Improvement of adequate use of warfarin for the elderly using decision tree-based approaches

Machine learning in medication prescription: A systematic review

BACKGROUND

Medication prescription is a complex process that could benefit from current research and development in machine learning through decision support systems. Particularly pediatricians are forced to prescribe medications "off-label" as children are still underrepresented in clinical studies, which leads to a high risk of an incorrect dose and adverse drug effects.

METHODS

PubMed, IEEE Xplore and PROSPERO were searched for relevant studies that developed and evaluated well-performing machine learning algorithms following the PRISMA statement. Quality assessment was conducted in accordance with the IJMEDI checklist. Identified studies were reviewed in detail, including the required variables for predicting the correct dose, especially of pediatric medication prescription.

RESULTS

The search identified 656 studies, of which 64 were reviewed in detail and 36 met the inclusion criteria. According to the IJMEDI checklist, five studies were considered to be of high quality. 19 of the 36 studies dealt with the active substance warfarin. Overall, machine learning algorithms based on decision trees or regression methods performed superior regarding their predictive power than algorithms based on neural networks, support vector machines or other methods. The use of ensemble methods like bagging or boosting generally enhanced the accuracy of the dose predictions. The required input and output variables of the algorithms were considerably heterogeneous and differ strongly among the respective substance.

CONCLUSIONS

By using machine learning algorithms, the prescription process could be simplified and dosing correctness could be enhanced. Despite the heterogenous results among the different substances and cases and the lack of pediatric use cases, the identified approaches and required variables can serve as an excellent starting point for further development of algorithms predicting drug doses, particularly for children. Especially the combination of physiologically-based pharmacokinetic models with machine learning algorithms represents a great opportunity to enhance the predictive power and accuracy of the developed algorithms.

A Real-World Exploration into Clinical Outcomes of Direct Oral Anticoagulant Dosing Regimens in Morbidly Obese Patients Using Data-Driven Approaches

INTRODUCTION

The clinical outcomes of direct oral anticoagulant (DOAC) dosage regimens in morbid obesity are uncertain due to limited clinical evidence. This study seeks to bridge this evidence gap by identifying the factors associated with clinical outcomes following the dosing of DOACs in morbidly obese patients.

METHOD

A data-driven observational study was carried out using supervised machine learning (ML) models with a dataset extracted from electronic health records and preprocessed. Following 70%:30% partitioning of the overall dataset via stratified sampling, the selected ML classifiers (e.g., random forest, decision trees, bootstrap aggregation) were applied to the training dataset (70%). The outcomes of the models were evaluated against the test dataset (30%). Multivariate regression analysis explored the association between DOAC regimens and clinical outcomes.

RESULTS

A sample of 4,275 morbidly obese patients was extracted and analysed. The decision trees, random forest, and bootstrap aggregation classifiers achieved acceptable (excellent) values of precision, recall, and F1 scores in terms of their contribution to clinical outcomes. The length of stay, treatment days, and age were ranked highest for relevance to mortality and stroke. Among DOAC regimens, apixaban 2.5 mg twice daily ranked highest for its association with mortality, increasing the mortality risk by 43% (odds ratio [OR] 1.430, 95% confidence interval [CI] 1.181-1.732, p = 0.001). On the other hand, apixaban 5 mg twice daily reduced the odds of mortality by 25% (OR 0.751, 95% CI 0.632-0.905, p = 0.003) but increased the odds of stroke events. No clinically relevant non-major bleeding events occurred in this group.

CONCLUSION

Data-driven approaches can identify key factors associated with clinical outcomes following the dosing of DOACs in morbidly obese patients. This will help design further studies to explore well tolerated and effective DOAC doses for morbidly obese patients.

Digital Health: Today's Solutions and Tomorrow's Impact

Artificial intelligence (AI) is becoming an indispensable tool to augment decision making in different health care settings and by various members of the patient pathway, including the patient. AI provides the ability to optimize data to bring clinical decision support for clinicians and laboratorians and/or empower patients to actively participate in their own health care. Though there are many examples of AI in health care, the exact role of AI and digital health solutions is still taking shape. Although AI will not replace the clinician, those who do not adopt AI may in time, be left behind.

