Improved accuracy of anticoagulant dose prediction using a pharmacogenetic and artificial neural network-based method

A Mobile Application for Anticoagulation Management in Patients After Heart Valve Replacement: A Usability Study

Purpose

Individualized anticoagulation therapy is a major challenge for patients after heart valve replacement. Mobile applications assisted by Artificial intelligence (AI) have great potential to meet the individual needs of patients. The study aimed to develop an AI technology-assisted mobile application (app) for anticoagulation management, understand patients' acceptance of such applications, and determine its feasibility.

Methods

After using the mobile application for anticoagulation management for 2 weeks, patients, doctors, and nurses rated its usability using the System Usability Scale (SUS). Additionally, semi-structured interviews were conducted with some patients, doctors, and nurses to gain insights about their thoughts and suggestions regarding the procedure.

Results

The study comprised 80 participants, including 38 patients, 18 doctors, and 24 nurses. The average SUS score for patients was 82.37±5.45; for doctors, it was 84.17±5.82; and for nurses, it was 81.88±6.44. This means the patients, physicians, and nurses rated the app highly usable. Semi-structured interviews were conducted on the app's usability with 18 participants (six nurses, three physicians, and nine patients). The interview results revealed that patients found the application of anticoagulation management simple and convenient, with high expectations for a precise dosage recommendation of anticoagulant drugs. Some patients expressed concerns regarding personal information security. Both doctors and nurses believed that elderly patients needed assistance from young family members to use the app and that it could improve patients' anticoagulant self-management ability. Some nurses also mentioned that the use of the app brought great convenience for transitional care.

Conclusion

This study confirmed the feasibility of using an AI technology-assisted mobile application for anticoagulation management in patients after heart valve replacement. To further develop this application, challenges lie in continuously improving the accuracy of recommended drug doses, obtaining family support, and ensuring information security.

Pharmacogenomics in Lebanon: current status, challenges and opportunities

Pharmacogenomics (PGx) research and applications are of utmost relevance in Lebanon considering its population genetic diversity. Moreover, as a country with regional leadership in medicine and higher education, Lebanon holds a strong potential in contributing to PGx research and clinical implementation. In this manuscript, we first review and evaluate the available PGx research conducted in Lebanon, then describe the current status of PGx practice in Lebanon while reflecting on the local and regional challenges, and highlighting areas for action, and opportunities to move forward. We specifically expand on the status of PGx at the American University of Beirut Faculty of Medicine and Medical Center as a case study and guide for the further development of local and regional comprehensive PGx research, teaching, and clinical implementation programs. We also delve into the status of PGx knowledge and education, and prospects for further advancement such as with online courses and certificates.

Determining the adjusted initial treatment dose of warfarin anticoagulant medicine using kernel-based support vector regression

BACKGROUND AND OBJECTIVE

A novel research field in bioinformatics is pharmacogenomics and the corresponding applications of artificial intelligence tools. Pharmacogenomics is the study of the relationship between genotype and responses to medical measures such as drug use. One of the most effective drugs is warfarin anticoagulant, but determining its initial treatment dose is challenging. Mistakes in the determination of the initial treatment dose can result directly in patient death.

METHODS

Some of the most successful techniques for estimating the initial treatment dose are kernel-based methods. However, all the available studies use pre-defined and constant kernels that might not necessarily address the problem's intended requirements. The present study seeks to define and present a new computational kernel extracted from a data set. This process aims to utilize all the data-related statistical features to generate a dose determination tool proportional to the data set with minimum error rate. The kernel-based version of the least square support vector regression estimator was defined. Through this method, a more appropriate approach was proposed for predicting the adjusted dose of warfarin.

RESULTS AND CONCLUSION

This paper benefits from the International Warfarin Pharmacogenomics Consortium (IWPC) Database. The results obtained in this study demonstrate that the support vector regression with the proposed new kernel can successfully estimate the ideal dosage of warfarin for approximately 68% of patients.

