Effect of an artificial intelligence-assisted tool on non-valvular atrial fibrillation anticoagulation management in primary care: protocol for a cluster randomized controlled trial

Reporting Quality of AI Intervention in Randomized Controlled Trials in Primary Care: Systematic Review and Meta-Epidemiological Study

BACKGROUND

The surge in artificial intelligence (AI) interventions in primary care trials lacks a study on reporting quality.

OBJECTIVE

This study aimed to systematically evaluate the reporting quality of both published randomized controlled trials (RCTs) and protocols for RCTs that investigated AI interventions in primary care.

METHODS

PubMed, Embase, Cochrane Library, MEDLINE, Web of Science, and CINAHL databases were searched for RCTs and protocols on AI interventions in primary care until November 2024. Eligible studies were published RCTs or full protocols for RCTs exploring AI interventions in primary care. The reporting quality was assessed using CONSORT-AI (Consolidated Standards of Reporting Trials-Artificial Intelligence) and SPIRIT-AI (Standard Protocol Items: Recommendations for Interventional Trials-Artificial Intelligence) checklists, focusing on AI intervention-related items.

RESULTS

A total of 11,711 records were identified. In total, 19 published RCTs and 21 RCT protocols for 35 trials were included. The overall proportion of adequately reported items was 65% (172/266; 95% CI 59%-70%) and 68% (214/315; 95% CI 62%-73%) for RCTs and protocols, respectively. The percentage of RCTs and protocols that reported a specific item ranged from 11% (2/19) to 100% (19/19) and from 10% (2/21) to 100% (21/21), respectively. The reporting of both RCTs and protocols exhibited similar characteristics and trends. They both lack transparency and completeness, which can be summarized in three aspects: without providing adequate information regarding the input data, without mentioning the methods for identifying and analyzing performance errors, and without stating whether and how the AI intervention and its code can be accessed.

CONCLUSIONS

The reporting quality could be improved in both RCTs and protocols. This study helps promote the transparent and complete reporting of trials with AI interventions in primary care.

The Application of Artificial Intelligence in Atrial Fibrillation Patients: From Detection to Treatment

Atrial fibrillation (AF) is the most prevalent arrhythmia worldwide. Although the guidelines for AF have been updated in recent years, its gradual onset and associated risk of stroke pose challenges for both patients and cardiologists in real-world practice. Artificial intelligence (AI) is a powerful tool in image analysis, data processing, and for establishing models. It has been widely applied in various medical fields, including AF. In this review, we focus on the progress and knowledge gap regarding the use of AI in AF patients and highlight its potential throughout the entire cycle of AF management, from detection to drug treatment. More evidence is needed to demonstrate its ability to improve prognosis through high-quality randomized controlled trials.

Community-based prevention and treatment of cardiovascular diseases

The Annual Report on Cardiovascular Health and Diseases in China (2022) intricate landscape of cardiovascular health in China. This is the third section of the report with a specific focus on community-based prevention and treatment of cardiovascular diseases (CVD). This section of the report underscores the importance of initiatives outlined in the "Healthy China 2030 Plan," emphasizing the comprehensive prevention and control strategy for chronic diseases. A key aspect of this plan involves the establishment of national demonstration areas aimed at comprehensive prevention and control of chronic diseases. By 2020, 488 such areas had been set up across China, surpassing the initial target and covering a significant proportion of counties and districts. The report highlights the successful implementation of these strategies in Lishan district, Anshan city, where demonstration areas for comprehensive prevention and control of chronic diseases were launched in 2013. Over the course of seven years, the number of healthy units increased substantially, leading to improvements in managing risk factors for CVD among residents. Significant reductions in prevalence rates of overweight, obesity, smoking, passive smoking, and drinking were observed, along with the development of healthier behaviors among residents. Similarly, Qiaokou district in Wuhan City, designated as a national demonstration area in 2014, implemented comprehensive public health promotion initiatives. Notably, special clinics for hypertension intervention were established, contributing to an increase in self-reported rates of hypertension, a slight decrease in prevalence, and a remarkable improvement in the control rate among treated patients. Overall, these efforts underscore the effectiveness of community-based approaches in driving positive health outcomes and advancing the comprehensive prevention and control of chronic diseases, particularly cardiovascular diseases, in China.

