Lester, Steven

Aims:Increased left ventricular (LV) wall thickness is frequently encountered in transthoracic echocardiography (TTE). While accurate and early diagnosis is clinically important, given the differences in available therapeutic options and prognosis, an extensive workup is often required to establish the diagnosis. We propose the first echo-based, automated deep learning model with a fusion architecture to facilitate the evaluation and diagnosis of increased left ventricular (LV) wall thickness. Methods and Results: Patients with an established diagnosis of increased LV wall thickness (hypertrophic cardiomyopathy (HCM), cardiac amyloidosis (CA), and hypertensive heart disease (HTN)/others) between 1/2015 and 11/2019 at Mayo Clinic Arizona were identified. The cohort was divided into 80%/10%/10% for training, validation, and testing sets, respectively. Six baseline TTE views were used to optimize a pre-trained InceptionResnetV2 model. Each model output was used to train a meta-learner under a fusion architecture. Model performance was assessed by multiclass area under the receiver operating characteristic curve (AUROC). A total of 586 patients were used for the final analysis (194 HCM, 201 CA, and 191 HTN/others). The mean age was 55.0 years, and 57.8% were male. Among the individual view-dependent models, the apical 4-chamber model had the best performance (AUROC: HCM: 0.94, CA: 0.73, and HTN/other: 0.87). The final fusion model outperformed all the view-dependent models (AUROC: HCM: 0.93, CA: 0.90, and HTN/other: 0.92). Conclusion: The echo-based InceptionResnetV2 fusion model can accurately classify the main etiologies of increased LV wall thickness and can facilitate the process of diagnosis and workup.

Background: Avoiding early hospital readmission after a diagnosis of atrial fibrillation (AF) lowers healthcare costs. Purpose: This investigation pilot tested the process of using a Connected Health (CH) communication platform in AF care management. Subjects: A self-selected group of patients (n=18, 56% male, mean age=69 years, SD =12.6) diagnosed with hemodynamically stable AF and an uncontrolled ventricular response with heart rates > 110 bpm were recruited. MethodS: Eligibility criteria included a recent AF related emergency department or outpatient clinic visit and the new prescription of a rate control medication. This included AV node modifying medications (either a beta blocker or nondihydropyradine calcium channel blocker) at a starting dose determined by the supervising physician. A care management team (CMT) coordinated by a nurse practitioner provided individualized telephone medical management with no planned clinical visits during a period of early recovery. Patients were equipped with the AliveCor TM Kardia electrocardiogram (ECG) home monitoring device and a supporting mobile device application. Patients returned home with medical guidance from the CMT and ECG recording instructions. Heart rate and rhythm were monitored remotely by the NP and the medication dose was adjusted to reach a target resting heart rate <110 bpm. Patients were managed for 3-weeks before being discharged back to primary care or outpatient cardiology for consideration of a rate versus rhythm control strategy if spontaneous restoration of sinus rhythm had not occurred. ResultS: Patients recorded an average of 50 ( SD =40.0) ECG tracings with a mean of 13 ( SD =3.79) related CMT telephone contacts. The mean resting heart rate was significantly lower ( p <0.05) at the completion of the intervention (72.9 bpm, SD =17.31) compared to baseline (102.3 bpm, SD =27.17). All of the AF patients achieved adequate heart rate control or spontaneously returned to sinus rhythm. However, 4 patients (22%) required a related emergency room visit and unplanned hospitalization. Conclusion: In this small feasibility study, an electronic healthcare device (biosensor) paired with a mobile-heath application provided a practical remote monitoring communication platform to support tele-management, but the intervention did not prevent hospital readmission. Future Directions: Further research is needed to identify factors that will improve the process of applying CH to AF care management.