Artificial intelligence, particularly machine learning, has gained prominence in medical research due to its potential to develop non-invasive diagnostics. Pulmonary hypertension presents a diagnostic challenge due to its heterogeneous nature and similarity in symptoms to other cardiovascular conditions. Here, we describe the development of a supervised machine learning model using non-invasive signals (orthogonal voltage gradient and photoplethysmographic) and a hand-crafted library of 3298 features. The developed model achieved a sensitivity of 87% and a specificity of 83%, with an overall Area Under the Receiver Operator Characteristic Curve (AUC-ROC) of 0.93. Subgroup analysis showed consistent performance across genders, age groups and classes of PH. Feature importance analysis revealed changes in metrics that measure conduction, repolarization and respiration as significant contributors to the model. The model demonstrates promising performance in identifying pulmonary hypertension, offering potential for early detection and intervention when embedded in a point-of-care diagnostic system.

The current standard of care for coronary artery disease (CAD) requires an intake of radioactive or contrast enhancement dyes, radiation exposure, and stress and may take days to weeks for referral to gold-standard cardiac catheterization. The CAD diagnostic pathway would greatly benefit from a test to assess for CAD that enables the physician to rule it out at the point of care, thereby enabling the exploration of other diagnoses more rapidly. We sought to develop a test using machine learning to assess for CAD with a rule-out profile, using an easy-to-acquire signal (without stress/radiation) at the point of care. Given the historic disparate outcomes between sexes and urban/rural geographies in cardiology, we targeted equal performance across sexes in a geographically accessible test. Noninvasive photoplethysmogram and orthogonal voltage gradient signals were simultaneously acquired in a representative clinical population of subjects before invasive catheterization for those with CAD (gold-standard for the confirmation of CAD) and coronary computed tomographic angiography for those without CAD (excellent negative predictive value). Features were measured from the signal and used in machine learning to predict CAD status. The machine-learned algorithm achieved a sensitivity of 90% and specificity of 59%. The rule-out profile was maintained across both sexes, as well as all other relevant subgroups. A test to assess for CAD using machine learning on a noninvasive signal has been successfully developed, showing high performance and rule-out ability. Confirmation of the performance on a large clinical, blinded, enrollment-gated dataset is required before implementation of the test in clinical practice.

Many clinical studies have shown wide performance variation in tests to identify coronary artery disease (CAD). Coronary computed tomography angiography (CCTA) has been identified as an effective rule-out test but is not widely available in the USA, particularly so in rural areas. Patients in rural areas are underserved in the healthcare system as compared to urban areas, rendering it a priority population to target with highly accessible diagnostics. We previously developed a machine-learned algorithm to identify the presence of CAD (defined by functional significance) in patients with symptoms without the use of radiation or stress. The algorithm requires 215 s temporally synchronized photoplethysmographic and orthogonal voltage gradient signals acquired at rest. The purpose of the present work is to validate the performance of the algorithm in a frozen state (i.e., no retraining) in a large, blinded dataset from the IDENTIFY trial. IDENTIFY is a multicenter, selectively blinded, non-randomized, prospective, repository study to acquire signals with paired metadata from subjects with symptoms indicative of CAD within seven days prior to either left heart catheterization or CCTA. The algorithm’s sensitivity and specificity were validated using a set of unseen patient signals (n = 1816). Pre-specified endpoints were chosen to demonstrate a rule-out performance comparable to CCTA. The ROC-AUC in the validation set was 0.80 (95% CI: 0.78–0.82). This performance was maintained in both male and female subgroups. At the pre-specified cut point, the sensitivity was 0.85 (95% CI: 0.82–0.88), and the specificity was 0.58 (95% CI: 0.54–0.62), passing the pre-specified endpoints. Assuming a 4% disease prevalence, the NPV was 0.99. Algorithm performance is comparable to tertiary center testing using CCTA. Selection of a suitable cut-point results in the same sensitivity and specificity performance in females as in males. Therefore, a medical device embedding this algorithm may address an unmet need for a non-invasive, front-line point-of-care test for CAD (without any radiation or stress), thus offering significant benefits to the patient, physician, and healthcare system.

Background: Cardiac computed tomography angiography (CCTA), the premier coronary artery disease (CAD) rule-out test, is less available in rural areas (vs urban) in the US. To address this gap, we previously developed a test using non-invasive signals and a machine-learned algorithm, usable anywhere with internet. We trained the algorithm using US populations: (1) subjects enrolled before CCTA for specificity and (2) subjects undergoing invasive coronary angiography (ICA), for both sensitivity and specificity. US validation used separate, identically constructed, blinded populations (N = 1816). In US validation, sensitivity was 88% (95% CI 85–91%) and specificity was 51% (48–55%). Although China is urbanizing rapidly, 510 million (36% of the population) still reside in rural areas. Thus, China might benefit from the test, but given the demographic differences, the efficacy of the test in the Chinese population is unknown. The aim of the present study was to assess test performance within a cohort of Chinese ICA subjects. Methods: Subjects were enrolled at Zhongshan Hospital, Fudan University (China), using the same inclusion and exclusion criteria as in the US study. The same device as in the US captured signals pre-ICA. We applied the unchanged algorithm from US validation to the signals, then matched with the ICA results. Results: 558 subjects had both ICA results and a signal, 458 passed signal quality and outlier checks, and 348 had significant CAD. Compared to the US sensitivity cohort, the Chinese cohort was significantly younger, had a lower BMI, a higher proportion of males, and lower rates of tobacco use, hypertension, and diabetes. Race was Asian only in China, while the US was primarily White/Caucasian. Chinese cohort sensitivity was 89% (86–93%), p = 0.46 vs the US. Discussion: Our study was limited by the lack of a Chinese CCTA specificity cohort. However, sensitivity was high, and thus robust to the significant demographic shifts. Therefore, we anticipate similar behavior in specificity; to explore that, we combined the Chinese ICA negatives (N = 110) with the US CCTA negatives from the previous work, in the same proportion as used in US validation, which models the population of patients under assessment for cardiac symptoms. The resultant specificity was 51% (48–55%). With the Chinese ICA positives, the area under the receiver operator characteristic curve was 0.79 (0.77–0.81). These results suggest the test’s potential effectiveness in the Chinese population. Trial registration: NCT04034537.