Using a Clinical Decision Support System to Improve Anticoagulation in Patients with Nonvalve Atrial Fibrillation in China's Primary Care Settings: A Feasibility Study

BACKGROUND

To primarily investigate the effect of using a clinical decision support system (CDSS) in community health centers in Shanghai, China, on the proportion of patients prescribed guideline-directed antithrombotic therapy. This study also gauged the general practitioner (GP)'s acceptance of the CDSS who worked in the atrial fibrillation (AF) special consulting room of the CDSS group.

METHODS

This was a prospective cohort study that included a semistructured interview and a feasibility study for a cluster-randomized controlled trial. Eligible patients who sought medical care in the AF special consulting rooms in two community health centers in Shanghai, China, between April 1, 2020, and October 1, 2020, were enrolled, and their medical records from the enrollment date, up to October 1, 2021, were extracted. Based on whether the GPs in the AF special consulting rooms of the two sites used the CDSS or not, we classified the two sites as a software group and a control group. The CDSS could automatically assess the risks of stroke and bleeding and provide suggestions on treatment, follow-up, adjustment of anticoagulants or dosage, and other items. The primary outcome was the proportion of patients prescribed guideline-directed antithrombotic therapy. We also conducted a semistructured interview with the GP in the AF special consulting rooms of the software group regarding the acceptance of the CDSS and suggestions on the optimization of the CDSS and the study protocol of the cluster-randomized controlled trial in the future.

RESULTS

Eighty-four patients completed the follow-up. The mean age of these subjects was 75.71 years, the median time of clinical visits was six times per person, and the follow-up duration was 15 months. The basic demographics were similar between the two groups, except for age (t = 2.109, p = 0.038) and the HAS-BLED score (χ ² = 4.363, p = 0.037). The primary outcome in the software group was 8.071 times higher than that in the control group (adjusted odds ratio (OR) = 8.071, 95% confidence interval (2.570-25.344), p < 0.001). The frequency of consultation between groups was not significantly different (p = 0.981). It seemed that the incidence of adverse clinical events in the software group was lower than that in the control group. The main reason for dropouts in both groups was "following up in other hospitals." The GP in the AF special consulting rooms of the software group accepted the CDSS well.

CONCLUSIONS

The findings indicated that it was feasible to further promote the CDSS in the study among community health centers in China. The use of the CDSS might improve the proportion of patients prescribed guideline-directed antithrombotic therapy. The GP in the AF special consulting room of the software group showed a positive attitude toward the CDSS.

Guideline Adherence As An Indicator of the Extent of Antithrombotic Overuse and Underuse: A Systematic Review

Thromboembolic events are a common risk in adults with atrial fibrillation, those with previous cerebrovascular accidents and undergoing emergency or elective surgeries. The widespread availability of antithrombotic agents and differing guidelines contribute to practice variations and increased risk of complications and deaths. The objective of this review was to investigate the extent of overuse and underuse of antithrombotics for primary or secondary prevention as measured by deviation from prescribing guideline recommendations. We conducted a systematic review of Medline and EMBASE for quantitative articles published between 2000 and 2021 and used a modified version of the Hoy’s risk of bias assessment tool. Here we report evidence from the past decade about wide practice variations in hospitals and primary care, and discuss clinician and patient-driven determinants of non-adherence to guidelines. Finally, we summarise implications for practice, identify enhanced ways of measuring overuse and underuse, and propose potential solutions to the measurement challenges.

Development and validation of a mobile application based on a machine learning model to aid in predicting dosage of vitamin K antagonists among Indian patients post mechanical heart valve replacement

Patients who undergo heart valve replacements with mechanical valves need to take Vitamin K Antagonists (VKA) drugs (Warfarin, Nicoumalone) which has got a very narrow therapeutic range and needs very close monitoring using PT-INR. Accessibility to physicians to titrate drugs doses is a major problem in low-middle income countries (LMIC) like India. Our work was aimed at predicting the maintenance dosage of these drugs, using the de-identified medical data collected from patients attending an INR Clinic in South India. We used artificial intelligence (AI) - machine learning to develop the algorithm. A Support Vector Machine (SVM) regression model was built to predict the maintenance dosage of warfarin, who have stable INR values between 2.0 and 4.0. We developed a simple user friendly android mobile application for patients to use the algorithm to predict the doses. The algorithm generated drug doses in 1100 patients were compared to cardiologist prescribed doses and found to have an excellent correlation.