving the grammatical correctness of the translated sentences. The project employs a Neural Machine Translation (NMT) architecture, consisting of an encoder and decoder with LSTM components, to enhance the syntactical structure of the generated sentences. By training the NMT model on a parallel corpus of Sinhala wrong sentences and their corresponding grammatically correct translations, it learns to generate coherent and grammatically accurate sentences. The NMT model achieves an impressive accuracy rate of 98%, affirming its capability to produce linguistically sound translations. The proposed approach offers significant contributions to the field of SSL translation and grammar correction. Addressing the critical issue of grammar checking, it enhances the usability and reliability of SSL translation systems, facilitating effective communication between hearing-impaired and non-sign language users. Furthermore, the integration of deep learning techniques, such as LSTM and NMT, ensures the accuracy and robustness of the translation process. This research holds great potential for practical applications, including educational platforms, accessibility tools, and communication aids for the hearing-impaired. Furthermore, it lays the foundation for future advancements in SSL translation systems, fostering inclusive and equal opportunities for the deaf community. Future work includes expanding the existing datasets to further improve the accuracy and generalization of the SSL translation system. Additionally, the development of a dedicated mobile application would enhance the accessibility and convenience of SSL translation on handheld devices. Furthermore, efforts will be made to enhance the current application for educational purposes, enabling individuals to learn and practice SSL more effectively. Another area of future exploration involves enabling two-way communication, allowing seamless interaction between sign-language users and non-sign-language users.In conclusion, this paper presents a novel approach for converting Sinhala Sign Language gestures into grammatically correct sentences using NLP techniques in real time. The two-stage methodology, comprising an LSTM model for sign detection and translation and an NMT model for grammar correction, achieves high accuracy rates of 94% and 98%, respectively. By addressing the lack of grammar checking in existing SSL translation research, this work contributes significantly to the development of more accurate and reliable SSL translation systems, thereby fostering effective communication and inclusivity for the hearing-impaired community

Keywords: Sinhala sign language, sign Language, NLP, LSTM, NMT

Procedia PDF Downloads 103

Authors: Alexandra Papagianni, George Filis, Panagiotis Papadopoulos

Abstract:

The liberalization of the energy market and the increasing penetration of fluctuating renewables (e.g., wind and solar power) have heightened the importance of the spot market for ensuring efficient electricity supply. This is further emphasized by the EU’s goal of achieving net-zero emissions by 2050. The day-ahead market (DAM) plays a key role in European energy trading, accounting for 80-90% of spot transactions and providing critical insights for next-day pricing. Therefore, short-term electricity price forecasting (EPF) within the DAM is crucial for market participants to make informed decisions and improve their market positioning. Existing literature highlights out-of-sample performance as a key factor in assessing EPF accuracy, with influencing factors such as predictors, forecast horizon, model selection, and strategy. Several studies indicate that electricity demand is a primary price determinant, while renewable energy sources (RES) like wind and solar significantly impact price dynamics, often lowering prices. Additionally, incorporating data from neighboring countries, due to market coupling, further improves forecast accuracy. Most studies predict up to 24 steps ahead using hourly data, while some extend forecasts using higher-frequency data (e.g., half-hourly or quarter-hourly). Short-term EPF methods fall into two main categories: statistical and computational intelligence (CI) methods, with hybrid models combining both. While many studies use advanced statistical methods, particularly through different versions of traditional AR-type models, others apply computational techniques such as artificial neural networks (ANNs) and support vector machines (SVMs). Recent research combines multiple methods to enhance forecasting performance. Despite extensive research on EPF accuracy, a gap remains in understanding how forecasting strategy affects prediction outcomes. While iterated strategies are commonly used, they are often chosen without justification. This paper contributes by examining whether the choice of forecasting strategy impacts the quality of day-ahead price predictions, especially for multi-step forecasts. We evaluate both iterated and direct methods, exploring alternative ways of conducting iterated forecasts on benchmark and state-of-the-art forecasting frameworks. The goal is to assess whether these factors should be considered by end-users to improve forecast quality. We focus on the Greek DAM using data from July 1, 2021, to March 31, 2022. This period is chosen due to significant price volatility in Greece, driven by its dependence on natural gas and limited interconnection capacity with larger European grids. The analysis covers two phases: pre-conflict (January 1, 2022, to February 23, 2022) and post-conflict (February 24, 2022, to March 31, 2022), following the Russian-Ukraine conflict that initiated an energy crisis. We use the mean absolute percentage error (MAPE) and symmetric mean absolute percentage error (sMAPE) for evaluation, as well as the Direction of Change (DoC) measure to assess the accuracy of price movement predictions. Our findings suggest that forecasters need to apply all strategies across different horizons and models. Different strategies may be required for different horizons to optimize both accuracy and directional predictions, ensuring more reliable forecasts.

