Pasupathy, Kalyan S.

Abstract Background Hypertrophic cardiomyopathy (HCM) is a heritable cardiac disorder characterized by increased left ventricular (LV) wall thickness, often leading to heart failure (HF). The role of cardiovascular magnetic resonance (CMR) imaging in predicting new onset of HF symptoms in patients with HCM remains unknown. This study aimed to identify CMR predictors of new-onset HF symptoms in individuals with HCM. Methods This study was a single-centre retrospective cohort study of HCM patients treated at a tertiary referral centre in the USA who underwent CMR examination between 1998 and 2018, had no HF symptoms at baseline CMR, and at least 1 year of follow-up. Clinical data were collected by review of electronic medical records, and CMR images were analyzed by a blinded expert cardiac radiologis. The primary outcome was new onset of HF symptoms, defined as New York Heart Association (NYHA) class ≥ II at follow-up. Kaplan–Meier analyses and Cox proportional hazard analyses were performed. Results Of 1462 patients diagnosed with HCM who had at least 1 CMR, 276 HCM patients without HF symptoms (average age 52.7 years, 33.3% female),median maximum left ventricular (LV) wall thickness was 19 mm ([IQR] 17–22) with a and median LV ejection fraction of 71% (IQR 66–77). Late gadolinium enhancement was detected in 56.2%) patients (60.7% had mild; 30.7% moderate; 8.6% severe). During a median follow-up period of 6.3 years, 93 patients developed HF symptoms (NYHA class II in 56 (60.2%); class III in 31 (33.3%); and class IV in 6 (6.5%). Multivariable analysis adjusted for age showed that LA enlargement (HR 1.626; 95% CI 1.01–2.62; P = .045) and LV mass index (HR 1.014; 95% CI 1.007–1.022; P≤ .001) and sex (HR 1.7; 95% CI 1.074–2.691; P = .023) were independent predictors of new onset of HF symptoms in patients with HCM. Conclusions Nearly half of the patients with HCM developed HF symptoms within 6.3 years. Left atrial enlargement, LV mass index, and sex were independent predictors of new onset of HF symptoms in HCM patients. These findings emphasize the value of CMR in HF risk stratification.

Objectives: Electronic health records (EHR)-based triggers (eTriggers) have been used to study diagnostic errors in the emergency department (ED), often with suboptimal performance. Our objective was to investigate incremental value of multi-factor machine learning (ML) approaches to improve eTrigger performance. Methods: Patients presenting to an academic ED were categorized into trigger-positive and trigger-negative using standard trigger (T) definitions: (T1) ED return visits resulting in admission within 10 days; (T2) care escalation from the inpatient unit to the ICU within 24 hours; and (T3) deaths within 24 hours of admission. We trained and evaluated 6 supervised ML models. Results: A total of 124,053 consecutive encounters (5791 T-positive and 118,262 T-negative) were included. Among the T-positive, 4159 (72%) were associated with T1, 1415 (24%) with T2, and 217 (4%) with T3. The T-based positive predictive values (PPV) were 5.2% for T1, 8.2% for T2, and 6.5% for T3. ML models trained and evaluated on balanced training dataset and imbalanced test set had low classification performances (accuracy: 0.72–0.95; PPV: 0.00–0.16; F1-score: 0.00–0.23). Higher performances were observed in balanced test sets (accuracy: 0.80–0.97; PPV: 0.82–1.00; F1-score: 0.79–0.97). Comparing models trained on clinically annotated data with models trained on T-based labels identified other important factors. Conclusions: Utilizing machine learning to refine e-triggers slightly improves the identification of diagnostic errors, as evidenced by an increase in PPV values. We identified new potential factors contributing to ED diagnostic errors. These findings open new avenues to construct or modify more accurate e-triggers for diagnostic error identification.

