Search

Machine learning (ML), a form of artificial intelligence (AI), is being increasingly employed in neurology. Reported performance metrics often match or exceed the efficiency of average clinicians. The neurologist is easily baffled by the underlying concepts and terminologies associated with ML studies. The superlative performance metrics of ML algorithms often hide the opaque nature of its inner workings. Questions regarding ML model's interpretability and reproducibility of its results in real-world scenarios, need emphasis. Given an abundance of time and information, the expert clinician should be able to deliver comparable predictions to ML models, a useful benchmark while evaluating its performance. Predictive performance metrics of ML models should not be confused with causal inference between its input and output. ML and clinical gestalt should compete in a randomized controlled trial before they can complement each other for screening, triaging, providing second opinions and modifying treatment. [ABSTRACT FROM AUTHOR]

We report three cases of myasthenia gravis in whom the asymmetrical ptosis at presentation became more pronounced with the described bedside technique. Pronounced ptosis could be elicited by making the patient speak continuously for up to 2 minutes. Pauses for breathing and natural blinking were allowed. The sign is best elicited in newly diagnosed and treatment-naive patients. The loss of compensation for ptosis by frontalis muscle due to speech-induced fatigue may be responsible for the observed effect. Patients' symptoms abated on treatment with acetylcholine esterase inhibitors, steroids, and steroid-sparing agents. [ABSTRACT FROM AUTHOR]

Sir, Dr. Prasad has elegantly described the importance of the difference between "clinical importance/significance" and "statistical significance/detection."[1] We want to emphasize that apart from others, statistical significance depends profoundly on the sample size of the study. So, when the sample size is enormous, any clinically trivial difference (like a 1-day difference in headache-free days in migraine or five days difference in survival between two anticancer drugs) can turn out to be "statistically significant/detectable." Statistically significant but not clinically significant If one increases the sample size considerably, any trivial difference can become statistically "significant/detectable.". [Extracted from the article]