A speckle-tracking strain-based artificial neural network model to differentiate cardiomyopathy type

Objectives. In heart failure, invasive angiography is often employed to differentiate ischaemic from non-ischaemic cardiomyopathy. We aim to examine the predictive value of echocardiographic strain features alone and in combination with other features to differentiate ischaemic from non-ischaemic cardiomyopathy, using artificial neural network (ANN) and logistic regression modelling. Design. We retrospectively identified 204 consecutive patients with an ejection fraction <50% and a diagnostic angiogram. Patients were categorized as either ischaemic (n = 146) or non-ischaemic cardiomyopathy (n = 58). For each patient, left ventricular strain parameters were obtained. Additionally, regional wall motion abnormality, 13 electrocardiographic (ECG) features and six demographic features were retrieved for analysis. The entire cohort was randomly divided into a derivation and a validation cohort. Using the parameters retrieved, logistic regression and ANN models were developed in the derivation cohort to differentiate ischaemic from non-ischaemic cardiomyopathy, the models were then tested in the validation cohort. Results. A final strain-based ANN model, full feature ANN model and full feature logistic regression model were developed and validated, F₁ scores were 0.82, 0.79 and 0.63, respectively. Conclusions. Both ANN models were more accurate at predicting cardiomyopathy type than the logistic regression model. The strain-based ANN model should be validated in other cohorts. This model or similar models could be used to aid the diagnosis of underlying heart failure aetiology in the form of the online calculator (https://cimti.usj.edu.lb/strain/index.html) or built into echocardiogram software.

Precision dosing of warfarin: open questions and strategies

Warfarin has a very narrow therapeutic window and obvious interindividual variability in its effects, with many factors contributing to the body's response. Algorithms incorporating multiple genetic, environment and clinical factors have been established to select a precision dose for each patient. A number of randomized controlled trials (RCTs) were conducted to explore whether patients could benefit from these algorithms; however, the results were inconsistent. Some questions remain to be resolved. Recently, new genetic and non-genetic factors have been discovered to contribute to variability in optimal warfarin doses. The results of further RCTs have been unveiled, and guidelines for pharmacogenetically guided warfarin dosing have been updated. Based on these most recent advancements, we summarize some open questions in this field and try to propose possible strategies to resolve them.

Artificial neural network-based model enhances risk stratification and reduces non-invasive cardiac stress imaging compared to Diamond-Forrester and Morise risk assessment models: A prospective study

BACKGROUND

Coronary artery disease (CAD) accounts for more than half of all cardiovascular events. Stress testing remains the cornerstone for non-invasive assessment of patients with possible or known CAD. Clinical utilization reviews show that most patients presenting for evaluation of stable CAD by stress testing are categorized as low risk prior to the test. Attempts to enhance risk stratification of individuals who are sent for stress testing seem to be more in need today. The present study compares artificial neural networks (ANN)-based prediction models to the other risk models being used in practice (the Diamond-Forrester and the Morise models).

METHODS

In our study, we prospectively recruited patients who were 19 years of age or older, and were being evaluated for coronary artery disease with imaging-based stress tests. For ANN, the network architecture employed a systematic method, where the number of neurons is changed incrementally, and bootstrapping was performed to evaluate the accuracy of the models.

RESULTS

We prospectively enrolled 486 patients. The mean age of patients undergoing stress test was 55.2 ± 11.2 years, 35% were women, and 12% had a positive stress test for ischemic heart disease. When compared to Diamond-Forrester and Morise risk models, the ANN model for predicting ischemia provided higher discriminatory power (DP)(1.61), had a negative predictive value of 98%, Sensitivity 91% [81%-97%], Specificity 65% [60%-79%], positive predictive value 26%, and a potential 59% reduction of non-invasive imaging.

CONCLUSION

The ANN models improved risk stratification when compared to the other risk scores (Diamond-Forrester and Morise) with a 98% negative predictive value and a significant potential reduction in non-invasive imaging tests.

The Pharmacogenetics Laboratory of the Department of Pharmacology and Toxicology at the American University of Beirut Faculty of Medicine

The pharmacogenetics (PGx) laboratory at the Department of Pharmacology and Toxicology at the American University of Beirut Faculty of Medicine was established in October 2007. Several projects on the genetic polymorphisms of drug metabolizing enzymes and transporters with treatment of noncommunicable diseases such as cardiac diseases and cancers are ongoing. We have been applying the 'candidate gene' PGx approach, and recently started using higher throughput analyses. The more recent research projects are geared towards performing more extensive genotyping and including bigger and more representative population samples such as by developing research registries and prospectively following up patients. Furthermore, many technologies and research applications, such as next-generation sequencing and pharmacoepigenetics that complement and enhance PGx research and applications, are being actively pursued.

