ABSTRACT
Background & objectives: Artificial intelligence (AI) and machine learning (ML) have shown promising results in cancer diagnosis in validation tests involving retrospective patient databases. This study was aimed to explore the extent of actual use of AI/ML protocols for diagnosing cancer in prospective settings. Methods: PubMed was searched for studies reporting usage of AI/ML protocols for cancer diagnosis in prospective (clinical trial/real world) setting with the AI/ML diagnosis aiding clinical decision-making, from inception till May 17, 2021. Data pertaining to the cancer, patients and the AI/ML protocol were extracted. Comparison of AI/ML protocol diagnosis with human diagnosis was recorded. Through a post hoc analysis, data from studies describing validation of various AI/ML protocols were extracted. Results: Only 18/960 initial hits (1.88%) utilized AI/ML protocols for diagnostic decision-making. Most protocols used artificial neural network and deep learning. AI/ML protocols were utilized for cancer screening, pre-operative diagnosis and staging and intra-operative diagnosis of surgical specimens. The reference standard for 17/18 studies was histology. AI/ML protocols were used to diagnose cancers of the colorectum, skin, uterine cervix, oral cavity, ovaries, prostate, lungs and brain. AI/ML protocols were found to improve human diagnosis, and had either similar or better performance than the human diagnosis, especially made by the less experienced clinician. Validation of AI/ML protocols was described by 223 studies of which only four studies were from India. Also there was a huge variation in the number of items used for validation. Interpretation & conclusions: The findings of this review suggest that a meaningful translation from the validation of AI/ML protocols to their actual usage in cancer diagnosis is lacking. Development of regulatory framework specific for AI/ML usage in healthcare is essential.
ABSTRACT
Background & objectives: Regular practice of slow breathing has been shown to improve cardiovascular and respiratory functions and to decrease the effects of stress. This pilot study was planned to evaluate the short term effects of pranayama on cardiovascular functions, pulmonary functions and galvanic skin resistance (GSR) which mirrors sympathetic tone, and to evaluate the changes that appear within a short span of one week following slow breathing techniques. Methods: Eleven normal healthy volunteers were randomized into Pranayama group (n=6) and a non-Pranayama control group (n=5); the pranayama volunteers were trained in pranayama, the technique being Anuloma-Viloma pranayama with Kumbhak. All the 11 volunteers were made to sit in similar environment for two sessions of 20 min each for seven days, while the pranayama volunteers performed slow breathing under supervision, the control group relaxed without conscious control on breathing. Pulse, GSR, blood pressure (BP) and pulmonary function tests (PFT) were measured before and after the 7-day programme in all the volunteers. Results: While no significant changes were observed in BP and PFT, an overall reduction in pulse rate was observed in all the eleven volunteers; this reduction might have resulted from the relaxation and the environment. Statistically significant changes were observed in the Pranayama group volunteers in the GSR values during standing phases indicating that regular practice of Pranayama causes a reduction in the sympathetic tone within a period as short as 7 days. Interpretation & conclusions: Beneficial effects of pranayama started appearing within a week of regular practice, and the first change appeared to be a reduction in sympathetic tone.