Dataset Information

Concordance Between Watson for Oncology and a Multidisciplinary Clinical Decision-Making Team for Gastric Cancer and the Prognostic Implications: Retrospective Study.

ABSTRACT: BACKGROUND:With the increasing number of cancer treatments, the emergence of multidisciplinary teams (MDTs) provides patients with personalized treatment options. In recent years, artificial intelligence (AI) has developed rapidly in the medical field. There has been a gradual tendency to replace traditional diagnosis and treatment with AI. IBM Watson for Oncology (WFO) has been proven to be useful for decision-making in breast cancer and lung cancer, but to date, research on gastric cancer is limited. OBJECTIVE:This study compared the concordance of WFO with MDT and investigated the impact on patient prognosis. METHODS:This study retrospectively analyzed eligible patients (N=235) with gastric cancer who were evaluated by an MDT, received corresponding recommended treatment, and underwent follow-up. Thereafter, physicians inputted the information of all patients into WFO manually, and the results were compared with the treatment programs recommended by the MDT. If the MDT treatment program was classified as "recommended" or "considered" by WFO, we considered the results concordant. All patients were divided into a concordant group and a nonconcordant group according to whether the WFO and MDT treatment programs were concordant. The prognoses of the two groups were analyzed. RESULTS:The overall concordance of WFO and the MDT was 54.5% (128/235) in this study. The subgroup analysis found that concordance was less likely in patients with human epidermal growth factor receptor 2 (HER2)-positive tumors than in patients with HER2-negative tumors (P=.02). Age, Eastern Cooperative Oncology Group performance status, differentiation type, and clinical stage were not found to affect concordance. Among all patients, the survival time was significantly better in concordant patients than in nonconcordant patients (P<.001). Multivariate analysis revealed that concordance was an independent prognostic factor of overall survival in patients with gastric cancer (hazard ratio 0.312 [95% CI 0.187-0.521]). CONCLUSIONS:The treatment recommendations made by WFO and the MDT were mostly concordant in gastric cancer patients. If the WFO options are updated to include local treatment programs, the concordance will greatly improve. The HER2 status of patients with gastric cancer had a strong effect on the likelihood of concordance. Generally, survival was better in concordant patients than in nonconcordant patients.

SUBMITTER: Tian Y

PROVIDER: S-EPMC7059081 | biostudies-literature | 2020 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Concordance Between Watson for Oncology and a Multidisciplinary Clinical Decision-Making Team for Gastric Cancer and the Prognostic Implications: Retrospective Study.

Tian Yulong Y Liu Xiaodong X Wang Zixuan Z Cao Shougen S Liu Zimin Z Ji Qinglian Q Li Zequn Z Sun Yuqi Y Zhou Xin X Wang Daosheng D Zhou Yanbing Y

Journal of medical Internet research 20200220 2

<h4>Background</h4>With the increasing number of cancer treatments, the emergence of multidisciplinary teams (MDTs) provides patients with personalized treatment options. In recent years, artificial intelligence (AI) has developed rapidly in the medical field. There has been a gradual tendency to replace traditional diagnosis and treatment with AI. IBM Watson for Oncology (WFO) has been proven to be useful for decision-making in breast cancer and lung cancer, but to date, research on gastric can ...[more]

PMID: 32130123

Similar Datasets

Project description:BackgroundThe quality of decision-making in multidisciplinary team meetings (MDTMs) depends on the quality of information presented and the quality of team processes. Few studies have examined these factors using a standardized approach. The aim of this study was to objectively document the processes involved in decision-making in MDTMs, document the outcomes in terms of whether a treatment recommendation was given (none vs. singular vs. multiple), and to identify factors related to type of treatment recommendation.MethodsAn adaptation of the observer rating scale Multidisciplinary Tumor Board Metric for the Observation of Decision-Making (MDT-MODe) was used to assess the quality of the presented information and team processes in MDTMs. Data was analyzed using descriptive statistics and mixed logistic regression analysis.ResultsN?=?249 cases were observed in N?=?29 MDTMs. While cancer-specific medical information was judged to be of high quality, psychosocial information and information regarding patient views were considered to be of low quality. In 25% of the cases no, in 64% one, and in 10% more than one treatment recommendations were given (1% missing data). Giving no treatment recommendation was associated with duration of case discussion, duration of the MDTM session, quality of case history, quality of radiological information, and specialization of the MDTM. Higher levels of medical and treatment uncertainty during discussions were found to be associated with a higher probability for more than one treatment recommendation.ConclusionsThe quality of different aspects of information was observed to differ greatly. In general, we did not find MDTMs to be in line with the principles of patient-centered care. Recommendation outcome varied substantially between different specializations of MDTMs. The quality of certain information was associated with the recommendation outcome. Uncertainty during discussions was related to more than one recommendation being considered. Time constraints were found to play an important role. Some of those aspects seem modifiable, which offers possibilities for the reorganization of MDTMs.

