Artificial Intelligence in Neurology, Ethics, Recent Guideline and Law- An Indian PerspectiveIntroductionArtificial intelligence (AI), a boon, kept healthcare professionals safe during the COVID-19 era in the form of “Tommy,” the robot nurse in Italy or “Mitra” in India. But continuous involvement of AI in healthcare also brings various challenges, i.e., quality and ownership of the data, belief issues, and ethical challenges. Therefore, in this article, we want to discuss the global policies regarding AI from different countries including India. We also present the summary of the new ethical guideline for AI applications in healthcare by the Indian Council of Medical Research (ICMR) and the Digital Personal Data Protection Act 2023 (DPDP Act),the first law for personal data protection in India, released recently in India. Current AI applications in Neurology in IndiaAI can be utilized in different parts of neurology from diagnosis of seizures, developmental anomalies, i.e., Down syndrome, cerebral palsy, etc., and neurodegenerative diseases (e.g., Alzheimer’s disease) to the rehabilitation of stroke patients1. Recently in India, Aster CMI hospital has developed a screening tool to diagnose carpal tunnel syndrome2. Scientists from Kyoto University, Japan, and IIT Roorkee, India, have created an AI-based model to predict the glioma grading from brain MRI which will help to treat the tumors3. A USA-based company named Intel and the University of California have partnered with 29 international institutes including Tata Memorial Hospital, Mumbai to create an AI model for early detection of brain tumor4. Medtronic India has partnered with Qure.ai to develop an AI-based tool for early detection and management of stroke patients5.Ethical Laws and Guidelines Around the WorldUSAAround 120 bills are being contemplated by US Congress regarding AI but significantly less number of bills are related to ethics in healthcare. The Health Insurance Portability and Accountability Act of 1996 (HIPAA) exists in USA for personal data security of the citizens. However HIPPA can not shield the citizen from the “Black box” problem of AI. American Medical Association’s “Augmented Intelligence in Medicine” (2018) and “Payment and Coverage of AI” (2019), “Blueprint for an AI Bill of Rights” (2022) by the White House, and “Artificial Intelligence Risk Management Framework 1.0 (AI RMF)” (2023) by National Institute of Standards and Technology (NIST), exist regarding AI6. But these policies can not protect the citizens completely. Food and Drug Administration (FDA) has several guiding principles regarding AI-enabled medical devices (e.g. DermaSensor and Paige Prostate to detect skin cancer and carcinoma prostate respectively), i.e., “Good Machine Learning Practice for Medical Device Development: Guiding Principles” (2021), “Transparency for Machine Learning-Enabled Medical Devices: Guiding Principles”(2021), “Transparency for Machine Learning-Enabled Medical Devices: Guiding Principles” (2024)7. But till date no such guideline exists for non-device AI i.e., AI associated with the clinical decision support system.GermanySimilar to HIPPA in the USA, the General Data Protection Regulation (GDPR) is present in the European Union (EU) for the personal data security of citizens. Similarly, as a member of the EU, Bundesdatenschutzgesetz (BDSG) is present in Germany. General Product Safety Regulation (GPSR) 2023/988 involves safety rules for products. The New Product Liability Directive includes compensation for AI software which will be implemented in December 2026. Though the terminology “AI” is included as a reference in the German Works Constitution Act 2021, Germany does not have a separate AI regulation and will probably follow the EU AI Act. Among all the regulations, the EU AI Act (2024) is the most significant legislation as it is the first legal framework for AI. This act divides AI into several risk categories, ie., unacceptable (e.g. Biometric identification), high (e.g. Facial recognition), limited (e.g. ChatGPT and other chatbots), and low or minimal (e.g. Video games) risk8. Depending on their risk category, different compliance requirements exist. Whereas in the unaccepable risk category, the AI will be prohibited from further use, in case of the limited risk category, only a transparency requirement is present. Most of the rules in the EU AI Act will be applicable from August 2026.CanadaCanada has several data protection laws. Privacy Act and the Personal Information Protection and Electronic Documents Act (PIPEDA) exist at the federal level and various regulations, i.e., the Personal Information Protection Act, SA 2003 and the Personal Information Protection Act in Alberta and British Columbia, respectively are present at the provincial level9. A federal law, Artificial Intelligence and Data Act (AIDA) was initiated in 2022 but hopefully will come into effect soon.AIDA divides the key players into three categories, i.e., developers, deployers, and operators. It is mainly applicable to high-impact AI only and does not have a sector-specific approach. One of the main objectives of AIDA is to promote the safe use of AI. Health Canada, USFDA, and Medicines and Healthcare Products Regulatory Agency (MHRA)-UK, have jointly issued a guiding principle for AI in late 2021 followed by a draft premarket guideline of machine-learning enabled medical devices (MLMD) introduced by Health Canada in 2023.ChinaChina has several laws for data protection, i.e., Personal Information Protection Law (PIPL), Data Security Law, etc. There are several policies addressing the development of AI in China, i.e., “Made in China 2025” (2015), Central Committee of the Communist Party of China (CCP)’s 13th five-year plan (2016) etc10. Different policies regarding the ethical...