Dai, Qiying

Abstract Objectives Heart failure (HF) impacts millions of patients worldwide, yet the variability in treatment responses remains a major challenge for healthcare professionals. The current treatment strategies, largely derived from population based evidence, often fail to consider the unique characteristics of individual patients, resulting in suboptimal outcomes. This study aims to develop computational models that are patient-specific in predicting treatment outcomes, by utilizing a large Electronic Health Records (EHR) database. The goal is to improve drug response predictions by identifying specific HF patient subgroups that are likely to benefit from existing HF medications. Materials and Methods A novel, graph-based model capable of predicting treatment responses, combining Graph Neural Network and Transformer was developed. This method differs from conventional approaches by transforming a patient's EHR data into a graph structure. By defining patient subgroups based on this representation via K-Means Clustering, we were able to enhance the performance of drug response predictions. Results Leveraging EHR data from 11 627 Mayo Clinic HF patients, our model significantly outperformed traditional models in predicting drug response using NT-proBNP as a HF biomarker across five medication categories (best RMSE of 0.0043). Four distinct patient subgroups were identified with differential characteristics and outcomes, demonstrating superior predictive capabilities over existing HF subtypes (best mean RMSE of 0.0032). Discussion These results highlight the power of graph-based modeling of EHR in improving HF treatment strategies. The stratification of patients sheds light on particular patient segments that could benefit more significantly from tailored response predictions. Conclusions Longitudinal EHR data have the potential to enhance personalized prognostic predictions through the application of graph-based AI techniques.

Abstract Aims Takotsubo syndrome (TTS) is a rare complication of vaccination. In this study, we sought to provide insight into the characteristics of reported TTS induced by vaccination. Methods and results We did a systematic review, searching PubMed, Embase, Web of Science, Ovid MEDLINE, Journals@Ovid, and Scopus databases up to 26 April 2023 to identify case reports or case series of vaccine-induced TTS. We then extracted and summarized the data from these reports. Eighteen reports were identified, with a total of 19 patients with TTS associated with vaccinations. Of the 19 included patients, the majority were female (n = 13, 68.4%) with a mean age of 56.6 ± 21.9 years. Seventeen patients developed TTS after coronavirus disease 2019 vaccination, 14 of whom received an mRNA vaccination. Two cases of TTS occurred after influenza vaccination. Among the 19 patients, 17 (89.5%) completed transthoracic echocardiography and 16 (84.2%) underwent angiography procedures. Seven patients (36.8%) completed cardiac magnetic resonance imaging. The median time to symptom onset was 2 (inter-quartile range, 1–4) days. The most common symptoms were chest pain (68.4%), dyspnoea (57.9%), and digestive symptoms (31.6%). A total of 57.9% of patients developed nonspecific symptoms such as fatigue, myalgia, diaphoresis, and fever. Among the 16 reported cases of TTS, 15 patients (93.8%) exhibited elevated cardiac troponin levels, while among the nine reported cases, eight patients (88.9%) had elevated natriuretic peptide levels. All patients had electrocardiographic changes: ST-segment change (47.1%), T-wave inversion (58.8%), and prolonged corrected QT interval (35.3%). The most common TTS type was apical ballooning (88.2%). Treatment during hospitalization typically included beta-blockers (44.4%), angiotensin-converting enzyme inhibitors/angiotensin receptor blockers (33.3%), and diuretics (22.2%). After treatment, 81.3% of patients were discharged with improved symptoms. Among this group, nine patients (56.3%) were reported to have recovered ventricular wall motion during follow-up. Two patients (12.5%) died following vaccination without resuscitation attempts. Conclusions TTS is a rare but potentially life-threatening complication of vaccination. Typical TTS symptoms such as chest pain and dyspnoea should be considered alarming symptoms, though nonspecific symptoms are common. The risks of such rare adverse events should be balanced against the risks of infection.

Abstract Background Alzheimer’s disease (AD) is a progressive neurological disorder with no specific curative medications. Sophisticated clinical skills are crucial to optimize treatment regimens given the multiple coexisting comorbidities in the patient population. Objective Here, we propose a study to leverage reinforcement learning (RL) to learn the clinicians’ decisions for AD patients based on the longitude data from electronic health records. Methods In this study, we selected 1736 patients from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. We focused on the two most frequent concomitant diseases—depression, and hypertension, thus creating 5 data cohorts (ie, Whole Data, AD, AD-Hypertension, AD-Depression, and AD-Depression-Hypertension). We modeled the treatment learning into an RL problem by defining states, actions, and rewards. We built a regression model and decision tree to generate multiple states, used six combinations of medications (ie, cholinesterase inhibitors, memantine, memantine-cholinesterase inhibitors, hypertension drugs, supplements, or no drugs) as actions, and Mini-Mental State Exam (MMSE) scores as rewards. Results Given the proper dataset, the RL model can generate an optimal policy (regimen plan) that outperforms the clinician’s treatment regimen. Optimal policies (ie, policy iteration and Q-learning) had lower rewards than the clinician’s policy (mean −3.03 and −2.93 vs. −2.93, respectively) for smaller datasets but had higher rewards for larger datasets (mean −4.68 and −2.82 vs. −4.57, respectively). Conclusions Our results highlight the potential of using RL to generate the optimal treatment based on the patients’ longitude records. Our work can lead the path towards developing RL-based decision support systems that could help manage AD with comorbidities.