RESUMO
Pulmonary arterial hypertension (PAH), an intractable disease with a poor prognosis, is commonly treated using pulmonary vasodilators modulating the endothelin, cGMP, and prostacyclin pathway. Since the 2010s, drugs for treating pulmonary hypertension based on mechanisms other than pulmonary vasodilation have been actively developed. However, precision medicine is based on tailoring disease treatment to particular phenotypes by molecular-targeted drugs. Since interleukin-6 (IL-6) is involved in the development of PAH in animal models, and some patients with PAH have elevated IL-6 levels, the cytokine is expected to obtain potentials for therapeutic targeting. Accordingly, we identified a phenotype with elevated cytokine activity of the IL-6 family in the PAH population by combining case data extracted from the Japan Pulmonary Hypertension Registry with a comprehensive analysis of 48 cytokines using artificial intelligence clustering techniques. Including an IL-6 threshold ≥2.73 pg/mL as inclusion criteria for reducing the risk of insufficient efficacy, an investigator-initiated clinical study using satralizumab, a recycling anti-IL6 receptor monoclonal antibody, for patients with an immune-responsive phenotype is underway. This study is intended to test whether use of patient biomarker profile can identify a phenotype responsive to anti-IL6 therapy.
RESUMO
Atrial fibrillation is a clinically important arrhythmia. There are some reports on machine learning models for AF diagnosis using electrocardiogram data. However, few reports have proposed an eXplainable Artificial Intelligence (XAI) model to enable physicians to easily understand the machine learning model's diagnosis results.We developed and validated an XAI-enabled atrial fibrillation diagnosis model based on a convolutional neural network (CNN) algorithm. We used Holter electrocardiogram monitoring data and the gradient-weighted class activation mapping (Grad-CAM) method.Electrocardiogram data recorded from patients between January 4, 2016, and October 31, 2019, totaling 57,273 electrocardiogram waveform slots of 30 seconds each with diagnostic information annotated by cardiologists, were used for training our proposed model. Performance metrics of our AI model for AF diagnosis are as follows: sensitivity, 97.1% (95% CI: 0.969-0.972); specificity, 94.5% (95% CI: 0.943-0.946); accuracy, 95.3% (95% CI: 0.952-0.955); positive predictive value, 89.3% (95% CI: 0.892-0.897); and F-value, 93.1% (95% CI: 0.929-0.933). The area under the receiver operating characteristic curve for AF detection using our model was 0.988 (95% CI: 0.987-0.988). Furthermore, using the XAI method, 94.5 ± 3.5% of the areas identified as regions of interest using our machine learning model were identified as characteristic sites for AF diagnosis by cardiologists.AF was accurately diagnosed and favorably explained with Holter ECG waveforms using our proposed CNN-based XAI model. Our study presents another step toward realizing a viable XAI-based detection model for AF diagnoses for use by physicians.
