scholarly journals Data-Driven Clinical Decision Support System for Medical Diagnosis and Treatment Recommendation

2019 ◽  
Vol 8 (11) ◽  
pp. 3660-3668
Keyword(s):  
Face Recognition ◽  
Decision Support ◽  
Decision Support System ◽  
Clinical Decision Support ◽  
Support System ◽  
Clinical Decision Support System ◽  
Clinical Decision ◽  
Data Driven ◽  
Treatment Recommendation ◽  
Disease Prediction

This paper presents a Data-Driven Clinical Decision Support System (CDSS) using machine learning. The proposed system predicts the possibility of diseases based on the patient’s symptoms. It suggests lab tests and medication related to the disease. Lab test results are analyzed to check the probability of liver and kidney diseases. The proposed system uses face recognition to identify the patient. Face recognition module retrieves the Patient Health Record and provides patient information and health records access to the doctor and medical staff. The system is developed using Python Django for Backend, React.JS for User Interface and PostgreSQL as the relational database. The system uses Logistic Regression for possible disease prediction, Support Vector Machine for liver disease prediction, Random Forest for chronic kidney disease prediction. The result of the proposed data-driven clinical decision support system is compared with a doctor’s disease analysis to measure the effectiveness of the proposed system. This kind of system can help doctors in providing better care and predict the disease at an early stage.

scholarly journals A Risk-Based Clinical Decision Support System for Patient-Specific Antimicrobial Therapy (iBiogram): Design and Retrospective Analysis (Preprint)

2020 ◽  
Author(s):  
Lars Müller ◽  
Aditya Srinivasan ◽  
Shira R Abeles ◽  
Amutha Rajagopal ◽  
Francesca J Torriani ◽  
...  
Keyword(s):  
Decision Support ◽  
Antimicrobial Resistance ◽  
Decision Support System ◽  
Clinical Decision Support ◽  
Support System ◽  
Clinical Decision Support System ◽  
Clinical Decision ◽  
Data Driven ◽  
Patient Specific ◽  
Tract Infections

BACKGROUND There is a pressing need for digital tools that can leverage big data to help clinicians select effective antibiotic treatments in the absence of timely susceptibility data. Clinical presentation and local epidemiology can inform therapy selection to balance the risk of antimicrobial resistance and patient risk. However, data and clinical expertise must be appropriately integrated into clinical workflows. OBJECTIVE The aim of this study is to leverage available data in electronic health records, to develop a data-driven, user-centered, clinical decision support system to navigate patient safety and population health. METHODS We analyzed 5 years of susceptibility testing (1,078,510 isolates) and patient data (30,761 patients) across a large academic medical center. After curating the data according to the Clinical and Laboratory Standards Institute guidelines, we analyzed and visualized the impact of risk factors on clinical outcomes. On the basis of this data-driven understanding, we developed a probabilistic algorithm that maps these data to individual cases and implemented iBiogram, a prototype digital empiric antimicrobial clinical decision support system, which we evaluated against actual prescribing outcomes. RESULTS We determined patient-specific factors across syndromes and contexts and identified relevant local patterns of antimicrobial resistance by clinical syndrome. Mortality and length of stay differed significantly depending on these factors and could be used to generate heuristic targets for an acceptable risk of underprescription. Combined with the developed <i>remaining risk</i> algorithm, these factors can be used to inform clinicians’ reasoning. A retrospective comparison of the iBiogram-suggested therapies versus the actual prescription by physicians showed similar performance for low-risk diseases such as urinary tract infections, whereas iBiogram recognized risk and recommended more appropriate coverage in high mortality conditions such as sepsis. CONCLUSIONS The application of such data-driven, patient-centered tools may guide empirical prescription for clinicians to balance morbidity and mortality with antimicrobial stewardship.

scholarly journals A Risk-Based Clinical Decision Support System for Patient-Specific Antimicrobial Therapy (iBiogram): Design and Retrospective Analysis

10.2196/23571 ◽  
2021 ◽  
Vol 23 (12) ◽  
pp. e23571
Author(s):  
Lars Müller ◽  
Aditya Srinivasan ◽  
Shira R Abeles ◽  
Amutha Rajagopal ◽  
Francesca J Torriani ◽  
...  
Keyword(s):  
Decision Support ◽  
Antimicrobial Resistance ◽  
Decision Support System ◽  
Clinical Decision Support ◽  
Support System ◽  
Clinical Decision Support System ◽  
Clinical Decision ◽  
Data Driven ◽  
Patient Specific ◽  
Tract Infections

