Column – The power of artificial intelligence in the medical field
Artificial intelligence, or AI, is transforming the medical device industry today. As medical devices continue to integrate artificial intelligence to run or support medical applications, new regulations require AI-based medical devices to comply with state-of-the-art requirements and provide objective evidence of repeatability and of reliability. AI has the potential to improve patient outcomes as well as the productivity and efficiency of healthcare delivery. It can also improve the daily lives of healthcare providers by allowing them to spend more time caring for patients, thereby improving staff morale and retention. It could even accelerate the development of life-saving therapies. At the same time, concerns have been raised about the influence that AI can have on patients, practitioners and healthcare systems, as well as its potential risks; ethical arguments have erupted over how AI and the data that supports it should be used.
Leading researchers and clinical faculty members presented 12 technologies and healthcare industry areas that are most likely to see a major impact from artificial intelligence over the next decade at the Global Health Forum. Medical Innovation 2018 on Artificial Intelligence, organized by Partners Healthcare.
AI in medical equipment and healthcare
From real-time video from inside a refrigerator to automobiles that can identify when the driver is inattentive, smart gadgets are sweeping the consumer market. In the medical industry, smart gadgets are essential for monitoring patients in intensive care and elsewhere. Artificial intelligence can improve outcomes and minimize the costs associated with nosocomial illness penalties by improving the ability to predict deterioration, detect the development of sepsis, or detect the onset of complications.
When a section of heart muscle doesn’t get enough blood, it causes a heart attack, also known as a myocardial infarction. The longer heart muscle goes untreated to restore blood flow, the more damage it takes. The most common cause of heart attack is coronary artery disease. A strong spasm or sudden contraction of a coronary artery, which can block blood flow to the heart muscle, is a less common reason. Experts from the University of Oxford have used machine learning to create a “fingerprint” or biomarker.
The radiomic fat profile reveals biological red flags in the blood arteries that supply blood to the heart, such as inflammation, scarring, and vessel damage, all of which are indicators of a potential heart attack. Another example is Cardiovascular Magnetic Resonance (CMR): CMR is a scan that detects how much of a particular contrast agent the heart muscle picks up and assesses blood flow to the heart; the stronger the blood flow, the fewer blockages there will be in the heart veins.
Uncontrolled diabetes causes diabetes mellitus, which can lead to multiple organ failure in individuals. Thanks to improvements in machine learning and artificial intelligence, it is now possible to detect and diagnose diabetes in its early stages using an automated procedure that is more efficient than manual diagnosis. Image-based AI-assisted medical screening and diagnosis is currently under development. Diabetic retinopathy (DR), age-related macular degeneration, glaucoma, retinopathy of prematurity, age-related or congenital cataracts and retinal vein occlusion are some of the disorders where this technique is now applied in ophthalmology.
IDx-DR is the first AI algorithm cleared by the FDA to detect DR in non-ophthalmology healthcare professional offices. The gadget is hooked up to a non-mydriatic retinal camera (Topcon’s TRC-NW400), which sends the images to a cloud-based server. Based on a standalone comparison with a large collection of typical fundus photos, the server uses IDx-DR software and a deep-learning algorithm to discover retinal abnormalities consistent with DR. One of two outcomes is provided by the software: (1) Refer to an Eye Care Professional (ECP) if more than moderate DR is found; (2) If results are negative for more than mild DR, repeat screening in 12 months.
Immunotherapy is one of the most promising methods of treating cancer. Patients can defeat resistant tumors by attacking them with the body’s immune system. Machine learning algorithms and their ability to synthesize extremely complex data can open up new avenues for tailoring drugs to a person’s genetic makeup.
Dermatology and Ophthalmology
Every year, the quality of mobile phone cameras improves and they can now create photos that can be analyzed by artificial intelligence systems. Two of the first specialties to benefit from this trend are dermatology and ophthalmology. British researchers have even developed a gadget that analyzes photos of a child’s face to detect developmental difficulties. The approach can detect inconspicuous features including a child’s jaw, eye and nose placement, and other features that might suggest craniofacial aberration. The program can associate daily images with more than 90 diseases, allowing doctors to make more informed decisions.
Electronic health records are a goldmine of patient data, but doctors and engineers have struggled to collect and analyze it accurately, quickly and reliably.
Due to data quality and integrity challenges, as well as a tangle of data formats, structured and unstructured inputs, and missing data, it was particularly difficult to figure out how to engage in stratification. meaningful risk, predictive analytics and clinical decision support. From cell phones with step tracking to wearable devices capable of detecting a pulse around the clock, a significant amount of health-related data is generated on the road. Collecting and analyzing this information, and complementing it with information provided by patients through apps and other home monitoring devices, can provide a unique perspective on the health of individuals and populations. Artificial intelligence will play a key role in obtaining relevant insights from this massive and diverse dataset.
The difficulty of interoperability and integration is one of the main traits that separates academic research from practical applications of AI. The majority of research focuses on building AI models that work with carefully vetted health datasets. Data is complex, dispersed and difficult to access in real life. Lack of sufficient data architecture is often the biggest barrier to integrating AI into current applications.
Machine learning and artificial intelligence research require high quality reports. The danger of bias and the possible value of prediction models can only be accurately assessed if all characteristics of a diagnostic or prognostic model are fully and clearly reported. Machine learning studies should aim to follow best practice recommendations such as transparent reporting of a Multivariate Prediction Model for Individual Prognosis or Diagnosis (TRIPOD), which is designed to help researchers report studies that develop, validate or update a predictive model for diagnosis or prognosis. purposes.
Artificial intelligence has great potential in medical science beyond what we can imagine, and current applications are just the beginning. As we have briefly mentioned, immunotherapy holds great promise in the treatment of cancer. As we know, cancer is a deadly disease that affects vital parts of the body. The personalization of the diagnosis according to the genes of the patient is simply exceptional. It is imminent that AI will help us effectively diagnose diseases, develop personalized medicines for complex treatments, and much more.
In addition, many of the disease states discussed are a determining factor in a patient’s cause of death (ie, heart attack). Not to mention that the adverse effects of diabetes are unimaginable, including cardiovascular complications, kidney damage, and eye damage. Retinal image analysis also helps diabetic patients because it helps the doctor analyze the fundus image, which can help determine the next steps in a patient’s treatment more quickly. Physicians could deal with more patients needing treatment. Emerging healthcare technologies aim to minimize visits to eye care specialists, reduce total treatment costs and increase the number of patients seen by each practitioner. AI can help the healthcare provider achieve their goal more efficiently.
While this technology is useful in the healthcare industry, it should not be used to replace a clinician’s time. Advances in AI bring new possibilities for running and scoring algorithms. But as noted, this is only the beginning of the era of artificial intelligence and machine learning in medical sciences. The more we focus on improving data quality and automating the analysis of medical data, the more algorithms can help us identify useful patterns – patterns that can be used to make accurate and profitable judgments. in complex procedures.