Predicting the Risk of Future Multiple Suicide Attempt among First-Time Suicide Attempters: Implications for Suicide Prevention Policy

Suicide is listed in the top ten causes of death in Taiwan. Previous studies have pointed out that psychiatric patients having suicide attempts in their history are more likely to attempt suicide again than non-psychiatric patients. Therefore, how to predict the future multiple suicide attempts of psychiatric patients is an important issue of public health. Different from previous studies, we collect the psychiatric patients who have a suicide diagnosis in the National Health Insurance Research Database (NHIRD) as the study cohort. Study variables include psychiatric patients’ characteristics, medical behavior characteristics, physician characteristics, and hospital characteristics. Three machine learning techniques, including decision tree (DT), support vector machine (SVM), and artificial neural network (ANN), are used to develop models for predicting the risk of future multiple suicide attempts. The Adaboost technique is further used to improve prediction performance in model development. The experimental results show that Adaboost+DT performs the best in predicting the behavior of multiple suicide attempts among psychiatric patients. The findings of this study can help clinical staffs to early identify high-risk patients and improve the effectiveness of suicide prevention.

Visual Analytics for Predicting Disease Outcomes Using Laboratory Test Results

Laboratory tests play an essential role in the early and accurate diagnosis of diseases. In this paper, we propose SUNRISE, a visual analytics system that allows the user to interactively explore the relationships between laboratory test results and a disease outcome. SUNRISE integrates frequent itemset mining (i.e., Eclat algorithm) with extreme gradient boosting (XGBoost) to develop more specialized and accurate prediction models. It also includes interactive visualizations to allow the user to interact with the model and track the decision process. SUNRISE helps the user probe the prediction model by generating input examples and observing how the model responds. Furthermore, it improves the user’s confidence in the generated predictions and provides them the means to validate the model’s response by illustrating the underlying working mechanism of the prediction models through visualization representations. SUNRISE offers a balanced distribution of processing load through the seamless integration of analytical methods with interactive visual representations to support the user’s cognitive tasks. We demonstrate the usefulness of SUNRISE through a usage scenario of exploring the association between laboratory test results and acute kidney injury, using large provincial healthcare databases from Ontario, Canada.

Key use cases for artificial intelligence to reduce the frequency of adverse drug events: a scoping review

Adverse drug events (ADEs) represent one of the most prevalent types of health-care-related harm, and there is substantial room for improvement in the way that they are currently predicted and detected. We conducted a scoping review to identify key use cases in which artificial intelligence (AI) could be leveraged to reduce the frequency of ADEs. We focused on modern machine learning techniques and natural language processing. 78 articles were included in the scoping review. Studies were heterogeneous and applied various AI techniques covering a wide range of medications and ADEs. We identified several key use cases in which AI could contribute to reducing the frequency and consequences of ADEs, through prediction to prevent ADEs and early detection to mitigate the effects. Most studies (73 [94%] of 78) assessed technical algorithm performance, and few studies evaluated the use of AI in clinical settings. Most articles (58 [74%] of 78) were published within the past 5 years, highlighting an emerging area of study. Availability of new types of data, such as genetic information, and access to unstructured clinical notes might further advance the field.

A post-hoc interpretable ensemble model to feature effect analysis in warfarin dose prediction for Chinese patients

To interprete the importance of clinical features and genotypes for warfarin daily dose prediction, we developed a post-hoc interpretable framework based on an ensemble predictive model. This framework includes permutation importance for global interpretation and local interpretable model-agnostic explanation (LIME) and shapley additive explanations (SHAP) for local explanation. The permutation importance globally ranks the importance of features on the whole data set. This can guide us to build a predictive model with less variables and the complexity of final predictive model can be reduced. LIME and SHAP together explain how the predictive model give the predicted dosage for specific samples. This help clinicians prescribe accurate doses to patients using more effective clinical variables. Results showed that both the permutation importance and SHAP demonstrated that VKORC1, age, serum creatinine (SCr), left atrium (LA) size, CYP2C9 and weight were the most important features on the whole data set. In specific samples, both SHAP and LIME discovered that in Chinese patients, wild-type VKORC1-AA, mutant-type CYP2C9*3, age over 60, abnormal LA size, SCr within the normal range, and using amiodarone definitely required dosage reduction, whereas mutant-type VKORC1-AG/GG, small age, SCr out of normal range, normal LA size, diabetes and heavy weight required dosage enhancement.

Applications of machine learning in the chemical pathology laboratory

Machine learning (ML) is an area of artificial intelligence that provides computer programmes with the capacity to autodidact and learn new skills from experience, without continued human programming. ML algorithms can analyse large data sets quickly and accurately, by supervised and unsupervised learning techniques, to provide classification and prediction value outputs. The application of ML to chemical pathology can potentially enhance efficiency at all phases of the laboratory's total testing process. Our review will broadly discuss the theoretical foundation of ML in laboratory medicine. Furthermore, we will explore the current applications of ML to diverse chemical pathology laboratory processes, for example, clinical decision support, error detection in the preanalytical phase, and ML applications in gel-based image analysis and biomarker discovery. ML currently demonstrates exploratory applications in chemical pathology with promising advancements, which have the potential to improve all phases of the chemical pathology total testing pathway.

