Artificial Intelligence (AI) refers to a computerized system that performs physical tasks, cognitive functions, solves problems, and/ or makes decisions without overt human instructions. First proposed by McCarthy in 1955, the concept of AI has been applied in many health-related areas, including clinical research, hospital care, drug development, disease diagnosis, prognosis, and treatment monitoring. Advancement in the field of research has led to low-cost computational resources leading to digitalization of healthcare, innovation in daily routine examination, and improving overall quality of treatment. It has become an important element of medical diagnosis, for example, in the assessment skin lesions, detection of diabetic retinopathy, interpretation of chest X-rays, etc. In addition, AI has great value in aiding clinicians to improve quality and safety of healthcare delivery.
Over the years, big data has unknowingly been part of daily routine in the medical field as well, through clinical trials data, patients’ records, pharmaceutical research, claims data, fitness and diet apps, and various data storage platforms. Big data originated in 1997, when it became difficult to display large data sets that were stored in computers and limited the analysis of data. Doug Laney summarised the challenges of big data as the ‘3 Vs’: volume, variety, and velocity.
- ‘Volume’ refers to the quantity of the new data that is created from multiple sources, such as health records, insurance claims, transactions, sensors, etc.
- ‘Variety’ refers to the difference in the format of Big Data from different sources, which can be structured, unstructured, semi-structured or a mixture of the three.
- ‘Velocity’ refers to the temporal component of Big Data, in terms of creation, storage, and analysis: this can be in batches, near time, real time, streaming, retrospective, prospective, or a combination.
There has been integration of AI and big data in the field of medicine. AI concepts such as data mining, complex statistical analysis, machine learning, and neural networks are being increasingly used for faster and more precise big data analysis in medicine. This integration of AI and big data has been seen in different applications, such as mHealth (wearable devices such as smartwatches, fitness bands) and eHealth (Google fit, Apple health) applications for self-management and home care. AI also has a role in the analysis of big data originating in:
- Electronic health records (EHRs) and electronic medical records (EMRs) for epidemiological, safety, efficacy, and patient-reported outcomes insights
- Imaging data for precise diagnosis and treatment monitoring, especially in oncology, wherein the AI has been used for precise description of tumour biology and implementation of precision medicine for the assessment of tumour, its microenvironment, and radiomics.
- Personal health records (PHRs) and practice management software (PMS) to improve the service, quality and costs of healthcare delivery with less medical errors.
- Genomic sequencing like genotyping and gene expression.
- Development and usage of wellness monitoring devices has gained popularity in improving health.[5,6]
Though AI and big data work in synergy, often it is observed that health care systems are not fully equipped, as in the case of medical imaging, to share large amount of images. Analysis, labelling, accurate curation and clinical applications are the major challenges. Repeated models with homogeneous data, lack of diversity in different populations and restricted clinical setting with poor generalizability remain the major setbacks of AI currently. The currently available AI systems, though advanced, still have a far way to go to be completely and reliably accurate enough to totally replace human intervention. There are concerns surrounding quality control, accuracy, consistency, security and privacy with AI, which mandate human intervention and participation in health-related data curation. 
The analysis of big data in medicine, either through stand-alone AI protocols or with assistance of manual data curation, largely contributes to the development of real-world evidence (RWE). This offers incredible amount of data that can support regulatory drug approvals. In fact, RWE has been the basis of several approvals, such as the recent approval of Novartis’ alpelisib as the first and only treatment for PIK3CA-related overgrowth spectrum, which is considered as a rare disease. This showcases the importance of RWE generation through big data curation by means of manual curation-assisted AI protocols.
AI has a big role to play in big data curation and analysis in health care, but at the present, human intervention still cannot be completely replaced by AI. Manual curation still has an important role to play in medical big data analytics.
Become A Certified HEOR Professional – Enrol yourself here!
- Kaplan A, Haenlein M. Siri, Siri, in my hand: Who’s the fairest in the land? On the interpretations, illustrations, and implications of artificial intelligence. Bus Horiz. 2019;62(1):15–25.
- Ahmad Z, Rahim S, Zubair M, Abdul-Ghafar J. Artificial intelligence (AI) in medicine, current applications and future role with special emphasis on its potential and promise in pathology: present and future impact, obstacles including costs and acceptance among pathologists, practical and philosophical considerations. A comprehensive review. Diagn Pathol. 2021 Mar 17;16(1):24.
- Laney, D. (2001). 3D data management: controlling data volume, velocity, and variety. Meta Group. http://blogs.gartner.com/douglaney/files/2012/01/ad949-3D-Data-Management-ControllingData-Volume-Velocity-and-Variety.pdf
- Rahmani AM, Azhir E, Ali S, Mohammadi M, Ahmed OH, Yassin Ghafour M, Hasan Ahmed S, Hosseinzadeh M. Artificial intelligence approaches and mechanisms for big data analytics: a systematic study. PeerJ Comput Sci. 2021 Apr 14;7:e488.
- Yang YC, Islam SU, Noor A, Khan S, Afsar W, Nazir S. Influential Usage of Big Data and Artificial Intelligence in Healthcare. Comput Math Methods Med. 2021 Sep 6;2021:5812499
- Dash S, Shakyawar SK, Sharma M, Kaushik S. Big data in healthcare: management, analysis and future prospects. J Big Data 2019;6:54
- Willemink MJ, Koszek WA, Hardell C, Wu J, Fleischmann D, Harvey H, Folio LR, Summers RM, Rubin DL, Lungren MP. Preparing Medical Imaging Data for Machine Learning. Radiology. 2020 Apr;295(1):4-15.
- Wehner MR, Levandoski KA, Kulldorff M, Asgari MM. Research Techniques Made Simple: An Introduction to Use and Analysis of Big Data in Dermatology. J Invest Dermatol. 2017 Aug;137(8):e153-e158.