Cognitive computing in oncology: A qualitative assessment of IBM Watson for Oncology in Mexico.

Abstract

e18166 Background: Watson for Oncology (WFO) is a Memorial Sloan Kettering trained cognitive computing system designed to extract structured and unstructured data from medical records; ingest a large body of published evidence and guidelines; and provide evidence-based treatment options tailored to an individual patient. In Mexico, 160,000 new cases of cancer are diagnosed per year, causing almost 80,000 deaths. 70% of cases are diagnosed at a late stage (Secretariat of Health, 2016). Given the burden of cancer on morbidity and mortality in Mexico, WFO was evaluated as a potential tool to help oncologists select treatment options for their patients. Our objective was to gain feedback on the experience of using WFO in a Mexican population by a panel of local oncology experts, retrospectively comparing their treatment recommendations to the options provided by WFO. Methods: Patient cases with lung, breast, gastric, colon and rectal cancer diagnosed within the last 5 years were included. Physician users were asked to describe the perceived utility of WFO and to compare the treatment options proposed by WFO with local treatment decisions and guidelines. Results: A total of 100 cases were processed using WFO. Oncologists found WFO to be very useful. They felt that it would be particularly beneficial in clinics that lack subspecialist expertise, and for training medical students and residents. Differences between WFO recommendations and those of the Mexican oncologists were attributed primarily to limited access to high-cost therapies in Mexico and differences between U.S. and Mexican cancer treatment guidelines. Conclusions: WFO is a cognitive computing tool that has the potential to improve the consistency, efficiency, and overall quality of cancer care in Mexico. By surfacing relevant literature and evidence, WFO may provide support for coverage of effective yet high-cost therapies.

Physicians’ Perceptions of and Satisfaction With Artificial Intelligence in Cancer Treatment: A Clinical Decision Support System Experience and Implications for Low-Middle–Income Countries

“…Physicians also chose chemotherapy instead of WfO's recommended medication because the medication was too expensive for patients. Similar challenges were found for WfO users in Mexico and Thailand [19,28]. In Mexico, clinicians deviated from WfO's recommendations due to the high costs associated with them and the fact that they did not adhere to Mexican cancer treatment guidelines [19].…”

“…Similar challenges were found for WfO users in Mexico and Thailand [19,28]. In Mexico, clinicians deviated from WfO's recommendations due to the high costs associated with them and the fact that they did not adhere to Mexican cancer treatment guidelines [19]. In Thailand, oncologists preferred basing their treatment recommendations on other countries' guidelines instead of US guidelines [28].…”

“…WfO's ability to compare treatment options was tested in Mexico, where it was used for a total of 100 patient cases involving lung, breast, gastric, colon, and rectal cancers diagnosed within the last 5 years [19]. In terms of perceived utility, oncologists found WfO to be "very useful" in comparing treatment options.…”

“…Additionally, there is concern about whether AI tools would exacerbate the divide in health care access and use, especially with respect to socioeconomic status. There is a fear that AI would recommend treatment options that patients cannot afford or that only high-income and educated patients who are aware of AI tools may benefit from the use of AI in LMICs [4,19,28] Another important concern-one that applies to a tool such as WfO-is that the data and training of AI tools may not incorporate patient characteristics into treatment recommendations. For example, in China, local patient characteristics such as gene mutations and the weaker physiques of Chinese patients, which can influence treatment recommendations, were not accounted for in WfO recommendations [20].…”

<p>Comparative review of drug–drug interactions with epidermal growth factor receptor tyrosine kinase inhibitors for the treatment of non-small-cell lung cancer</p>

“…“Cancer Drug Interactions” (https://cancer-druginteractions.org/), which is endorsed by the British Oncology Pharmacy Association, allows users to select from a list of anticancer drugs and commonly prescribed concomitant medications and obtain information on whether a DDI is likely, together with the rationale and quality of evidence. Watson for Oncology (https://www.ibm.com/watson/health/oncology-and-genomics/oncology/) is an artificial intelligence system that extracts data from medical records and provides evidence-based treatment options tailored to the individual patient 142,143. Lexicomp Online (http://www.lexi.com) and Micromedex 2.0 (http://micromedex.com) both include interactive tools for evaluation of drug interactions 144.…”