Project description:ObjectiveThe objective of this study was to examine effectiveness of codesigned quality-improving interventions with a multidisciplinary team (MDT) with high workload and prolonged meetings to ascertain: (1) presence and impact of decision-making (DM) fatigue on team performance in the weekly MDT meeting and (2) impact of a short meeting break as a countermeasure of DM fatigue.Design and interventionsThis is a longitudinal multiphase study with a codesigned intervention bundle assessed within team audit and feedback cycles. The interventions comprised short meeting breaks, as well as change of room layout and appointing a meeting chair.Setting and participantsA breast cancer MDT with 15 members was recruited between 2013 and 2015 from a teaching hospital of the London (UK) metropolitan area.MeasuresA validated observational tool (Metric for the Observation of Decision-making) was used by trained raters to assess quality of DM during 1335 patient reviews. The tool scores quality of information and team contributions to reviews by individual disciplines (Likert-based scores), which represent our two primary outcome measures.ResultsData were analysed using multivariate analysis of variance. DM fatigue was present in the MDT meetings: quality of information (M=16.36?to M=15.10) and contribution scores (M=27.67?to M=21.52) declined from first to second half of meetings at baseline. Of the improvement bundle, we found breaks reduced the effect of fatigue: following introduction of breaks (but not other interventions) information quality remained stable between first and second half of meetings (M=16.00?to M=15.94), and contributions to team DM improved overall (M=17.66?to M=19.85).ConclusionQuality of cancer team DM is affected by fatigue due to sequential case review over often prolonged periods of time. This detrimental effect can be reversed by introducing a break in the middle of the meeting. The study offers a methodology based on 'team audit and feedback' principle for codesigning interventions to improve teamwork in cancer care.

Project description:BackgroundThe contribution of patients' non-medical characteristics to individual physicians' decision-making has attracted considerable attention, but little information is available on this topic in the context of collective decision-making. Medical decision-making at cancer centres is currently carried out using a collective approach, at MultiDisciplinary Team (MDT) meetings. The aim of this study was to determine how patients' non-medical characteristics are presented at MDT meetings and how this information may affect the team's final medical decisions.DesignObservations were conducted at a French Cancer Centre during MDT meetings at which non-standard cases involving some uncertainty were discussed from March to May 2014. Physicians' verbal statements and predefined contextual parameters were collected with a non-participant observational approach. Non numerical data collected in the form of open notes were then coded for quantitative analysis. Univariate and multivariate statistical analyses were performed.ResultsIn the final sample of patients' records included and discussed (N = 290), non-medical characteristics were mentioned in 32.8% (n = 95) of the cases. These characteristics corresponded to demographics in 22.8% (n = 66) of the cases, psychological data in 11.7% (n = 34), and relational data in 6.2% (n = 18). The patient's age and his/her "likeability" were the most frequently mentioned characteristics. In 17.9% of the cases discussed, the final decision was deferred: this outcome was positively associated with the patients' non-medical characteristics and with uncertainty about the outcome of the therapeutic options available.LimitationsThe design of the study made it difficult to draw definite cause-and-effect conclusions.ConclusionThe Social Representations approach suggests that patients' non-medical characteristics constitute a kind of tacit professional knowledge that may be frequently mobilised in physicians' everyday professional practice. The links observed between patients' attributes and the medical decisions made at these meetings show that these attributes should be taken into account in order to understand how medical decisions are reached in difficult situations of this kind.