Clinical Decision Support Tools: The Evolution of a Revolution

Dashboard systems for clinical decision support integrate data from multiple sources. These systems, the newest in a long line of dose calculators and other decision support tools, utilize Bayesian approaches to fully individualize dosing using information gathered through therapeutic drug monitoring. In the treatment of inflammatory bowel disease patients with infliximab, dashboards may reduce therapeutic failures and treatment costs. The history and future development of modern Bayesian dashboard systems is described.

Artificial neural network modeling enhances risk stratification and can reduce downstream testing for patients with suspected acute coronary syndromes, negative cardiac biomarkers, and normal ECGs

Despite uncertain yield, guidelines endorse routine stress myocardial perfusion imaging (MPI) for patients with suspected acute coronary syndromes, unremarkable serial electrocardiograms, and negative troponin measurements. In these patients, outcome prediction and risk stratification models could spare unnecessary testing. This study therefore investigated the use of artificial neural networks (ANN) to improve risk stratification and prediction of MPI and angiographic results. We retrospectively identified 5354 consecutive patients referred from the emergency department for rest-stress MPI after serial negative troponins and normal ECGs. Patients were risk stratified according to thrombolysis in myocardial infarction (TIMI) scores, ischemia was defined as >5 % reversible perfusion defect, and obstructive coronary artery disease was defined as >50 % angiographic obstruction. For ANN, the network architecture employed a systematic method where the number of neurons is changed incrementally, and bootstrapping was performed to evaluate the accuracy of the models. Compared to TIMI scores, ANN models provided improved discriminatory power. With regards to MPI, an ANN model could reduce testing by 59 % and maintain a 96 % negative predictive value (NPV) for ruling out ischemia. Application of an ANN model could also avoid 73 % of invasive coronary angiograms while maintaining a 98 % NPV for detecting obstructive CAD. An online calculator for clinical use was created using these models. The ANN models improved risk stratification when compared to the TIMI score. Our calculator could also reduce downstream testing while maintaining an excellent NPV, though further study is needed before the calculator can be used clinically.

Comparison of Nine Statistical Model Based Warfarin Pharmacogenetic Dosing Algorithms Using the Racially Diverse International Warfarin Pharmacogenetic Consortium Cohort Database

Objective

Multiple linear regression (MLR) and machine learning techniques in pharmacogenetic algorithm-based warfarin dosing have been reported. However, performances of these algorithms in racially diverse group have never been objectively evaluated and compared. In this literature-based study, we compared the performances of eight machine learning techniques with those of MLR in a large, racially-diverse cohort.

Methods

MLR, artificial neural network (ANN), regression tree (RT), multivariate adaptive regression splines (MARS), boosted regression tree (BRT), support vector regression (SVR), random forest regression (RFR), lasso regression (LAR) and Bayesian additive regression trees (BART) were applied in warfarin dose algorithms in a cohort from the International Warfarin Pharmacogenetics Consortium database. Covariates obtained by stepwise regression from 80% of randomly selected patients were used to develop algorithms. To compare the performances of these algorithms, the mean percentage of patients whose predicted dose fell within 20% of the actual dose (mean percentage within 20%) and the mean absolute error (MAE) were calculated in the remaining 20% of patients. The performances of these techniques in different races, as well as the dose ranges of therapeutic warfarin were compared. Robust results were obtained after 100 rounds of resampling.

Results

BART, MARS and SVR were statistically indistinguishable and significantly out performed all the other approaches in the whole cohort (MAE: 8.84–8.96 mg/week, mean percentage within 20%: 45.88%–46.35%). In the White population, MARS and BART showed higher mean percentage within 20% and lower mean MAE than those of MLR (all p values < 0.05). In the Asian population, SVR, BART, MARS and LAR performed the same as MLR. MLR and LAR optimally performed among the Black population. When patients were grouped in terms of warfarin dose range, all machine learning techniques except ANN and LAR showed significantly higher mean percentage within 20%, and lower MAE (all p values < 0.05) than MLR in the low- and high- dose ranges.

Conclusion

Overall, machine learning-based techniques, BART, MARS and SVR performed superior than MLR in warfarin pharmacogenetic dosing. Differences of algorithms’ performances exist among the races. Moreover, machine learning-based algorithms tended to perform better in the low- and high- dose ranges than MLR.