Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Mar 24, 2019
Open Peer Review Period: Mar 27, 2019 - May 22, 2019
Date Accepted: Dec 16, 2019
(closed for review but you can still tweet)
The Concordance Study between IBM Watson for Oncology and Multidisciplinary Team in Clinical Decision-making of Gastric Cancer and the Prognostic Implication
ABSTRACT
Background:
With the increasingly abundant of cancer treatment, the emergence of multidisciplinary team (MDT) will provide patients with personalized treatment options. In recent years, artificial intelligence has developed rapidly in the medical field. And there is a tendency to replace traditional diagnosis and treatment gradually. IBM Watson for Oncology (WFO) has been proven in breast cancer and lung cancer, but the research on gastric cancer is rarely so far.
Objective:
Compared the concordance of WFO with that of MDT, and we try to investigate the patients' prognosis between them.
Methods:
This study retrospectively analyzed the eligible cases (N=235) of MDT with gastric cancer who received the corresponding treatment and obtained follow-up. Then doctors input the information of all cases into WFO manually, and the results was compared with the treatment programs by MDT. If the treatment program of MDT is classified as “recommended” or “considered”, we define the results as concordant. All patients were divided into concordant group and non-concordant group according to whether the treatment program of WFO and MDT were concordant. The prognostic analysis of the two groups was analyzed.
Results:
The overall concordance of WFO and MDT was 54.5% (128/235) in all 235 cases included in the study. Subgroup analysis found that patients with human epidermal growth factor receptor 2 (HER2)-positive were less likely to be concordant than patients with HER2-negative (P=0.019). Age, Eastern Cooperative Oncology Group performance status, differentiation type and clinical stage was not found to affect concordance. In all patients, the survival time of concordant patients were significantly better than that of non-concordant patients (P<0.001). Multivariate analysis revealed that consistency was an independent prognostic factor of overall survival in patients with gastric cancer (HR=0.312, 95% CI: 0.187-0.521).
Conclusions:
Treatment recommendations made by WFO and MDT were mostly concordant for gastric cancer cases. If they can include the local treatment programs, the concordance will be significantly improved. The HER2 status of gastric cancer have a significant effect on concordance. Generally speaking, patients with concordant treatment programs had quite better survival than non-concordant patients.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.