Search

Most cancer patients exhibit autonomic dysfunction with attenuated heart rate variability (HRV) levels compared to healthy controls. This research aimed to create and evaluate a machine learning (ML) model enabling discrimination between cancer patients and healthy controls based on 5-min-ECG recordings. We selected 12 HRV features based on previous research and compared the results between cancer patients and healthy individuals using Wilcoxon sum-rank test. Recursive Feature Elimination (RFE) identified the top five features, averaged over 5 min and employed them as input to three different ML. Next, we created an ensemble model based on a stacking method that aggregated the predictions from all three base classifiers. All HRV features were significantly different between the two groups. SDNN, RMSSD, pNN50%, HRV triangular index, and SD1 were selected by RFE and used as an input to three different ML. All three base-classifiers performed above chance level, RF being the most efficient with a testing accuracy of 83%. The ensemble model showed a classification accuracy of 86% and an AUC of 0.95. The results obtained by ML algorithms suggest HRV parameters could be a reliable input for differentiating between cancer patients and healthy controls. Results should be interpreted in light of some limitations that call for replication studies with larger sample sizes.

Introduction Doctors and patients influence each other when interacting and, as a result, can become similar to each other in affect and behavior. In the current work, we examine whether they also become similar to each other on a moment-to-moment basis in their physiological responses. Specifically, we examine physiological linkage—how much a doctor's (or patient's) physiological response predicts a patient's (or doctor's) response at a subsequent time interval—and whether this changes over the course of doctor-patient relationships (measured as the number of consultations held for each unique doctor-patient dyad). Methods We collected interbeat interval responses (IBI) continuously during consultations between oncologists and patients undergoing cancer treatment (N = 102 unique doctor-patient interactions) at a hospital in Austria. Results Physiological linkage varied by an interaction between role (doctor vs. patient) and relationship length (in a non-linear, quadratic pattern). Patients showed significant positive linkage to their doctors (i.e., doctors' physiological responses positively, significantly predicted patients' responses) in relationships that spanned three to eight consultations together. Patients were not linked to their doctors in shorter or longer relationships. Doctors were never significantly linked to their patients, meaning that patients' physiological responses never predicted doctors’ responses. Conclusion These results reveal that, by influencing patients' physiological responses on a moment-to-moment basis, doctors may have even more influence over patients’ physiology than previously known.