Keywords: short-term electricity price forecast, forecast strategies, forecast horizons, recursive strategy, direct strategy

Procedia PDF Downloads 4

Authors: Leila Noori, Rosario Barone, Francesca Rappa, Antonella Marino Gammazza, Alessandra Maria Vitale, Giuseppe Donato Mangano, Giusy Sentiero, Filippo Macaluso, Kathryn H. Myburgh, Francesco Cappello, Federica Scalia

Abstract:

The neuromuscular system controls, directs, and allows movement of the body through the action of neural circuits, which include motor neurons, sensory neurons, and skeletal muscle fibers. Protein homeostasis of the involved cytotypes appears crucial to maintain the correct and prolonged functions of the neuromuscular system, and both neuronal cells and skeletal muscle fibers express significant quantities of protein chaperones, the molecular machinery responsible to maintain the protein turnover. Genetic mutations or defective post-translational modifications of molecular chaperones (i.e., genetic or acquired chaperonopathies) may lead to neuromuscular disorders called as neurochaperonopathies. The limited knowledge of the effects of the defective chaperones on skeletal muscle fibers and neurons impedes the progression of therapeutic approaches. A distinct genetic variation of CCT5 gene encoding for the subunit 5 of the chaperonin CCT (Chaperonin Containing TCP1; also known as TRiC, TCP1 Ring Complex) was recently described associated with severe distal motor neuropathy by our team. In this study, we investigated the histopathological abnormalities of the skeletal muscle biopsy of the pediatric patient affected by the mutation Leu224Val in the CCT5 subunit. We provide molecular and structural features of the diseased skeletal muscle tissue that we believe may be useful to identify undiagnosed cases of this rare genetic disorder. We investigated the histological abnormalities of the affected tissue via hematoxylin and eosin staining. Then we used immunofluorescence and qPCR techniques to explore the expression and distribution of CCT5 in diseased and healthy skeletal muscle tissue. Immunofluorescence and immunohistochemistry assays were performed to study the sarcomeric and structural proteins of skeletal muscle, including actin, myosin, tubulin, troponin-T, telethonin, and titin. We performed Western blot to examine the protein expression of CCT5 and some heat shock proteins, Hsp90, Hsp60, Hsp27, and α-B crystallin, along with the main client proteins of the CCT5, actin, and tubulin. Our findings revealed muscular atrophy, abnormal morphology, and different sizes of muscle fibers in affected tissue. The swollen nuclei and wide interfiber spaces were seen. Expression of CCT5 had been decreased and showed a different distribution pattern in the affected tissue. Altered expression, distribution, and bandage pattern were detected by confocal microscopy for the interested muscular proteins in tissue from the patient compared to the healthy control. Protein levels of the studied Hsps normally located at the Z-disk were reduced. Western blot results showed increased levels of the actin and tubulin proteins in the diseased skeletal muscle biopsy compared to healthy tissue. Chaperones must be expressed at high levels in skeletal muscle to counteract various stressors such as mechanical, oxidative, and thermal crises; therefore, it seems relevant that defects of molecular chaperones may result in damaged skeletal muscle fibers. So far, several chaperones or cochaperones involved in neuromuscular disorders have been defined. Our study shows that alteration of the CCT5 subunit is associated with the damaged structure of skeletal muscle fibers and alterations of chaperone system components and paves the way to explore possible alternative substrates of chaperonin CCT. However, further studies are underway to investigate the CCT mechanisms of action to design applicable therapeutic strategies.

