In physiological conditions, heart period (HP) affects systolic arterial pressure (SAP) through diastolic runoff and Starling's law, but, the reverse relation also holds as a result of the continuous action of baroreflex control. The prevailing mechanism sets the dominant temporal direction in the HP-SAP interactions (i.e., causality). We exploited cross-conditional entropy to assess HP-SAP causality. A traditional approach based on phases was applied for comparison. The ability of the approach to detect the lack of causal link from SAP to HP was assessed on 8 short-term (STHT) and 11 long-term heart transplant (LTHT) recipients (i.e., less than and more than 2 yr after transplantation, respectively). In addition, spontaneous HP and SAP variabilities were extracted from 17 healthy humans (ages 21-36 yr, median age 29 yr; 9 females) at rest and during graded head-up tilt. The tilt table inclinations ranged from 15 to 75° and were changed in steps of 15°. All subjects underwent recordings at every step in random order. The approach detected the lack of causal relation from SAP to HP in STHT recipients and the gradual restoration of the causal link from SAP to HP with time after transplantation in the LTHT recipients. The head-up tilt protocol induced the progressive shift from the prevalent causal direction from HP to SAP to the reverse causality (i.e., from SAP to HP) with tilt table inclination in healthy subjects. Transformation of phases into time shifts and comparison with baroreflex latency supported this conclusion. The proposed approach is highly efficient because it does not require the knowledge of baroreflex latency. The dependence of causality on tilt table inclination suggests that "spontaneous" baroreflex sensitivity estimated using noncausal methods (e.g., spectral and cross-spectral approaches) is more reliable at the highest tilt table inclinations.

Artificial intelligence (AI) and machine learning (ML) techniques are revolutionizing several industrial and research fields like computer vision, autonomous driving, natural language processing, and speech recognition. These novel tools are already having a major impact in radiology, diagnostics, and many other fields in which the availability of automated solution may benefit the accuracy and repeatability of the execution of critical tasks. In this narrative review, we first present a brief description of the various techniques that are being developed nowadays, with special focus on those used in spine research. Then, we describe the applications of AI and ML to problems related to the spine which have been published so far, including the localization of vertebrae and discs in radiological images, image segmentation, computer‐aided diagnosis, prediction of clinical outcomes and complications, decision support systems, content‐based image retrieval, biomechanics, and motion analysis. Finally, we briefly discuss major ethical issues related to the use of AI in healthcare, namely, accountability, risk of biased decisions as well as data privacy and security, which are nowadays being debated in the scientific community and by regulatory agencies.