Predicting heart failure outcomes by integrating breath-by-breath measurements from cardiopulmonary exercise testing and clinical data through a deep learning survival neural network

Aims

Mathematical models previously developed to predict outcomes in patients with heart failure (HF) generally have limited performance and have yet to integrate complex data derived from cardiopulmonary exercise testing (CPET), including breath-by-breath data. We aimed to develop and validate a time-to-event prediction model using a deep learning framework using the DeepSurv algorithm to predict outcomes of HF.

Methods and results

Inception cohort of 2490 adult patients with high-risk cardiac conditions or HF underwent CPET with breath-by-breath measurements. Potential predictive features included known clinical indicators, standard summary statistics from CPETs, and mathematical features extracted from the breath-by-breath time series of 13 measurements. The primary outcome was a composite of death, heart transplant, or mechanical circulatory support treated as a time-to-event outcomes. Predictive features ranked as most important included many of the features engineered from the breath-by-breath data in addition to traditional clinical risk factors. The prediction model showed excellent performance in predicting the composite outcome with an area under the curve of 0.93 in the training and 0.87 in the validation data sets. Both the predicted vs. actual freedom from the composite outcome and the calibration of the prediction model were excellent. Model performance remained stable in multiple subgroups of patients.

Conclusion

Using a combined deep learning and survival algorithm, integrating breath-by-breath data from CPETs resulted in improved predictive accuracy for long-term (up to 10 years) outcomes in HF. DeepSurv opens the door for future prediction models that are both highly performing and can more fully use the large and complex quantity of data generated during the care of patients with HF.

Neural Networks for Prognostication of Patients With Heart Failure

Background Prognostication of heart failure patients from cardiopulmonary exercise test (CPET) currently involves simplification of complex time-series data into summary indices. We hypothesized that prognostication could be improved by considering the totality of the data generated during a CPET, instead of using summary indices alone. Methods and Results Complete data from 1156 CPETs were used to predict clinical deterioration (characterized by initiation of mechanical circulatory support, listing for heart transplantation or mortality) 1 year post-CPET. We compared the prognostic value (area under the receiver operating characteristic curve) of (1) the most predictive summary indices, (2) staged data collected at discrete intervals using multivariable regression models, and (3) breath-by-breath data using a feedforward neural network. The top-performing models were compared with the commonly used CPET risk score, using absolute net reclassification index. All models were trained and assessed using a 100-iteration Monte Carlo cross-validation. A total of 190 (16.4%) patients experienced clinical deterioration. The summary indices demonstrated subpar discriminative value (area under the receiver operating characteristic curve ≤0.800). Each multivariable model outperformed the summary indices, with the neural network incorporating breath-by-breath data achieving the best performance (area under the receiver operating characteristic curve =0.842). When compared with the CPET risk score (area under the receiver operating characteristic curve =0.759), the top-performing model obtained a net reclassification index of 4.9%. Conclusions The current practice of considering summary indices in isolation fails to realize the full value of CPET data. This may lead to less accurate prognostication of patients and in consequence, inaccurate selection of patients for advanced therapy. Clinical practices, like CPET prognostication, must be continuously reevaluated to ensure optimal usage of valuable (and oft-underutilized) data sources.

Genome-wide association scan identifies a colorectal cancer susceptibility locus on chromosome 8q24

Using a multistage genetic association approach comprising 7,480 affected individuals and 7,779 controls, we identified markers in chromosomal region 8q24 associated with colorectal cancer. In stage 1, we genotyped 99,632 SNPs in 1,257 affected individuals and 1,336 controls from Ontario. In stages 2-4, we performed serial replication studies using 4,024 affected individuals and 4,042 controls from Seattle, Newfoundland and Scotland. We identified one locus on chromosome 8q24 and another on 9p24 having combined odds ratios (OR) for stages 1-4 of 1.18 (trend; P = 1.41 x 10(-8)) and 1.14 (trend; P = 1.32 x 10(-5)), respectively. Additional analyses in 2,199 affected individuals and 2,401 controls from France and Europe supported the association at the 8q24 locus (OR = 1.16, trend; 95% confidence interval (c.i.): 1.07-1.26; P = 5.05 x 10(-4)). A summary across all seven studies at the 8q24 locus was highly significant (OR = 1.17, c.i.: 1.12-1.23; P = 3.16 x 10(-11)). This locus has also been implicated in prostate cancer.