Importance Diagnostic errors represent a major patient safety concern, with the potential to significantly impact patient outcomes. To address this, various trigger-based strategies have been developed to identify diagnostic errors, aiming to enhance clinical decision-making and improve patient safety. Objective To evaluate the performance of three pre-established triggers (T) in the emergency department (ED) setting and assess their effectiveness in detecting diagnostic errors. Design Consecutive cohort, retrospective observational design. Setting Academic ED with 80 000 annual visits. Participants Adults and children presenting to a single ED in the USA between 1 May 2018 and 1 January 2020. Intervention/outcomes Electronic health records (EHRs) were retrieved and categorised into trigger-positive and trigger-negative cases using the following criteria: T1—unscheduled returnvisits to the ED with admission within 7–10 days of theinitial visit; T2—care escalation from the inpatient unitto the intensive care unit (ICU) within 6, 12 or 24 hoursof ED admission; and T3—all deaths in the ED or within24 hours of ED admission, excluding palliative care. A random sample of trigger-positive cases was reviewed using the SaferDx tool to determine the presence or absence of a diagnostic error. Results A total of 5791 trigger-positive and 118262 trigger-negative cases were identified. Among trigger-positive cases, 4159 (72%) were associated with T1, 1415 (24%) with T2, and 217 (4%) with T3. A preliminary chart review of 462 trigger-positive and 251 trigger-negative cases showed most were error-negative (279 and 217, respectively). Detailed reviews found 32 diagnostic errors among 183 trigger-positive cases, yielding PPVs of 5.4% (T1), 8.9% (T2), and 6.9% (T3). No errors were found in 34 reviewed trigger-negative cases, resulting in a 100% NPV. Sepsis was the most common diagnosis among error-positive cases (n=11, 34.4%). Those with non-specific chief complaints like altered mental status or shortness of breath had higher diagnostic error risk. Conclusion and relevance While previously proposed EHR-based triggers can identify some diagnostic errors, they are insufficient for detecting all cases. To improve error detection performance, we recommend exploring data-driven strategies, such as machine learning techniques, to more effectively identify underlying contributing factors to diagnostic errors and enhance detection accuracy in the ED.

Abstract Objectives There is limited knowledge on how providers and patients in the emergency department (ED) use electronic health records (EHRs) to facilitate the diagnostic process. While EHRs can support diagnostic decision-making, EHR features that are not user-centered may increase the likelihood of diagnostic error. We aimed to identify how EHRs facilitate or impede the diagnostic process in the ED and to identify opportunities to reduce diagnostic errors and improve care quality. Materials and Methods We conducted semistructured interviews with 10 physicians, 15 nurses, and 8 patients across 4 EDs. Data were analyzed using a hybrid thematic analysis approach, which blends deductive (ie, using multiple conceptual frameworks) and inductive coding strategies. A team of 4 coders performed coding. Results We identified 4 themes, 3 at the care team level and 1 at the patient level. At the care team level, the benefits of the EHR in the diagnostic process included (1) customizing features to facilitate diagnostic workup and (2) aiding in communication. However, (3) EHR-driven protocols were found to potentially burden the care process and reliance on asynchronous communication could impede team dynamics. At the patient-level, we found that (4) patient portals facilitated meaningful patient engagement through timely delivery of results. Discussion While EHRs can improve the diagnostic process, they can also impair communication and increase workload. Electronic health record design should leverage provider-created tools to improve usability and enhance diagnostic safety. Conclusions Our findings have important implications for health information technology design and policy. Further work should assess optimal ways to release patient results via the EHR portal.

AbstractObjectiveTo report the first steps of a project to automate and optimize scheduling of multidisciplinary consultations for patients with longstanding dizziness utilizing artificial intelligence.Study DesignRetrospective case review.SettingQuaternary referral center.MethodsA previsit self‐report questionnaire was developed to query patients about their complaints of longstanding dizziness. We convened an expert panel of clinicians to review diagnostic outcomes for 98 patients and used a consensus approach to retrospectively determine what would have been the ideal appointments based on the patient's final diagnoses. These results were then compared retrospectively to the actual patient schedules. From these data, a machine learning algorithm was trained and validated to automate the triage process.ResultsCompared with the ideal itineraries determined retrospectively with our expert panel, visits scheduled by the triage clinicians showed a mean concordance of 70%, and our machine learning algorithm triage showed a mean concordance of 79%.ConclusionManual triage by clinicians for dizzy patients is a time‐consuming and costly process. The formulated first‐generation automated triage algorithm achieved similar results to clinicians when triaging dizzy patients using data obtained directly from an online previsit questionnaire.