Project description:BackgroundMultidisciplinary teams (MDT) formulate expert informed treatment recommendations for people with cancer. We set out to examine how the factors proposed by the functional perspective of group decision making (DM), that is, interaction process, internal factors (factors emanating from within the group such as group size), external circumstances (factors coming from the outside of the team), and case-complexity affect the quality of MDT decision making.MethodsThis was a cross-sectional observational study. Three cancer MDTs were recruited with 44 members overall and 30 of their weekly meetings filmed. Validated observational instruments were used to measure quality of DM, interactions, and complexity of 822 case discussions.ResultsThe full regression model with the variables proposed by the functional perspective was significant, R2 = 0.52, F(20, 801) = 43.47, P < .001, adjusted R2 = 0.51. Positive predictors of DM quality were asking questions (P = .001), providing answers (P = .001), team size (P = .007), gender balance (P = .003), and clinical complexity (P = .001), while negative socioemotional reactions (P = .007), gender imbalance (P = .003), logistical issues (P = .001), time-workload pressures (P = .002), and time spent in the meeting (P = .001) were negative predictors. Second half of the meetings also saw significant decrease in the DM quality (P = .001), interactions (P = .001), group size (P = .003), and clinical complexity (P = .001), and an increase in negative socioemotional reactions (P = .001) and time-workload pressures (P = .001).DiscussionTo the best of our knowledge, this is the first study to attempt to assess the factors proposed by the functional perspective in cancer MDTs. One novel finding is the effect of sociocognitive factors on team DM quality, while another is the cognitive-catch 22 effect: while the case discussions are significantly simpler in the second half of the meeting, there is significantly less time left to discuss the remaining cases, further adding to the cognitive taxation in teams who are now rapidly attempting to close their time-workload gap. Implications are discussed in relation to quality and safety.

Project description:IntroductionMultidisciplinary team meetings (MDMs), also known as tumor conferences, are a cornerstone of cancer treatments. However, barriers such as incomplete patient information or logistical challenges can postpone tumor board decisions and delay patient treatment, potentially affecting clinical outcomes. Therapeutic Assistance and Decision algorithms for hepatobiliary tumor Boards (ADBoard) aims to reduce this delay by providing automated data extraction and high-quality, evidence-based treatment recommendations.Methods and analysisWith the help of natural language processing, relevant patient information will be automatically extracted from electronic medical records and used to complete a classic tumor conference protocol. A machine learning model is trained on retrospective MDM data and clinical guidelines to recommend treatment options for patients in our inclusion criteria. Study participants will be randomized to either MDM with ADBoard (Arm A: MDM-AB) or conventional MDM (Arm B: MDM-C). The concordance of recommendations of both groups will be compared using interrater reliability. We hypothesize that the therapy recommendations of ADBoard would be in high agreement with those of the MDM-C, with a Cohen's kappa value of ≥ 0.75. Furthermore, our secondary hypotheses state that the completeness of patient information presented in MDM is higher when using ADBoard than without, and the explainability of tumor board protocols in MDM-AB is higher compared to MDM-C as measured by the System Causability Scale.DiscussionThe implementation of ADBoard aims to improve the quality and completeness of the data required for MDM decision-making and to propose therapeutic recommendations that consider current medical evidence and guidelines in a transparent and reproducible manner.Ethics and disseminationThe project was approved by the Ethics Committee of the Charité - Universitätsmedizin Berlin.Registration detailsThe study was registered on ClinicalTrials.gov (trial identifying number: NCT05681949; https://clinicaltrials.gov/study/NCT05681949 ) on 12 January 2023.