Keywords: molecular chaperones, neurochaperonopathy, neuromuscular system, protein homeostasis

Procedia PDF Downloads 70

Authors: Yu-Hsiu Lin, Wen-Chun Lin, Yen-Chang Cheng, Chia-Ju Yeh, Yu-Chuan Chen, Tai-You Li

Abstract:

Demand-Side Management (DSM) has the potential to reduce electricity costs and carbon emission, which are associated with electricity used in the modern society. A home Energy Management System (EMS) commonly used by residential consumers in a down-stream sector of a smart grid to monitor, control, and optimize energy efficiency to domestic appliances is a system of computer-aided functionalities as an energy audit for residential DSM. Implementing fault detection and classification to domestic appliances monitored, controlled, and optimized is one of the most important steps to realize preventive maintenance, such as residential air conditioning and heating preventative maintenance in residential/industrial DSM. In this study, a cloud intelligence-based green EMS that comes up with an Internet of Things (IoT) technology stack for residential DSM is developed. In the EMS, Arduino MEGA Ethernet communication-based smart sockets that module a Real Time Clock chip to keep track of current time as timestamps via Network Time Protocol are designed and implemented for readings of load phenomena reflecting on voltage and current signals sensed. Also, a Network-Attached Storage providing data access to a heterogeneous group of IoT clients via Hypertext Transfer Protocol (HTTP) methods is configured to data stores of parsed sensor readings. Lastly, a desktop computer with a WAMP software bundle (the Microsoft® Windows operating system, Apache HTTP Server, MySQL relational database management system, and PHP programming language) serves as a data science analytics engine for dynamic Web APP/REpresentational State Transfer-ful web service of the residential DSM having globally-Advanced Internet of Artificial Intelligence (AI)/Computational Intelligence. Where, an abstract computing machine, Java Virtual Machine, enables the desktop computer to run Java programs, and a mash-up of Java, R language, and Python is well-suited and -configured for AI in this study. Having the ability of sending real-time push notifications to IoT clients, the desktop computer implements Google-maintained Firebase Cloud Messaging to engage IoT clients across Android/iOS devices and provide mobile notification service to residential/industrial DSM. In this study, in order to realize edge intelligence that edge devices avoiding network latency and much-needed connectivity of Internet connections for Internet of Services can support secure access to data stores and provide immediate analytical and real-time actionable insights at the edge of the network, we upgrade the designed and implemented smart sockets to be embedded AI Arduino ones (called embedded AIduino). With the realization of edge analytics by the proposed embedded AIduino for data analytics, an Arduino Ethernet shield WizNet W5100 having a micro SD card connector is conducted and used. The SD library is included for reading parsed data from and writing parsed data to an SD card. And, an Artificial Neural Network library, ArduinoANN, for Arduino MEGA is imported and used for locally-embedded AI implementation. The embedded AIduino in this study can be developed for further applications in manufacturing industry energy management and sustainable energy management, wherein in sustainable energy management rotating machinery diagnostics works to identify energy loss from gross misalignment and unbalance of rotating machines in power plants as an example.

Keywords: demand-side management, edge intelligence, energy management system, fault detection and classification

Procedia PDF Downloads 249

Authors: Atish Bagchi, Siva Chandrasekaran

Abstract:

