Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: The effective implementation of personalized pharmacogenomics (PGx) requires the integration of released clinical guidelines into decision support systems (CDSS) to facilitate clinical applications. Large language models (LLMs) can be valuable tools for automating information extraction and updates. Objective: To assess the effectiveness of repeated cross-comparisons and an agreement-threshold strategy in two advanced LLMs as supportive tools for updating information. Methods: The study evaluated the performance of two LLMs, GPT-4o and Gemini-1.5-Pro, in extracting PGx clinical guidelines and comparing their outputs with expert-annotated evaluations. The two LLMs classified 385 PGx clinical guidelines, with each recommendation tested 20 times per model. Accuracy was assessed by comparing the results with manually labeled data. Two prospectively defined strategies were employed to identify inconsistent predictions. The first involved repeated cross-comparison, flagging discrepancies between the most frequent classifications from each model. The second employed a consistency threshold strategy, which designated predictions appearing in less than 60% of the 40 combined outputs as unstable. Cases flagged by either strategy were subjected to manual review. This study also estimated the overall cost of model usage and was conducted between October 1 and November 30, 2024. Results: GPT-4o and Gemini-1.5-Pro yielded reproducibility rates of 97.8% (7,534/7,700) and 98.9% (7,612/7,700), respectively, based on the most frequent classification for each query. Compared with expert labels, GPT-4o achieved 93.5% accuracy (Cohen’s Kappa=0.90; P<.001) and Gemini-1.5-Pro 92.7% accuracy (Cohen’s Kappa=0.89; P<.001). Both models demonstrated high overall performance, with comparable weighted average F1 scores (GPT-4o: 0.9288; Gemini: 0.9350). The models generated consistent predictions for 341 of 385 guideline items, reducing the need for manual review by 88.6%. Among these agreed-upon cases, only one (0.3%) diverged from expert labels. Applying a predefined agreement-threshold strategy further reduced the number of priority manual review cases to 2.9% (11/385), although the error rate slightly increased to 0.5% (2/374). The inconsistencies identified through these methods prompted prioritization of manual review to minimize errors and enhance clinical applicability. The total combined cost of using both LLMs was only $0.76. Conclusions: These findings suggest that using two LLMs can effectively streamline PGx guideline integration into CDSS, while maintaining high performance and minimal cost. Although selective manual review remains necessary, this approach offers a practical and scalable solution for PGx guideline classification in clinical workflows.

Doxorubicin (DOX) is a potent chemotherapeutic widely used against various cancers, but its clinical application is limited by DOX-induced cardiotoxicity (DIC). This study explored the cardioprotective potential of extracellular vesicle-enriched secretome derived from adipose stem cells (EVS_ASC) in mitigating DOX-induced apoptosis in cardiomyocytes. Adipose-derived stem cells were cultured, and their conditioned medium and extraceullular vesicles were isolated and characterized according to the Minimal Information for Studies of Extracellular Vesicles 2023 guidelines. HL-1 cardiomyocytes were pretreated with EVS_ASC before exposure to 1 µM DOX. Cell viability was assessed via the cell counting kit-8 assay, while apoptosis markers and survival mediators were evaluated through Western blotting. RNA sequencing identified differentially expressed genes, including clusterin (Clu), which was further quantified using an enzyme-linked immunosorbent assay. The functional role of clusterin was validated through siRNA-mediated knockdown. EVS_ASC significantly improved cell viability in DOX-exposed cardiomyocytes and reduced the cleaved caspase-3 to procaspase-3 ratio. Clusterin expression was highest in EVS_ASC-treated cells, and its knockdown markedly increased caspase-3 cleavage, confirming its pivotal role in cardioprotection. Moreover, EVS_ASC enhanced the phosphorylation of AKT, Bcl2-associated agonist of cell death, and glycogen synthase kinase-3β, implicating PI3K/AKT pathway activation in clusterin upregulation and anti-apoptotic effects. These findings demonstrate that EVS_ASC mitigates DOX-induced apoptosis in cardiomyocytes through clusterin upregulation and PI3K/AKT pathway activation. Clusterin is identified as a potential biomarker for evaluating EVS_ASC efficacy. While EVS_ASC shows promise as a cardioprotective strategy against DIC, further studies are needed to optimize its therapeutic safety by addressing potential oncogenic risks.

Angiotensin inhibition remains a cornerstone for pharmacologic management of heart failure (HF), despite being associated with decreased hemoglobin (Hb) levels. To investigate the effect of anemia and its treatment on patients with HF treated with sacubitril–valsartan (S/V), we conducted a retrospective study involving patients with recorded left ventricular ejection fractions (LVEFs) of < 40% between January 2017 and December 2019. We identified 677 patients, 37.7% of whom received S/V. The median follow-up period was 868 days. Anemia was associated with significantly decreased survival, increased mortality rates, and higher all-cause hospitalizations in S/V-using patients. We further analyzed 236 patients with HF who had recorded renal function, LVEF, and Hb at the initiation of S/V therapy to identify Hb patterns after S/V therapy. Of these patients, 35.6% exhibited decreasing Hb 12 months after S/V initiation, which was associated with a lower survival rate. Among the patients who were not prescribed anemia medications, Hb of ≥ 12 (vs. < 12 g/dL) was associated with a higher survival rate; this association was absent among the patients undergoing anemia treatment. These results emphasize that consistent screening and treatment for anemia should be implemented to reduce the morbidity and mortality of patients with HF receiving S/V.