Project description:BackgroundIBM Watson for Oncology (WFO), which can use natural language processing to evaluate data in structured and unstructured formats, has begun to be used in China. It provides physicians with evidence-based treatment options and ranks them in three categories for treatment decision support. This study was designed to examine the concordance between the treatment recommendation proposed by WFO and actual clinical decisions by oncologists in our cancer center, which would reflect the differences of cancer treatment between China and the U.S.Patients and methodsRetrospective data from 362 patients with cancer were ingested into WFO from April 2017 to October 2017. WFO recommendations were provided in three categories: recommended, for consideration, and not recommended. Concordance was analyzed by comparing the treatment decisions proposed by WFO with those of the multidisciplinary tumor board. Concordance was achieved when the oncologists' treatment decisions were in the recommended or for consideration categories in WFO.ResultsOvarian cancer showed the highest concordance, which was 96%. Lung cancer and breast cancer obtained a concordance of slightly above 80%. The concordance of rectal cancer was 74%, whereas colon cancer and cervical cancer showed the same concordance of 64%. In particular, the concordance of gastric cancer was very low, only 12%, and 88% of cases were under physicians choice.ConclusionDifferent cancer types showed different concordances, and only gastric cancers were significantly less likely to be concordant. Incidence and pharmaceuticals may be the major cause of discordance. To be comprehensively and rapidly applied in China, WFO needs to accelerate localization. ClinicalTrials.gov Identifier: NCT03400514.Implications for practiceIBM Watson for Oncology (WFO) has begun to be used in China. In this study, concordance was examined between the treatment recommendation proposed by WFO and clinical decisions for 362 patients in our cancer center, which could reflect the differences of cancer treatment between China and the U.S. Different cancer types showed different concordances, and only gastric cancers were significantly less likely to be concordant. Incidence and pharmaceuticals may be the major causes of discordance. To be comprehensively and rapidly applied in China, WFO needs to accelerate localization. This study may have a significant effect on application of artificial intelligence systems in China.

Project description:ImportanceWait times for autism spectrum disorder (ASD) diagnosis are lengthy because of inadequate supply of specialist teams. General pediatricians may be able to diagnose some cases of ASD, thereby reducing wait times.ObjectiveTo determine the accuracy of ASD diagnostic assessments conducted by general pediatricians compared with a multidisciplinary team (MDT).Design, setting, and participantsThis prospective diagnostic study was conducted in and a specialist assessment center in Toronto, Ontario, Canada, and Ontario general pediatrician practices from June 2016 to March 2020. Children were younger than 5.5 years, referred with a developmental concern, and without an existing ASD diagnosis. Data analysis was performed from October 2021 to February 2022.ExposuresThe pediatrician and MDT each conducted blinded assessments and recorded a decision as to whether the child had ASD.Main outcomes and measuresMain outcomes included sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). A logistic regression was performed to identify factors associated with accurate pediatrician assessment for children with or without an ASD diagnosis.ResultsSeventeen pediatricians (12 women [71%]) participated in the study and referred 106 children (79 boys [75%]; mean [SD] age, 41.9 [13.3] months). Sixty participants (57%) were from minoritized racial and ethnic groups (eg, Black, Asian, Hispanic, Middle Eastern, and multiracial). Seventy-two participants (68%) received a diagnosis of ASD by the MDT. Sensitivity and specificity of the pediatrician assessments compared with MDT were 0.75 (95% CI, 0.67-0.83) and 0.79 (95% CI, 0.62-0.91), respectively. The PPV of the pediatrician assessments was 0.89 (95% CI, 0.80-0.94) (ie, 89% agreement with the MDT), and NPV was 0.60 (95% CI, 0.49-0.70) (ie, 60% agreement with the MDT). Higher pediatrician certainty (odds ratio [OR], 3.33; 95% CI, 1.71-7.34; P = .001) was associated with increased diagnostic accuracy for children with ASD. Lower accuracy was seen for children with higher Visual Reception subscale developmental skills (OR, 0.93; 95% CI, 0.89-0.97; P = .001), speaking abilities (OR, 0.17; 95% CI, 0.03-0.67; P = .03), and White race (OR, 0.32; 95% CI, 0.10-0.97; P = .04). Age, gender, and Autism Diagnostic Observation Schedule, 2nd Edition composite scores were not significantly associated with the accuracy of assessments. All 7 children with a sibling with ASD received an accurate diagnosis; otherwise, no significant factors were identified for accuracy in children without ASD.Conclusions and relevanceThis study of concordance of autism assessment between pediatricians and an expert MDT in young children found high accuracy when general pediatricians felt confident and lower accuracy when ruling out ASD. These findings suggest that children with co-occurring delays may be potential candidates for community assessment.

Dataset Information

Concordance Between Watson for Oncology and a Multidisciplinary Clinical Decision-Making Team for Gastric Cancer and the Prognostic Implications: Retrospective Study.

Publications

Concordance Between Watson for Oncology and a Multidisciplinary Clinical Decision-Making Team for Gastric Cancer and the Prognostic Implications: Retrospective Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets