How Does The Massachusetts General Hospital Use Machine Learning

In a recent commodity in Register of Surgery, a research team from Massachusetts General Hospital and MIT details the ways in which bogus intelligence (AI) could revolutionize the practise and teaching of surgery—and how patients volition benefit with safer surgeries and better outcomes.

The squad, which includes Mass General physician-researchers Daniel Hashimoto, MD, MS, and Ozanan Meireles, Medico, from the Department of Surgery, encourages surgeons to interact with data scientists in the development of new AI applications and to find the nearly constructive means to integrate these technologies into clinical do.

For AI, much of its clinical potential lies in its ability to clarify combinations of structured and unstructured data such every bit EMR notes, vitals, laboratory values and video footage to provide surgeons with significantly improved clinical decision back up, the authors say.

While the potential for AI is not bad, the authors also circumspection that these technologies will only be equally good as the information that is used to power them—and the clinical expertise of the surgeons in implementing them into the operating room (OR).

Machine Learning

Machine learning (ML) is a method of data assay that identifies underlying patterns and structures to enable a computer to larn and make predictions.

By applying multiple algorithms to the same information set, ML applications could significantly improve on the predictions fabricated by conventional statistical methods, the authors say.

The authors note a recent study in which an ML application significantly outperformed a decision tree arroyo in predicting lung cancer staging.

The ML awarding performed at 93% sensitivity (correctly identifying the disease), 92% specificity (correctly identifying those who did not have the disease) and 72% accuracy (the percentage of patients it correctly identified out of the total). By comparison, the conclusion tree model performed at 53% sensitivity, 89% specificity and 72% accuracy.

Natural Language Processing

Natural language processing (NLP) is a subfield of AI that emphasizes building a estimator's power to sympathise human language. The authors say NLP volition play a crucial function in analyzing and integrating electronic medical information into AI applications, especially narrative documentation from physicians.

NLP technologies tin can be trained to extract relevant medical information out of narrative statements provided past physicians in a way that will allow physicians to write more naturally, rather than having to input specific text sequences or select from a card of options.

Bogus Neural Networks

Much like the brain changes the style it processes information equally it responds to external stimuli, bogus neural networks (ANNs) alter the pathways used to process data equally they develop different input and output maps corresponding to tasks such equally pattern recognition and data nomenclature.

A 2016 report demonstrated that by using clinical variables such every bit patient history, medications, blood pressure and length of stay, ANN algorithms can yield predictions of in-infirmary bloodshed afterwards open intestinal aortic aneurysm repair with a sensitivity of 87%, specificity of 96.i% and accurateness of 95.four%.

Computer Vision

Computer vision describes the ability of a car to clarify and empathise information contained in images and videos.

Utilizing ML approaches, electric current work in computer vision is focusing on college level concepts such as epitome-based assay of surgical procedures to identify patient cohorts, deport longitudinal studies and inform decision-making in surgery.

The authors say that computer vision could also be used equally a real-fourth dimension operating banana to identify and reply to surgical complications and errors.

For example, a recent study found that real-time assay of laparoscopic video yielded 92.8% accuracy in identifying the steps of a sleeve gastrectomy and was able to note missing or unexpected steps.

The Role of Surgeons

While these use cases are promising, the authors caution that as with any new technology, AI is susceptible to unrealistic expectations that tin can lead to disappoint and disillusionment.

"It is not a magic bullet that can respond all questions, and it will not meliorate on all methods of analysis."

For example, systemic biases in information collection can affect the accuracy of algorithms and could impact the accuracy of prediction models for women and racial minorities due to their under-representation in clinical trials.
"Although the automatic nature of these technologies finds patterns missed by humans, scientists are left with little ability to assess how or why such patterns were recognized by the computer."

The team says that surgeons must work to improve the variety of patient information in information models, abet for transparency in AI algorithms, and collaborate with patients to develop the right way to integrate AI technologies into clinical care.

"If appropriately developed and implemented, AI has the potential to revolutionize the fashion surgery is taught and practiced with the promise of a future optimized for highest quality patient care."

Larn More

Surgical Artificial Intelligence Laboratory (Canvass) at Mass Full general
TEDx Talk past Daniel Hashimoto, MD, MS
Watch the PBS News 60 minutes segment

Nigh the Mass General Enquiry Institute
Inquiry at Massachusetts General Hospital is interwoven through more than 30 different departments, centers and institutes. Our research includes fundamental, lab-based science; clinical trials to test new drugs, devices and diagnostic tools; and customs and population-based enquiry to improve wellness outcomes across populations and eliminate disparities in care.
Support our Research