Healthcare is experiencing a transformative phase, with artificial intelligence (AI) and machine learning (ML). Physical therapists (PTs) stand on the brink of a paradigm shift in education, practice, and research. Rather than visualizing AI as a threat, it presents an opportunity to revolutionize. This paper examines how large language models (LLMs), such as ChatGPT and BioMedLM, driven by deep ML can offer human-like performance but face challenges in accuracy due to vast data in PT and rehabilitation practice. PTs can benefit by developing and training an LLM specifically for streamlining administrative tasks, connecting globally, and customizing treatments using LLMs. However, human touch and creativity remain invaluable. This paper urges PTs to engage in learning and shaping AI models by highlighting the need for ethical use and human supervision to address potential biases. Embracing AI as a contributor, and not just a user, is crucial by integrating AI, fostering collaboration for a future in which AI enriches the PT field provided data accuracy, and the challenges associated with feeding the AI model are sensitively addressed.
We have read with great interest the recently published article titled “Economic Burden of Stroke Disease: A Systematic Review” by Rochmah and colleagues
30 November 2021 in Journal of Medical Ultrasonics
Introduction: Stroke is one of the leading causes of morbidity and mortality worldwide accompanied by huge financial burden on an individual and society. Objective: The objective is to estimate the economic burden by calculating the costs (per capita Gross Domestic Product (GDP)) on stroke survivors in African and Asian countries. Materials and Methods: Published electronic articles from inception till August 2022 will be screened from five databases: MEDLINE (PubMed), Scopus, Embase, Science Direct, and Web of Science. Effect sizes in the form of risk ratios and risk differences will be calculated for estimating the burden per capita income of the country. In accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analysis 2020 Guidelines, titles and abstracts will be screened by two authors independently. Any disagreements will be resolved by the third author. Rayyan QCRI software will be used for the inclusion of articles and removing of duplicates. Quality assessment will be conducted by the National Institute of Health (NIH) tool for observational and cross-sectional studies whereas risk of bias will be assessed using the Cochrane’s ROBINS-I tool for observational studies. RevMan 5.4 software will be used for plotting forest plots and further analysis. In case, heterogeneity is observed in the outcomes data, I2 statistics will be calculated to further the possibility of a meta-analysis. Publication bias will be assessed by plotting a funnel plot and “trim-and-fill method”. This systematic review will estimate the economic burden by collating data using socioeconomic indicators of stroke in African and Asian countries. The results will help policymakers in designing and allocation of resources in the two continents.