Physician Judgement vs Model-Predicted Prognosis in Patients With Heart Failure

Minimum Core Data Elements for Evaluation of TAVR: A Scientific Statement by PASSION CV, HVC, and TVT Registry

Transcatheter aortic valve replacement (TAVR) is the standard of care for severe, symptomatic aortic stenosis. Real-world TAVR data collection contributes to benefit/risk assessment and safety evidence for the U.S. Food and Drug Administration, quality evaluation for the Centers for Medicare and Medicaid Services and hospitals, as well as clinical research and real-world implementation through appropriate use criteria. The essential minimum core dataset for these purposes has not previously been defined but is necessary to promote efficient, reusable real-world data collection supporting quality, regulatory, and clinical applications. The authors performed a systematic review of the published research for high-impact TAVR studies and U.S. multicenter, multidevice registries. Two expert task forces, one from the Predictable and Sustainable Implementation of National Cardiovascular Registries/Heart Valve Collaboratory and another from The Society of Thoracic Surgeons/American College of Cardiology TVT (Transcatheter Valve Therapy) Registry convened separately and then met to reconcile a final list of essential data elements. From 276 unique data elements considered, unanimous consensus agreement was achieved on 132 "core" data elements, with the most common reasons for exclusion from the minimum core dataset being burden or difficulty in accurate assessment (36.9%), duplicative information (33.3%), and low likelihood of affecting outcomes (10.7%). After a systematic review and extensive discussions, a multilateral group of academicians, industry representatives, and regulators established 132 interoperable, reusable essential core data elements essential to supporting more efficient, consistent, and informative TAVR device evidence for regulatory submissions, safety surveillance, best practice, and hospital quality assessments.

Minimum Core Data Elements for Evaluation of TAVR: A Scientific Statement by PASSION CV, HVC, and TVT Registry

Transcatheter aortic valve replacement (TAVR) is the standard of care for severe, symptomatic aortic stenosis. Real-world TAVR data collection contributes to benefit/risk assessment and safety evidence for the U.S. Food and Drug Administration, quality evaluation for the Centers for Medicare and Medicaid Services and hospitals, as well as clinical research and real-world implementation through appropriate use criteria. The essential minimum core dataset for these purposes has not previously been defined but is necessary to promote efficient, reusable real-world data collection supporting quality, regulatory, and clinical applications. The authors performed a systematic review of the published research for high-impact TAVR studies and U.S. multicenter, multidevice registries. Two expert task forces, one from the Predictable and Sustainable Implementation of National Cardiovascular Registries/Heart Valve Collaboratory and another from The Society of Thoracic Surgeons/American College of Cardiology TVT (Transcatheter Valve Therapy) Registry convened separately and then met to reconcile a final list of essential data elements. From 276 unique data elements considered, unanimous consensus agreement was achieved on 132 "core" data elements, with the most common reasons for exclusion from the minimum core dataset being burden or difficulty in accurate assessment (36.9%), duplicative information (33.3%), and low likelihood of affecting outcomes (10.7%). After a systematic review and extensive discussions, a multilateral group of academicians, industry representatives, and regulators established 132 interoperable, reusable essential core data elements essential to supporting more efficient, consistent, and informative TAVR device evidence for regulatory submissions, safety surveillance, best practice, and hospital quality assessments.

Multi-channel Fusion LSTM for Medical Event Prediction using HERs

Automatic medical event prediction (MEP), e.g. diagnosis prediction, medication prediction, using electronic health records (EHRs) is a popular research direction in health informatics. In many cases, MEP relies on the determinations from different types of medical events, which demonstrates the heterogeneous nature of EHRs. However, most existing methods for MEP fail to distinguishingly model the type of event that is highly associated with the prediction task, i.e. task-wise event, which usually plays a more significant role than other events. In this paper, we proposed a Long Short-Term Memory network (LSTM)-based method for MEP, named Multi-Channel Fusion LSTM (MCF-LSTM), which models the correlations between different types of medical events using multiple network channels. To this end, we designed a task-wise fusion module, in which a gated network is applied to select how much information can be transferred between events. Furthermore, the irregular temporal interval between adjacent medical visits is also modeled in an individual channel, which is combined with other events in a unified manner. We compared MCF-LSTM with state-of-the-art methods on four MEP tasks on two public datasets: MIMIC-III and eICU. Experimental results show that MCF-LSTM achieves promising results on AUC(receiver operating characteristic curve), AUPR (area under the precision-recall curve), and top-k recall, and outperforms other methods with high stability.

Automated model versus treating physician for predicting survival time of patients with metastatic cancer

OBJECTIVE

Being able to predict a patient's life expectancy can help doctors and patients prioritize treatments and supportive care. For predicting life expectancy, physicians have been shown to outperform traditional models that use only a few predictor variables. It is possible that a machine learning model that uses many predictor variables and diverse data sources from the electronic medical record can improve on physicians' performance. For patients with metastatic cancer, we compared accuracy of life expectancy predictions by the treating physician, a machine learning model, and a traditional model.

MATERIALS AND METHODS

A machine learning model was trained using 14 600 metastatic cancer patients' data to predict each patient's distribution of survival time. Data sources included note text, laboratory values, and vital signs. From 2015-2016, 899 patients receiving radiotherapy for metastatic cancer were enrolled in a study in which their radiation oncologist estimated life expectancy. Survival predictions were also made by the machine learning model and a traditional model using only performance status. Performance was assessed with area under the curve for 1-year survival and calibration plots.

RESULTS

The radiotherapy study included 1190 treatment courses in 899 patients. A total of 879 treatment courses in 685 patients were included in this analysis. Median overall survival was 11.7 months. Physicians, machine learning model, and traditional model had area under the curve for 1-year survival of 0.72 (95% CI 0.63-0.81), 0.77 (0.73-0.81), and 0.68 (0.65-0.71), respectively.

CONCLUSIONS

The machine learning model's predictions were more accurate than those of the treating physician or a traditional model.

Predictors of Mortality in Patients Treated with Veno-Arterial ECMO for Cardiogenic Shock Complicating Acute Myocardial Infarction: a Systematic Review and Meta-Analysis

BACKGROUND

Mortality for patients on veno-arterial extracorporeal membrane oxygenation (VA-ECMO) for cardiogenic shock (CS) complicating acute myocardial infarction (AMI) remains high. This meta-analysis aims to identify factors that predict higher risk of mortality after VA-ECMO for AMI.

METHODS

We meta-analyzed mortality after VA-ECMO for CS complicating AMI and the effect of factors from systematically selected studies published after 2009.

RESULTS

72 studies (10,276 patients) were included with a pooled mortality estimate of 58 %. With high confidence in estimates, failure to achieve TIMI III flow and left main culprit were identified as factors associated with higher mortality. With low-moderate confidence, older age, high BMI, renal dysfunction, increasing lactate, prothrombin activity < 50%, VA-ECMO implantation after revascularization, and non-shockable ventricular arrythmias were identified as factors associated with mortality.

CONCLUSION

These results provide clinicians with a framework for selecting patients for VA-ECMO for CS complicating AMI.

Predicting High-Risk Patients and High-Risk Outcomes in Heart Failure

Identifying patients with heart failure at high risk for poor outcomes is important for patient care, resource allocation, and process improvement. Although numerous risk models exist to predict mortality, hospitalization, and patient-reported health status, they are infrequently used for several reasons, including modest performance, lack of evidence to support routine clinical use, and barriers to implementation. Artificial intelligence has the potential to enhance the performance of risk prediction models, but has its own limitations and remains unproved.