Background: According to World Bank national accounts data, the estimated global manufacturing value-added output in 2020 was 13.74 trillion USD. These manufacturing processes are monitored, modelled, and controlled by advanced, real-time, computer-based systems, e.g., Industrial IoT, PLC, SCADA, etc. These systems measure and manipulate a set of physical variables, e.g., temperature, pressure, etc. Despite the use of IoT, SCADA etc., in manufacturing, studies suggest that unplanned downtime leads to economic losses of approximately 864 billion USD each year. Therefore, real-time, accurate detection, classification and prediction of machine behaviour are needed to minimise financial losses. Although vast literature exists on time-series data processing using machine learning, the challenges faced by the industries that lead to unplanned downtimes are: The current algorithms do not efficiently handle the high-volume streaming data from industrial IoTsensors and were tested on static and simulated datasets. While the existing algorithms can detect significant 'point' outliers, most do not handle contextual outliers (e.g., values within normal range but happening at an unexpected time of day) or subtle changes in machine behaviour. Machines are revamped periodically as part of planned maintenance programmes, which change the assumptions on which original AI models were created and trained. Aim: This research study aims to deliver a Graph Neural Network(GNN)based hybrid forecasting model that interfaces with the real-time machine control systemand can detect, predict machine behaviour and behavioural changes (anomalies) in real-time. This research will help manufacturing industries and utilities, e.g., water, electricity etc., reduce unplanned downtimes and consequential financial losses. Method: The data stored within a process control system, e.g., Industrial-IoT, Data Historian, is generally sampled during data acquisition from the sensor (source) and whenpersistingin the Data Historian to optimise storage and query performance. The sampling may inadvertently discard values that might contain subtle aspects of behavioural changes in machines. This research proposed a hybrid forecasting and classification model which combines the expressive and extrapolation capability of GNN enhanced with the estimates of entropy and spectral changes in the sampled data and additional temporal contexts to reconstruct the likely temporal trajectory of machine behavioural changes. The proposed real-time model belongs to the Deep Learning category of machine learning and interfaces with the sensors directly or through 'Process Data Historian', SCADA etc., to perform forecasting and classification tasks. Results: The model was interfaced with a Data Historianholding time-series data from 4flow sensors within a water treatment plantfor45 days. The recorded sampling interval for a sensor varied from 10 sec to 30 min. Approximately 65% of the available data was used for training the model, 20% for validation, and the rest for testing. The model identified the anomalies within the water treatment plant and predicted the plant's performance. These results were compared with the data reported by the plant SCADA-Historian system and the official data reported by the plant authorities. The model's accuracy was much higher (20%) than that reported by the SCADA-Historian system and matched the validated results declared by the plant auditors. Conclusions: The research demonstrates that a hybrid GNN based approach enhanced with entropy calculation and spectral information can effectively detect and predict a machine's behavioural changes. The model can interface with a plant's 'process control system' in real-time to perform forecasting and classification tasks to aid the asset management engineers to operate their machines more efficiently and reduce unplanned downtimes. A series of trialsare planned for this model in the future in other manufacturing industries.

Keywords: GNN, Entropy, anomaly detection, industrial time-series, AI, IoT, Industry 4.0, Machine Learning

Procedia PDF Downloads 149

Authors: Katie M. Clark, Adriana A. Tienda, Krista C. Paffenroth, Lindsey N. Brigante, Daniel C. Colvin, Jose Maldonado, Erin S. Calipari, Fiona E. Harrison

Abstract:

