A treatment recommender clinical decision support system for personalized medicine: method development and proof-of-concept for drug resistant tuberculosis

A machine-learning based model for automated recommendation of individualized treatment of rifampicin-resistant tuberculosis

BACKGROUND

Rifampicin resistant tuberculosis remains a global health problem with almost half a million new cases annually. In high-income countries patients empirically start a standardized treatment regimen, followed by an individualized regimen guided by drug susceptibility test (DST) results. In most settings, DST information is not available or is limited to isoniazid and fluoroquinolones. Whole genome sequencing could more accurately guide individualized treatment as the full drug resistance profile is obtained with a single test. Whole genome sequencing has not reached its full potential for patient care, in part due to the complexity of translating a resistance profile into the most effective individualized regimen.

METHODS

We developed a treatment recommender clinical decision support system (CDSS) and an accompanying web application for user-friendly recommendation of the optimal individualized treatment regimen to a clinician.

RESULTS

Following expert stakeholder meetings and literature review, nine drug features and 14 treatment regimen features were identified and quantified. Using machine learning, a model was developed to predict the optimal treatment regimen based on a training set of 3895 treatment regimen-expert feedback pairs. The acceptability of the treatment recommender CDSS was assessed as part of a clinical trial and in a routine care setting. Within the clinical trial setting, all patients received the CDSS recommended treatment. In 8 of 20 cases, the initial recommendation was recomputed because of stock out, clinical contra-indication or toxicity. In routine care setting, physicians rejected the treatment recommendation in 7 out of 15 cases because it deviated from the national TB treatment guidelines. A survey indicated that the treatment recommender CDSS is easy to use and useful in clinical practice but requires digital infrastructure support and training.

CONCLUSIONS

Our findings suggest that global implementation of the novel treatment recommender CDSS holds the potential to improve treatment outcomes of patients with RR-TB, especially those with 'difficult-to-treat' forms of RR-TB.

Effectiveness of Artificial Intelligence (AI) in Clinical Decision Support Systems and Care Delivery

This review aims to assess the effectiveness of AI-driven CDSSs on patient outcomes and clinical practices. A comprehensive search was conducted across PubMed, MEDLINE, and Scopus. Studies published from January 2018 to November 2023 were eligible for inclusion. Following title and abstract screening, full-text articles were assessed for methodological quality and adherence to inclusion criteria. Data extraction focused on study design, AI technologies employed, reported outcomes, and evidence of AI-CDSS impact on patient and clinical outcomes. Thematic analysis was conducted to synthesise findings and identify key themes regarding the effectiveness of AI-CDSS. The screening of the articles resulted in the selection of 26 articles that satisfied the inclusion criteria. The content analysis revealed four themes: early detection and disease diagnosis, enhanced decision-making, medication errors, and clinicians' perspectives. AI-based CDSSs were found to improve clinical decision-making by providing patient-specific information and evidence-based recommendations. Using AI in CDSSs can potentially improve patient outcomes by enhancing diagnostic accuracy, optimising treatment selection, and reducing medical errors.

Effect of Obesity on the Use of Antiarrhythmics in Adults With Atrial Fibrillation: A Narrative Review

BACKGROUND

Atrial fibrillation (AF) and obesity coexist in approximately 37.6 million and 650 million people globally, respectively. The anatomical and physiological changes in individuals with obesity may influence the pharmacokinetic properties of drugs.

AIM

This review aimed to describe the evidence of the effect of obesity on the pharmacokinetics of antiarrhythmics in people with AF.

METHODS

Three databases were searched from inception to June 2023. Original studies that addressed the use of antiarrhythmics in adults with AF and concomitant obesity were included.

RESULTS

A total of 4549 de-duplicated articles were screened, and 114 articles underwent full-text review. Ten studies were included in this narrative synthesis: seven cohort studies, two pharmacokinetic studies, and a single case report. Samples ranged from 1 to 371 participants, predominately males (41%-85%), aged 59-75 years, with a body mass index (BMI) of 23-66 kg/m2. The two most frequently investigated antiarrhythmics were amiodarone and dofetilide. Other drugs investigated included diltiazem, flecainide, disopyramide, propafenone, dronedarone, sotalol, vernakalant, and ibutilide. Findings indicate that obesity may affect the pharmacokinetics of amiodarone and sodium channel blockers (e.g., flecainide, disopyramide, and propafenone). Factors such as drug lipophilicity may also influence the pharmacokinetics of the drug and the need for dose modification.

