Key points
- AI algorithms are used to analyse medical images, such as X-rays, MRIs, and CT scans
- It also aids radiologists in lesion detection and diagnosis
- Diabetes patients can benefit from AI-powered glucose monitoring systems
- AI could save the healthcare industry between $200 billion and $300 billion annually by streamlining processes and eliminating inefficiencies
ISLAMABAD: Like other realms, Artificial Intelligence (AI) is also making significant strides in healthcare, particularly in diagnostics and personalised treatment planning.
Its ability to process large datasets and analyse complex medical information is reshaping how doctors diagnose diseases and prescribe treatments. However, broadly speaking, these developments offer both hope and challenges to healthcare systems.
AI in Medical Diagnostics
One of the most promising innovations is the use of AI algorithms to analyse medical images, such as X-rays, Magnetic Resonance Imaging (MRIs), and Computed Tomography (CT) scans. These algorithms can find abnormalities with accuracy, often exceeding human performance.
AI’s pattern recognition and decision-making abilities offer promise in detection, diagnosis, personalised treatment, risk assessment, and prevention. Screening and early detection are improved by AI-enhanced mammography, according to the study titled ‘Artificial Intelligence for Breast Cancer: Implications for Diagnosis and Management’ in ScienceDirect which is the world’s leading source for scientific, technical, and medical research.
The research further adds that AI aids radiologists in lesion detection and diagnosis, though concerns about false positives persist. In addition, AI revolutionises breast imaging, assisting in reading mammograms, biomarker assessment, lymph node detection, and outcome prediction. Genetic insights into risk and treatment response are advanced by AI, particularly through deep learning algorithms.
Personalised treatment plans
AI-driven predictive models are transforming how treatments are designed for individual patients. These models use patient data—including medical history, genetics, and lifestyle factors—to recommend the most effective therapies.
“AI can play an important role in the development of personalised medicines at all relevant phases of the clinical development and implementation of new personalised health products, from finding appropriate intervention targets to testing them for their utility,” writes Nicholas J Schork in a research article, Artificial Intelligence and Personalised Medicine, published in National Library of Medicine.
AI is also improving chronic disease management. Diabetes patients, for example, benefit from AI-powered glucose monitoring systems that provide real-time recommendations for insulin dosage adjustments.
“The proportional Integral Derivative (PID) controller’s role in adjusting insulin dosage based on the discrepancy between desired setpoints and actual measurements showcases a proactive strategy for maintaining blood glucose levels within a healthy range,” states Sravani Medanki of Ramakrishna Siddhartha Engineering College, Vijayawada Andhra Pradesh, India.
Proportional Integral Derivative (PID) control is the widely used feedback control algorithm for automatic process control. It consists of proportional, integral, and derivative algorithms, which are based on present, past, and future errors, respectively.
Similarly, wearable devices integrated with AI monitor heart patients, detecting irregularities and alerting doctors before emergencies arise.
“Recent breakthroughs in wearable technology have revolutionised the landscape of heart failure management,” writes Victor Adeyi Odeh of the Department of Biomedical Engineering, School of Life Science and Technology, University of Electronic Science and Technology of China.
Impact on healthcare costs
AI helps healthcare costs by improving early diagnosis and treatment precision. Early disease detection often leads to less invasive and expensive treatments.
“Numerous medical data sources are required to perfectly diagnose diseases using artificial intelligence techniques, such as ultrasound, magnetic resonance imaging, mammography, genomics, computed tomography scan, etc. Furthermore, AI primarily enhanced the infirmary experience and sped up preparing patients to continue their rehabilitation at home,” reports Yogesh Kumar in his research article, Artificial Intelligence in Disease Diagnosis: A Systematic Literature Review, Synthesizing Framework, and Future Research Agenda, published in National Library of Medicine.
Moreover, hospitals are using AI to optimise resource allocation. Predictive algorithms analyse patient admission data to manage staffing and resource needs efficiently, minimising hospital overcrowding.
Automating staff scheduling
“AI-driven solutions offer the potential to optimise bed utilisation, automate staff scheduling, and improve patient flow, ultimately leading to better resource allocation, reduced operational costs, and improved patient care,” writes Emmanuel Chris in his study published in Research Gate under the name “Smarter Hospital Management with AI: Using Machine Learning to Manage Hospital Resources More Efficiently.”
In the United States, AI-driven initiatives have saved hospitals millions of dollars annually. “A 2023 Ernst & Young study estimated that AI could save the healthcare industry between $200 billion and $300 billion annually by streamlining processes and eliminating inefficiencies,” writes Inna Fishchuk in her blog “Adopting AI in Healthcare: Benefits, Challenges and Real-Life Examples.”
This corresponds to as much as 5-10 per cent of total healthcare spending, according to Inna Fishchuk.
Moreover, McKinsey states that 60 per of organisations that have implemented generative AI solutions are already seeing positive returns on investment or expect to do so soon.
McKinsey & Company is an American multinational strategy and management consulting firm that offers professional services to corporations, governments, and other organizations.
Challenges
Despite these advancements, significant challenges remain. Data privacy and security are critical concerns, particularly when sensitive health information is used to train AI models.
Ethical guidelines are needed to ensure that AI recommendations are transparent and bias-free. Moreovers, there is an ongoing debate about the role of AI in decision-making—should AI merely assist doctors or eventually replace certain diagnostic roles?
“The introduction of these cutting-edge solutions poses substantial challenges in clinical and care environments, necessitating a thorough exploration of ethical, legal, and regulatory considerations,” cautions Ciro Mennella of Institute for High-Performance Computing and Networking (ICAR) – Research National Council of Italy (CNR).
Global adoption of AI in healthcare
Countries worldwide are embracing AI to address healthcare challenges. In India, AI platforms are improving access to diagnostics in rural areas with limited medical professionals, according to IndiaAI which is a knowledge portal, research organisation, and an ecosystem-building initiative.
Meanwhile, AI is widely used for image recognition and analysis, especially in cardiac, cancer, stroke, and fracture detection.
Chinese local leaders, in healthcare, include DeepWise and Shukun Technology. China’s National Medical Products Administration (NMPA) has approved 92 AI tools under Class III to accelerate healthcare decision-making and improve diagnostic accuracy, according to Daxue Consulting which has extensive experience in the Chinese market.
Developed countries, including the United States and the United Kingdom, continue to lead in AI research and development, but collaborations with emerging economies are expanding AI’s reach. The World Health Organization (WHO), in its first global report on Artificial Intelligence (AI) in health, encourages global partnerships to ensure equitable access to AI technologies, particularly in underserved regions.