The Value of Artificial Intelligence in Laboratory Medicine

OBJECTIVES

As laboratory medicine continues to undergo digitalization and automation, clinical laboratorians will likely be confronted with the challenges associated with artificial intelligence (AI). Understanding what AI is good for, how to evaluate it, what are its limitations, and how it can be implemented are not well understood. With a survey, we aimed to evaluate the thoughts of stakeholders in laboratory medicine on the value of AI in the diagnostics space and identify anticipated challenges and solutions to introducing AI.

METHODS

We conducted a web-based survey on the use of AI with participants from Roche's Strategic Advisory Network that included key stakeholders in laboratory medicine.

RESULTS

In total, 128 of 302 stakeholders responded to the survey. Most of the participants were medical practitioners (26%) or laboratory managers (22%). AI is currently used in the organizations of 15.6%, while 66.4% felt they might use it in the future. Most had an unsure attitude on what they would need to adopt AI in the diagnostics space. High investment costs, lack of proven clinical benefits, number of decision makers, and privacy concerns were identified as barriers to adoption. Education in the value of AI, streamlined implementation and integration into existing workflows, and research to prove clinical utility were identified as solutions needed to mainstream AI in laboratory medicine.

CONCLUSIONS

This survey demonstrates that specific knowledge of AI in the medical community is poor and that AI education is much needed. One strategy could be to implement new AI tools alongside existing tools.

Ensemble of machine learning algorithms using the stacked generalization approach to estimate the warfarin dose

Warfarin dosing remains challenging due to narrow therapeutic index and highly individual variability. Incorrect warfarin dosing is associated with devastating adverse events. Remarkable efforts have been made to develop the machine learning based warfarin dosing algorithms incorporating clinical factors and genetic variants such as polymorphisms in CYP2C9 and VKORC1. The most widely validated pharmacogenetic algorithm is the IWPC algorithm based on multivariate linear regression (MLR). However, with only a single algorithm, the prediction performance may reach an upper limit even with optimal parameters. Here, we present novel algorithms using stacked generalization frameworks to estimate the warfarin dose, within which different types of machine learning algorithms function together through a meta-machine learning model to maximize the prediction accuracy. Compared to the IWPC-derived MLR algorithm, Stack 1 and 2 based on stacked generalization frameworks performed significantly better overall. Subgroup analysis revealed that the mean of the percentage of patients whose predicted dose of warfarin within 20% of the actual stable therapeutic dose (mean percentage within 20%) for Stack 1 was improved by 12.7% (from 42.47% to 47.86%) in Asians and by 13.5% (from 22.08% to 25.05%) in the low-dose group compared to that for MLR, respectively. These data suggest that our algorithms would especially benefit patients requiring low warfarin maintenance dose, as subtle changes in warfarin dose could lead to adverse clinical events (thrombosis or bleeding) in patients with low dose. Our study offers novel pharmacogenetic algorithms for clinical trials and practice.

Discussion of “The Evolution of Boosting Algorithms” and “Extending Statistical Boosting”

This article is part of a For-Discussion-Section of Methods of Information in Medicine about the papers “The Evolution of Boosting Algorithms – From Machine Learning to Statistical Modelling” [1] and “Extending Statistical Boosting – An Overview of Recent Methodological Developments” [2], written by Andreas Mayr and co-authors. It is introduced by an editorial. This article contains the combined commentaries invited to independently comment on the Mayr et al. papers. In sub-sequent issues the discussion can continue through letters to the editor.

Machine learning in laboratory medicine: waiting for the flood?

This review focuses on machine learning and on how methods and models combining data analytics and artificial intelligence have been applied to laboratory medicine so far. Although still in its infancy, the potential for applying machine learning to laboratory data for both diagnostic and prognostic purposes deserves more attention by the readership of this journal, as well as by physician-scientists who will want to take advantage of this new computer-based support in pathology and laboratory medicine.

