|
 
 |
| LETTER TO EDITOR |
|
| Year : 2019 | Volume
: 5
| Issue : 1 | Page : 46-47 |
|
Artificial intelligence in health care: A game changer
Manigreeva Krishnatreya
Department of Cancer Registry and Epidemiology, Dr. B Borooah Cancer Institute, Guwahati, Assam, India
| Date of Web Publication | 29-May-2019 |
Correspondence Address:
Manigreeva Krishnatreya
Room No. 2, OPD Block, Dr. B Borooah Cancer Institute, Gopinath Nagar, A.K. Azad Road, Guwahati - 781 016, Assam
India
 Source of Support: None, Conflict of Interest: None  | Check |
DOI: 10.4103/digm.digm_8_19
How to cite this article:
Krishnatreya M. Artificial intelligence in health care: A game changer. Digit Med 2019;5:46-7 |
Dear Editor,
Health care is now at the dawn of two significant developments. The first is the evolution of personalized medicine and second is the use of artificial intelligence (AI) in health care. The ability of a machine to represent the human mind and perform any intellectual task that a human can perform is termed AI. The field of AI has come a long way since the term was first coined by a group of researchers in 1956 at Dartmouth Summer Research Project on Artificial Intelligence.[1] AI basically uses sophisticated algorithms to learn features from a large volume of health-care data. In the near future, most health-care professionals will be using AI as deep neural network. A deep learning neural network consists of digitized inputs, such as an image or speech, which proceed through multiple layers of connected neurons that progressively detect features and ultimately provide an output, which is a diagnosis in medicine practice. Deep neural networks can help interpret medical scans, pathology slides, skin lesions, retinal images, electrocardiograms, endoscopy, and vital signs, all by itself without human interpretation. In one study in detecting pneumonia in over 112,000 chest X-ray images which were compared with that of four radiologists, the conclusion was that the AI algorithm outperformed the radiologists.[2] Another field is pathology, where there is marked heterogeneity among pathologists' interpretations of slides for various conditions. In a study of breast cancer, with or without local spread that compared the performance of 11 pathologists with that of AI system,[3] the results varied and were affected in part by the length of time that the pathologists had to review the slides. Some of the AI algorithms performed better than the group of pathologists, who had varying expertise. The pathologists were given 129 test slides and had <1 min for review per slide, which likely does not reflect the normal workflow. On the other hand, when one expert pathologist had no time limits and took 30 h to review the same slide set, the results were comparable with the algorithm for detecting cancer. The study emphasized the synergy between a pathologist and AI system for saving time and consistency in the diagnosis. One of the recent interests of AI in health care is in cancer screening. In the field of mental health, AI has been explored for predicting successful antidepressant medication,[4] characterizing depression,[5] predicting suicide, and predicting bouts of psychosis in schizophrenics,[6] to name a few. Similarly, smartphone examinations with AI are being considered for a variety of medical diagnostic purposes, such as skin lesions and rashes, ear infections, headaches, and retinal diseases such as diabetic retinopathy and age-related macular degeneration.[7]
AI in health care will complement the present system of health-care services. Many of the hurdles in delivering health care to all, such as lack of specialist physician in every nook and corner, can be taken care of by the use of AI. The combination of AI and huge cache of health-care data offers the potential to create a revolutionary way of practicing evidence-based medicine in future.
Financial support and sponsorship
Nil.
Conflicts of interest
There are no conflicts of interest.
| References | |  |
| 1. | |
| 2. | Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases; 2017. Available from: https://www.arxiv.org/abs/1705.02315. [Last accessed on 2019 Apr 01].  |
| 3. | Ehteshami Bejnordi B, Veta M, Johannes van Diest P, van Ginneken B, Karssemeijer N, Litjens G, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 2017;318:2199-210. |
| 4. | Mohr DC, Riper H, Schueller SM. A solution-focused research approach to achieve an implementable revolution in digital mental health. JAMA Psychiatry 2018;75:113-4. |
| 5. | Schnyer DM, Clasen PC, Gonzalez C, Beevers CG. Evaluating the diagnostic utility of applying a machine learning algorithm to diffusion tensor MRI measures in individuals with major depressive disorder. Psychiatry Res Neuroimaging 2017;264:1-9. |
| 6. | Walsh CG, Ribeiro JD, Franklin JC. Predicting risk of suicide attempts over time through machine learning. Clin Psychol Sci 2017;5:457-69. |
| 7. | Topol EJ. High-performance medicine: The convergence of human and artificial intelligence. Nat Med 2019;25:44-56. |
|
Search Pubmed for