DISCUSSION

Antiarrhythmics are not uniformly affected by obesity. This observation is based on heterogeneous studies of participants with an average BMI and poorly controlled confounding factors such as multimorbidity, concomitant medications, varying routes of administration, and assessment of obesity. Controlled trials with stratification at the time of recruitment for obesity are necessary to determine the significance of these findings.

APPRAISE-RS: Automated, updated, participatory, and personalized treatment recommender systems based on GRADE methodology

Purpose

Clinical practice guidelines (CPGs) have become fundamental tools for evidence-based medicine (EBM). However, CPG suffer from several limitations, including obsolescence, lack of applicability to many patients, and limited patient participation. This paper presents APPRAISE-RS, which is a methodology that we developed to overcome these limitations by automating, extending, and iterating the methodology that is most commonly used for building CPGs: the GRADE methodology.

Method

APPRAISE-RS relies on updated information from clinical studies and adapts and automates the GRADE methodology to generate treatment recommendations. APPRAISE-RS provides personalized recommendations because they are based on the patient's individual characteristics. Moreover, both patients and clinicians express their personal preferences for treatment outcomes which are considered when making the recommendation (participatory). Rule-based system approaches are used to manage heuristic knowledge.

Results

APPRAISE-RS has been implemented for attention deficit hyperactivity disorder (ADHD) and tested experimentally on 28 simulated patients. The resulting recommender system (APPRAISE-RS/TDApp) shows a higher degree of treatment personalization and patient participation than CPGs, while recommending the most frequent interventions in the largest body of evidence in the literature (EBM). Moreover, a comparison of the results with four blinded psychiatrist prescriptions supports the validation of the proposal.

Conclusions

APPRAISE-RS is a valid methodology to build recommender systems that manage updated, personalized and participatory recommendations, which, in the case of ADHD includes at least one intervention that is identical or very similar to other drugs prescribed by psychiatrists.

Bedaquiline resistance probability to guide treatment decision making for rifampicin-resistant tuberculosis: insights from a qualitative study

BACKGROUND

Bedaquiline (BDQ) is a core drug for rifampicin-resistant tuberculosis (RR-TB) treatment. Accurate prediction of a BDQ-resistant phenotype from genomic data is not yet possible. A Bayesian method to predict BDQ resistance probability from next-generation sequencing data has been proposed as an alternative.

METHODS

We performed a qualitative study to investigate the decision-making of physicians when facing different levels of BDQ resistance probability. Fourteen semi-structured interviews were conducted with physicians experienced in treating RR-TB, sampled purposefully from eight countries with varying income levels and burden of RR-TB. Five simulated patient scenarios were used as a trigger for discussion. Factors influencing the decision of physicians to prescribe BDQ at macro-, meso- and micro levels were explored using thematic analysis.

RESULTS

The perception and interpretation of BDQ resistance probability values varied widely between physicians. The limited availability of other RR-TB drugs and the high cost of BDQ hindered physicians from altering the BDQ-containing regimen and incorporating BDQ resistance probability in their decision-making. The little experience with BDQ susceptibility testing and whole-genome sequencing results, and the discordance between phenotypic susceptibility and resistance probability were other barriers for physicians to interpret the resistance probability estimates. Especially for BDQ resistance probabilities between 25% and 70%, physicians interpreted the resistance probability value dynamically, and other factors such as clinical and bacteriological treatment response, history of exposure to BDQ, and resistance profile were often considered more important than the BDQ probability value for the decision to continue or stop BDQ. In this grey zone, some physicians opted to continue BDQ but added other drugs to strengthen the regimen.

CONCLUSIONS

This study highlights the complexity of physicians' decision-making regarding the use of BDQ in RR-TB regimens for different levels of BDQ resistance probability.. Ensuring sufficient access to BDQ and companion drugs, improving knowledge of the genotype-phenotype association for BDQ resistance, availability of a rapid molecular test, building next-generation sequencing capacity, and developing a clinical decision support system incorporating BDQ resistance probability will all be essential to facilitate the implementation of BDQ resistance probability in personalizing treatment for patients with RR-TB.