Manganese (Mn) is an essential trace element required for human health and is important in antioxidant defenses, as well as in the development and function of dopaminergic neurons. However, chronic low-level Mn exposure, such as through contaminated drinking water, poses risks that may contribute to neurodevelopmental and neurodegenerative conditions, including attention deficit hyperactivity disorder (ADHD). Pharmacological inhibition of the dopamine transporter (DAT) blocks reuptake, elevates synaptic dopamine, and alleviates ADHD symptoms. This study aimed to determine whether Mn exposure in juvenile mice modifies their response to DAT blockers, amphetamine, and methylphenidate and utilize neuroimaging methods to visualize and quantify Mn distribution across dopaminergic brain regions. Male and female heterozygous DATᵀ³⁵⁶ᴹ and wild-type littermates were randomly assigned to receive control (2.5% Stevia) or high Manganese (2.5 mg/ml Mn + 2.5% Stevia) via water ad libitum from weaning (21-28 days) for 4-5 weeks. Mice underwent repeated testing in locomotor activity chambers for three consecutive days (60 mins.) to ensure that they were fully habituated to the environments. On the fourth day, a 3-hour activity session was conducted following treatment with amphetamine (3 mg/kg) or methylphenidate (5 mg/kg). The second drug was administered in a second 3-hour activity session following a 1-week washout period. Following the washout, the mice were given one last injection of amphetamine and euthanized one hour later. Using the ex-vivo brains, magnetic resonance relaxometry (MRR) was performed on a 7Telsa imaging system to map T1- and T2-weighted (T1W, T2W) relaxation times. Mn inherent paramagnetic properties shorten both T1W and T2W times, which enhances the signal intensity and contrast, enabling effective visualization of Mn accumulation in the entire brain. A subset of mice was treated with amphetamine 1 hour before euthanasia. SmartSPIM light sheet microscopy with cleared whole brains and cFos and tyrosine hydroxylase (TH) labeling enabled an unbiased automated counting and densitometric analysis of TH and cFos positive cells. Immunohistochemistry was conducted to measure synaptic protein markers and quantify changes in neurotransmitter regulation. Mn exposure elevated Mn brain levels and potentiated stimulant effects in males. The globus pallidus, substantia nigra, thalamus, and striatum exhibited more pronounced T1W shortening, indicating regional susceptibility to Mn accumulation (p<0.0001, 2-Way ANOVA). In the cleared whole brains, initial analyses suggest that TH and c-Fos co-staining mirrors behavioral data with decreased co-staining in DATT356M+/- mice. Ongoing studies will identify the molecular basis of the effect of Mn, including changes to DAergic metabolism and transport and post-translational modification to the DAT. These findings demonstrate that alterations in T1W relaxation times, as measured by MRR, may serve as an early biomarker for Mn neurotoxicity. This neuroimaging approach exhibits remarkable accuracy in identifying Mn-susceptible brain regions, with a spatial resolution and sensitivity that surpasses current conventional dissection and mass spectrometry approaches. The capability to label and map TH and cFos expression across the entire brain provides insights into whole-brain neuronal activation and its connections to functional neural circuits and behavior following amphetamine and methylphenidate administration.

Keywords: manganese, environmental toxicology, dopamine dysfunction, biomarkers, drinking water, light sheet microscopy, magnetic resonance relaxometry (MRR)

Procedia PDF Downloads 4

Authors: Manavjit Singh Dhindsa, Ursula Das, Kshirasagar Naik, Marzia Zaman, Richard Purcell, Srinivas Sampalli, Abdul Mutakabbir, Chung-Horng Lung, Thambirajah Ravichandran

Abstract:

These days, wildland fires, also known as forest fires, are more prevalent than ever. Wildfires have major repercussions that affect ecosystems, communities, and the environment in several ways. Wildfires lead to habitat destruction and biodiversity loss, affecting ecosystems and causing soil erosion. They also contribute to poor air quality by releasing smoke and pollutants that pose health risks, especially for individuals with respiratory conditions. Wildfires can damage infrastructure, disrupt communities, and cause economic losses. The economic impact of firefighting efforts, combined with their direct effects on forestry and agriculture, causes significant financial difficulties for the areas impacted. This research explores different forest fire spread models and presents a comprehensive review of various techniques and methodologies used in the field. A forest fire spread model is a computational or mathematical representation that is used to simulate and predict the behavior of a forest fire. By applying scientific concepts and data from empirical studies, these models attempt to capture the intricate dynamics of how a fire spreads, taking into consideration a variety of factors like weather patterns, topography, fuel types, and environmental conditions. These models assist authorities in understanding and forecasting the potential trajectory and intensity of a wildfire. Emphasizing the need for a comprehensive understanding of wildfire dynamics, this research explores the approaches, assumptions, and findings derived from various models. By using a comparison approach, a critical analysis is provided by identifying patterns, strengths, and weaknesses among these models. The purpose of the survey is to further wildfire research and management techniques. Decision-makers, researchers, and practitioners can benefit from the useful insights that are provided by synthesizing established information. Fire spread models provide insights into potential fire behavior, facilitating authorities to make informed decisions about evacuation activities, allocating resources for fire-fighting efforts, and planning for preventive actions. Wildfire spread models are also useful in post-wildfire mitigation strategies as they help in assessing the fire's severity, determining high-risk regions for post-fire dangers, and forecasting soil erosion trends. The analysis highlights the importance of customized modeling approaches for various circumstances and promotes our understanding of the way forest fires spread. Some of the known models in this field are Rothermel’s wildland fuel model, FARSITE, WRF-SFIRE, FIRETEC, FlamMap, FSPro, cellular automata model, and others. The key characteristics that these models consider include weather (includes factors such as wind speed and direction), topography (includes factors like landscape elevation), and fuel availability (includes factors like types of vegetation) among other factors. The models discussed are physics-based, data-driven, or hybrid models, also utilizing ML techniques like attention-based neural networks to enhance the performance of the model. In order to lessen the destructive effects of forest fires, this initiative aims to promote the development of more precise prediction tools and effective management techniques. The survey expands its scope to address the practical needs of numerous stakeholders. Access to enhanced early warning systems enables decision-makers to take prompt action. Emergency responders benefit from improved resource allocation strategies, strengthening the efficacy of firefighting efforts.

