Watson for Oncology (WFO) – more details

Back to Watson for Oncology (WFO). … so today was deep dive day to look at what papers were written specifically re WFO.

So,  on Sunday, June 23, 2019, using Google Scholar … the list below is of  the main useful things I could find.

Conclusions:

• Shows promise
• Not ready for solo flight (i.e. needs clinicians to work with it).
• Benefits from adding diagnostic tests liken GEA (Gene expression assays)
• Keep working on improving WFO, and understand specifics better.

 

Literature I looked at, will look at it again in more detail, and provide further insights.

1. Choi, Y. I., Chung, J. W., Kim, K. O., Kwon, K. A., Kim, Y. J., Park, D. K., … & Sung, K. H. (2019). Concordance Rate between Clinicians and Watson for Oncology among Patients with Advanced Gastric Cancer: Early, Real-World Experience in Korea. Canadian Journal of Gastroenterology and Hepatology, 2019.
2. Kim, Y. Y., Oh, S. J., Chun, Y. S., Lee, W. K., & Park, H. K. (2018). Gene expression assay and Watson for Oncology for optimization of treatment in ER-positive, HER2-negative breast cancer. PloS one, 13(7), e0200100.
3. Schmidt, C. (2017). MD Anderson breaks with IBM Watson, raising questions about artificial intelligence in oncology. JNCI: Journal of the National Cancer Institute, 109(5).
4. Zhang, X. C., Zhou, N., Zhang, C. T., Lv, H. Y., Li, T. J., Zhu, J. J., … & Liu, G. (2017). 544P Concordance study between IBM Watson for Oncology (WFO) and clinical practice for breast and lung cancer patients in China. Annals of Oncology, 28(suppl_10), mdx678-001.
5. Zou, F., Liu, C. Y., Liu, X. H., Tang, Y. F., Ma, J. A., & Hu, C. H. (2018). Concordance Study between IBM Watson for Oncology and Real Clinical Practice for Cervical Cancer Patients in China: A Retrospective Analysis. Available at SSRN 3287513.
6. Somashekhar, S. P., Sepúlveda, M. J., Puglielli, S., Norden, A. D., Shortliffe, E. H., Rohit Kumar, C., … & Ramya, Y. (2018). Watson for Oncology and breast cancer treatment recommendations: agreement with an expert multidisciplinary tumor board. Annals of Oncology, 29(2), 418-423.
7. Somashekhar, S. P., Sepúlveda, M. J., Norden, A. D., Rauthan, A., Arun, K., Patil, P., … & Kumar, R. C. (2017). Early experience with IBM Watson for Oncology (WFO) cognitive computing system for lung and colorectal cancer treatment.
8. Somashekhar, S. P., Kumarc, R., Rauthan, A., Arun, K. R., Patil, P., & Ramya, Y. E. (2017). Abstract S6-07: Double blinded validation study to assess performance of IBM artificial intelligence platform, Watson for oncology in comparison with Manipal multidisciplinary tumour board–First study of 638 breast cancer cases.
9. Liu, C., Liu, X., Wu, F., Xie, M., Feng, Y., & Hu, C. (2018). Using artificial intelligence (Watson for oncology) for treatment recommendations amongst Chinese patients with lung cancer: Feasibility study. Journal of medical Internet research, 20(9), e11087.
10. Ross, C., & Swetlitz, I. (2017). IBM pitched its Watson supercomputer as a revolution in cancer care. It’s nowhere close. STAT News.
11. Zauderer, M. G., Gucalp, A., Epstein, A. S., Seidman, A. D., Caroline, A., Granovsky, S., … & Petri, J. (2014). Piloting IBM Watson Oncology within Memorial Sloan Kettering’s regional network.
12. Herath, D. H., Wilson-Ing, D., Ramos, E., & Morstyn, G. (2016). Assessing the natural language processing capabilities of IBM Watson for oncology using real Australian lung cancer cases.
13. Bach, P., Zauderer, M. G., Gucalp, A., Epstein, A. S., Norton, L., Seidman, A. D., … & Keesing, J. (2013). Beyond Jeopardy!: Harnessing IBM’s Watson to improve oncology decision making.
14. Kris, M. G., Gucalp, A., Epstein, A. S., Seidman, A. D., Fu, J., Keesing, J., … & Setnes, M. (2015). Assessing the performance of Watson for oncology, a decision support system, using actual contemporary clinical cases.

Hagen’s Biological and clinical data integration in healthcare study is great!

Just finished looking at Matt Hagen’s 2014 “Biological and clinical data integration and its applications in healthcare.” PhD  dissertation. This is a great piece of work … You can find it here.

While its around 5 years old, the insights and discussion are excellent.  I like the detailed breakdown of how different ontologies and vocabularies align (and how things fall through the cracks).  I liked the discussion of using Neo4j to analyze relationships and simplify searches and relationship mappings.

Particularly liked the discussion of using  ontologies.  to” facilitate improved prioritization of intensive care admissions and accurate clustering of multimorbidity conditions”.  THIS IS BIG! with enormous potential.

Discussion of his BioSPIDA relational database translator and its contrast with  the separate Entrez Gene, Pubmed, CDD, Refseq, MMDB, and Biosystems NCBI databases.

His Table 7.2: Descriptions of patient clusters is rather illuminating, as his discussion and analysis of ICU Electronic Health Records and findings associated with morbidity outcomes.

For example Cluster 1 contains the following Most Prevalent Conditions: Coronary arteriosclerosis, Hypercholesterolemia, Diabetes, Gastroesophageal reflux disease,  Atrial fibrillation, Hyperlipidemia, Tobacco dependence.  Which led to the following Most Prevalent Procedures:  Catheterization of left heart, Cardiopulmonary bypass operation, Angiocardiography of left heart,.

 

 I  am surprised this work is not cited as much as it should be!.  IMHO, this work definitely should be used as blueprint for additional investigations.