Background There is a pressing need for digital tools that can leverage big data to help clinicians select effective antibiotic treatments in the absence of timely susceptibility data. Clinical presentation and local epidemiology can inform therapy selection to balance the risk of antimicrobial resistance and patient risk. However, data and clinical expertise must be appropriately integrated into clinical workflows. Objective The aim of this study is to leverage available data in electronic health records, to develop a data-driven, user-centered, clinical decision support system to navigate patient safety and population health. Methods We analyzed 5 years of susceptibility testing (1,078,510 isolates) and patient data (30,761 patients) across a large academic medical center. After curating the data according to the Clinical and Laboratory Standards Institute guidelines, we analyzed and visualized the impact of risk factors on clinical outcomes. On the basis of this data-driven understanding, we developed a probabilistic algorithm that maps these data to individual cases and implemented iBiogram, a prototype digital empiric antimicrobial clinical decision support system, which we evaluated against actual prescribing outcomes. Results We determined patient-specific factors across syndromes and contexts and identified relevant local patterns of antimicrobial resistance by clinical syndrome. Mortality and length of stay differed significantly depending on these factors and could be used to generate heuristic targets for an acceptable risk of underprescription. Combined with the developed remaining risk algorithm, these factors can be used to inform clinicians’ reasoning. A retrospective comparison of the iBiogram-suggested therapies versus the actual prescription by physicians showed similar performance for low-risk diseases such as urinary tract infections, whereas iBiogram recognized risk and recommended more appropriate coverage in high mortality conditions such as sepsis. Conclusions The application of such data-driven, patient-centered tools may guide empirical prescription for clinicians to balance morbidity and mortality with antimicrobial stewardship.

scholarly journals Assessing Acceptance Level of a Hybrid Clinical Decision Support Systems

2021 ◽  
Author(s):  
Georgy Kopanitsa ◽  
Ilia V. Derevitskii ◽  
Daria A. Savitskaya ◽  
Sergey V. Kovalchuk
Keyword(s):  
Decision Support ◽  
Decision Support System ◽  
Clinical Decision Support ◽  
Support System ◽  
Clinical Decision Support System ◽  
Clinical Decision ◽  
User Acceptance ◽  
Perceived Usefulness ◽  
Data Driven ◽  
Risk Scale

We present a user acceptance study of a clinical decision support system (CDSS) for Type 2 Diabetes Mellitus (T2DM) risk prediction. We focus on how a combination of data-driven and rule-based models influence the efficiency and acceptance by doctors. To evaluate the perceived usefulness, we randomly generated CDSS output in three different settings: Data-driven (DD) model output; DD model with a presence of known risk scale (FINDRISK); DD model with presence of risk scale and explanation of DD model. For each case, a physician was asked to answer 3 questions: if a doctor agrees with the result, if a doctor understands it, if the result is useful for the practice. We employed a Lankton’s model to evaluate the user acceptance of the clinical decision support system. Our analysis has proved that without the presence of scales, a physician trust CDSS blindly. From the answers, we can conclude that interpretability plays an important role in accepting a CDSS.

1309-P: Utilizing a Clinical Decision Support System for Hypoglycemia Management

Diabetes ◽  
2019 ◽  
Vol 68 (Supplement 1) ◽  
pp. 1309-P
Author(s):  
JACQUELYN R. GIBBS ◽  
KIMBERLY BERGER ◽  
MERCEDES FALCIGLIA
Keyword(s):  
Decision Support ◽  
Decision Support System ◽  
Clinical Decision Support ◽  
Support System ◽  
Clinical Decision Support System ◽  
Clinical Decision

A Clinical Decision Support System for Assessing the Risk of Cardiovascular Diseases in Diabetic Hemodialysis Patients

2020 ◽  
Vol 16 (3) ◽  
pp. 262-269
Author(s):  
Tahere Talebi Azad Boni ◽  
Haleh Ayatollahi ◽  
Mostafa Langarizadeh
Keyword(s):  
Decision Support ◽  
Cardiovascular Diseases ◽  
Decision Support System ◽  
Clinical Decision Support ◽  
Support System ◽  
Clinical Decision Support System ◽  
Clinical Decision ◽  
Diabetic Patients ◽  
K Value ◽  
Care Plans

Background: One of the greatest challenges in the field of medicine is the increasing burden of chronic diseases, such as diabetes. Diabetes may cause several complications, such as kidney failure which is followed by hemodialysis and an increasing risk of cardiovascular diseases. Objective: The purpose of this research was to develop a clinical decision support system for assessing the risk of cardiovascular diseases in diabetic patients undergoing hemodialysis by using a fuzzy logic approach. Methods: This study was conducted in 2018. Initially, the views of physicians on the importance of assessment parameters were determined by using a questionnaire. The face and content validity of the questionnaire was approved by the experts in the field of medicine. The reliability of the questionnaire was calculated by using the test-retest method (r = 0.89). This system was designed and implemented by using MATLAB software. Then, it was evaluated by using the medical records of diabetic patients undergoing hemodialysis (n=208). Results: According to the physicians' point of view, the most important parameters for assessing the risk of cardiovascular diseases were glomerular filtration, duration of diabetes, age, blood pressure, type of diabetes, body mass index, smoking, and C reactive protein. The system was designed and the evaluation results showed that the values of sensitivity, accuracy, and validity were 85%, 92% and 90%, respectively. The K-value was 0.62. Conclusion: The results of the system were largely similar to the patients’ records and showed that the designed system can be used to help physicians to assess the risk of cardiovascular diseases and to improve the quality of care services for diabetic patients undergoing hemodialysis. By predicting the risk of the disease and classifying patients in different risk groups, it is possible to provide them with better care plans.

Sign in / Sign up

Export Citation Format

Share Document