Keywords: artificial intelligence, deep learning, forest fire management, fire risk assessment, fire simulation, machine learning, remote sensing, wildfire modeling

Procedia PDF Downloads 81

Authors: David J. Foran, Nhan Do, Samuel Ajjarapu, Wenjin Chen, Tahsin Kurc, Joel H. Saltz

Abstract:

The large-scale data and computational requirements of investigators throughout the clinical and research communities demand an informatics infrastructure that supports both existing and new investigative and translational projects in a robust, secure environment. In some subspecialties of medicine and research, the capacity to generate data has outpaced the methods and technology used to aggregate, organize, access, and reliably retrieve this information. Leading health care centers now recognize the utility of establishing an enterprise-wide, clinical data warehouse. The primary benefits that can be realized through such efforts include cost savings, efficient tracking of outcomes, advanced clinical decision support, improved prognostic accuracy, and more reliable clinical trials matching. The overarching objective of the work presented here is the development and implementation of a flexible Intelligent Retrieval and Interrogation System (IRIS) that exploits the combined use of computational imaging, genomics, and data-mining capabilities to facilitate clinical assessments and translational research in oncology. The proposed System includes a multi-modal, Clinical & Research Data Warehouse (CRDW) that is tightly integrated with a suite of computational and machine-learning tools to provide insight into the underlying tumor characteristics that are not be apparent by human inspection alone. A key distinguishing feature of the System is a configurable Extract, Transform and Load (ETL) interface that enables it to adapt to different clinical and research data environments. This project is motivated by the growing emphasis on establishing Learning Health Systems in which cyclical hypothesis generation and evidence evaluation become integral to improving the quality of patient care. To facilitate iterative prototyping and optimization of the algorithms and workflows for the System, the team has already implemented a fully functional Warehouse that can reliably aggregate information originating from multiple data sources including EHR’s, Clinical Trial Management Systems, Tumor Registries, Biospecimen Repositories, Radiology PAC systems, Digital Pathology archives, Unstructured Clinical Documents, and Next Generation Sequencing services. The System enables physicians to systematically mine and review the molecular, genomic, image-based, and correlated clinical information about patient tumors individually or as part of large cohorts to identify patterns that may influence treatment decisions and outcomes. The CRDW core system has facilitated peer-reviewed publications and funded projects, including an NIH-sponsored collaboration to enhance the cancer registries in Georgia, Kentucky, New Jersey, and New York, with machine-learning based classifications and quantitative pathomics, feature sets. The CRDW has also resulted in a collaboration with the Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC) at the U.S. Department of Veterans Affairs to develop algorithms and workflows to automate the analysis of lung adenocarcinoma. Those studies showed that combining computational nuclear signatures with traditional WHO criteria through the use of deep convolutional neural networks (CNNs) led to improved discrimination among tumor growth patterns. The team has also leveraged the Warehouse to support studies to investigate the potential of utilizing a combination of genomic and computational imaging signatures to characterize prostate cancer. The results of those studies show that integrating image biomarkers with genomic pathway scores is more strongly correlated with disease recurrence than using standard clinical markers.

Keywords: clinical data warehouse, decision support, data-mining, intelligent databases, machine-learning.

Procedia PDF Downloads 126