Warfarin Dosing Algorithms Underpredict Dose Requirements in Patients Requiring ≥7 mg Daily: A Systematic Review and Meta-analysis

There is preliminary evidence to suggest that some published warfarin dosing algorithms produce biased maintenance dose predictions in patients who require higher than average doses. We conducted a meta-analysis of warfarin dosing algorithms to determine if there exists a systematic under- or overprediction of dose requirements for patients requiring ≥7 mg/day across published algorithms. Medline and Embase databases were searched up to September 2015. We quantified the proportion of over- and underpredicted doses in patients whose observed maintenance dose was ≥7 mg/day. The meta-analysis included 47 evaluations of 22 different warfarin dosing algorithms from 16 studies. The meta-analysis included data from 1,492 patients who required warfarin doses of ≥7 mg/day. All 22 algorithms were found to underpredict warfarin dosing requirements in patients who required ≥7 mg/day by an average of 2.3 mg/day with a pooled estimate of underpredicted doses of 92.3% (95% confidence interval 90.3-94.1, I² = 24%).

Applying machine learning techniques to the identification of late-onset hypogonadism in elderly men

In the diagnosis of late-onset hypogonadism (LOH), the Androgen Deficiency in the Aging Male (ADAM) questionnaire or Aging Males' Symptoms (AMS) scale can be used to assess related symptoms. Subsequently, blood tests are used to measure serum testosterone levels. However, results obtained using ADAM and AMS have revealed no significant correlations between ADAM and AMS scores and LOH, and the rate of misclassification is high. Recently, many studies have reported significant associations between clinical conditions such as the metabolic syndrome, obesity, lower urinary tract symptoms, and LOH. In this study, we sampled 772 clinical cases of men who completed both a health checkup and two questionnaires (ADAM and AMS). The data were obtained from the largest medical center in Taiwan. Two well-known classification techniques, the decision tree (DT) and logistic regression, were used to construct LOH prediction models on the basis of the aforementioned features. The results indicate that although the sensitivity of ADAM is the highest (0.878), it has the lowest specificity (0.099), which implies that ADAM overestimates LOH occurrence. In addition, DT combined with the AdaBoost technique (AdaBoost DT) has the second highest sensitivity (0.861) and specificity (0.842), resulting in having the best accuracy (0.851) among all classifiers. AdaBoost DT can provide robust predictions that will aid clinical decisions and can help medical staff in accurately assessing the possibilities of LOH occurrence.

Improving Bridging from Informatics Theory to Practice

BACKGROUND

In 1962, Methods of Information in Medicine (MIM) began to publish papers on the methodology and scientific fundamentals of managing data, information, and knowledge in biomedicine and health care. Meeting an increasing demand for research about practical implementation of health information systems, the journal Applied Clinical Informatics (ACI) was launched in 2009. Both journals are official journals of the International Medical Informatics Association (IMIA).

OBJECTIVES

Based on prior analyses, we aimed to describe major topics published in MIM during 2014 and to explore whether theory of MIM influenced practice of ACI. Our objectives were further to describe lessons learned and to discuss possible editorial policies to improve bridging from theory to practice.

METHODS

We conducted a retrospective, observational study reviewing MIM articles published during 2014 (N=61) and analyzing reference lists of ACI articles from 2014 (N=70). Lessons learned and opinions about MIM editorial policies were developed in consensus by the two authors. These have been influenced by discussions with the journal's associate editors and editorial board members.

RESULTS

The publication topics of MIM in 2014 were broad, covering biomedical and health informatics, medical biometry and epidemiology. Important topics discussed were biosignal interpretation, boosting methodologies, citation analysis, health-enabling and ambient assistive technologies, health record banking, safety, and standards. Nine ACI practice articles from 2014 cited eighteen MIM theory papers from any year. These nine ACI articles covered mainly the areas of clinical documentation and medication-related decision support. The methodological basis they cited from was almost exclusively related to evaluation. We could show some direct links where theory impacted practice. These links are however few in relation to the total amount of papers published.

CONCLUSIONS

Editorial policies such as publishing systematic methodological reviews and clarification of possible practical impact of theory-focused articles may improve bridging.

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.

Comparison of the predictive abilities of pharmacogenetics-based warfarin dosing algorithms using seven mathematical models in Chinese patients

AIM

This study is aimed to find the best predictive model for warfarin stable dosage.

MATERIALS & METHODS

Seven models, namely multiple linear regression (MLR), artificial neural network, regression tree, boosted regression tree, support vector regression, multivariate adaptive regression spines and random forest regression, as well as the genetic and clinical data of two Chinese samples were employed.

RESULTS

The average predicted achievement ratio and mean absolute error of the algorithms were ranging from 52.31 to 58.08% and 4.25 to 4.84 mg/week in validation samples, respectively. The algorithm based on MLR showed the highest predicted achievement ratio and the lowest mean absolute error.

CONCLUSION

At present, MLR may be still the best model for warfarin stable dosage prediction in Chinese population. Original submitted 10 November 2014; Revision submitted 18 February 2015.