scholarly journals Establishment of CORONET; COVID-19 Risk in Oncology Evaluation Tool to identify cancer patients at low versus high risk of severe complications of COVID-19 infection upon presentation to hospital

2020 ◽  
Author(s):  
R.J. Lee ◽  
C. Zhou ◽  
O. Wysocki ◽  
R. Shotton ◽  
A. Tivey ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Decision Support ◽  
Cancer Patients ◽  
Sensitivity And Specificity ◽  
Decision Support Tool ◽  
Superior Performance ◽  
Evaluation Tool ◽  
Support Tool ◽  
Entire Cohort ◽  
Severity Prediction

AbstractBackgroundCancer patients are at increased risk of severe COVID-19. As COVID-19 presentation and outcomes are heterogeneous in cancer patients, decision-making tools for hospital admission, severity prediction and increased monitoring for early intervention are critical.ObjectiveTo identify features of COVID-19 in cancer patients predicting severe disease and build a decision-support online tool; COVID-19 Risk in Oncology Evaluation Tool (CORONET)MethodData was obtained for consecutive patients with active cancer with laboratory confirmed COVID-19 presenting in 12 hospitals throughout the United Kingdom (UK). Univariable logistic regression was performed on pre-specified features to assess their association with admission (≥24 hours inpatient), oxygen requirement and death. Multivariable logistic regression and random forest models (RFM) were compared with patients randomly split into training and validation sets. Cost function determined cut-offs were defined for admission/death using RFM. Performance was assessed by sensitivity, specificity and Brier scores (BS). The CORONET model was then assessed in the entire cohort to build the online CORONET tool.ResultsTraining and validation sets comprised 234 and 66 patients respectively with median age 69 (range 19-93), 54% males, 46% females, 71% vs 29% had solid and haematological cancers. The RFM, selected for further development, demonstrated superior performance over logistic regression with AUROC predicting admission (0.85 vs. 0.78) and death (0.76 vs. 0.72). C-reactive protein was the most important feature predicting COVID-19 severity. CORONET cut-offs for admission and mortality of 1.05 and 1.8 were established. In the training set, admission prediction sensitivity and specificity were 94.5% and 44.3% with BS 0.118; mortality sensitivity and specificity were 78.5% and 57.2% with BS 0.364. In the validation set, admission sensitivity and specificity were 90.7% and 42.9% with BS 0.148; mortality sensitivity and specificity were 92.3% and 45.8% with BS 0.442. In the entire cohort, the CORONET decision support tool recommended admission of 99% of patients requiring oxygen and of 99% of patients who died.Conclusions and RelevanceCORONET, a decision support tool validated in hospitals throughout the UK showed promise in aiding decisions regarding admission and predicting COVID-19 severity in patients with cancer presenting to hospital. Future work will validate and refine the tool in further datasets.

scholarly journals Video decision support tool promoting values conversations in advanced care planning in cancer: protocol of a randomised controlled trial

2021 ◽  
Vol 20 (1) ◽  
Author(s):  
Natasha Michael ◽  
Clare O’Callaghan ◽  
Ekavi Georgousopoulou ◽  
Adelaide Melia ◽  
Merlina Sulistio ◽  
...  
Keyword(s):  
Decision Making ◽  
Decision Support ◽  
Cancer Patients ◽  
Personal Values ◽  
Decision Support Tool ◽  
Trial Registration ◽  
Randomised Control Trial ◽  
Care Planning ◽  
Advanced Directives ◽  
Support Tool

Abstract Background Views on advance care planning (ACP) has shifted from a focus solely on treatment decisions at the end-of-life and medically orientated advanced directives to encouraging conversations on personal values and life goals, patient-caregiver communication and decision making, and family preparation. This study will evaluate the potential utility of a video decision support tool (VDST) that models values-based ACP discussions between cancer patients and their nominated caregivers to enable patients and families to achieve shared-decisions when completing ACP’s. Methods This open-label, parallel-arm, phase II randomised control trial will recruit cancer patient-caregiver dyads across a large health network. Previously used written vignettes will be converted to video vignettes using the recommended methodology. Participants will be ≥18 years and be able to complete questionnaires. Dyads will be randomised in a 1:1 ratio to a usual care (UC) or VDST group. The VDST group will watch a video of several patient-caregiver dyads communicating personal values across different cancer trajectory stages and will receive verbal and written ACP information. The UC group will receive verbal and written ACP information. Patient and caregiver data will be collected individually via an anonymous questionnaire developed for the study, pre and post the UC and VDST intervention. Our primary outcome will be ACP completion rates. Secondarily, we will compare patient-caregiver (i) attitudes towards ACP, (ii) congruence in communication, and (iii) preparation for decision-making. Conclusion We need to continue to explore innovative ways to engage cancer patients in ACP. This study will be the first VDST study to attempt to integrate values-based conversations into an ACP intervention. This pilot study’s findings will assist with further refinement of the VDST and planning for a future multisite study. Trial registration Australian New Zealand Clinical Trials Registry No: ACTRN12620001035910. Registered 12 October 2020. Retrospectively registered.

U-TEST, a simple decision support tool for the diagnosis of sarcopenia in orthopaedic patients: the Screening for People Suffering Sarcopenia in Orthopedic cohort of Kobe study (SPSS-OK)

2021 ◽  
pp. 1-8
Author(s):  
Tsukasa Kamitani ◽  
Takafumi Wakita ◽  
Osamu Wada ◽  
Kiyonori Mizuno ◽  
Noriaki Kurita
Keyword(s):  
Logistic Regression ◽  
Decision Support ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Decision Support Tool ◽  
Structured Interview ◽  
Internal Validation ◽  
Support Tool ◽  
Expert Opinions ◽  
Orthopaedic Patients

Abstract We aimed to develop and validate a new simple decision support tool (U-TEST) for diagnosis of sarcopenia in orthopaedic patients. We created seventeen candidate original questions to detect sarcopenia in orthopaedic patients with sarcopenia through expert opinions and a semi-structured interview. To derive a decision support tool, a logistic regression model with backward elimination was applied to select variables from the seventeen questions, age and underweight (BMI < 18·5 kg/m2). Sarcopenia was defined by Asian Working Group for Sarcopenia 2019 criteria. After assigning a score to each selected variable, the sum of scores was calculated. We evaluated the diagnostic performance of the new tool using a logistic regression model. A bootstrap technique was used for internal validation. Among a total of 1334 orthopaedic patients, sixty-five (4·9 %) patients were diagnosed with sarcopenia. We succeeded in developing a ‘U-TEST’ with scores ranging from 0 to 11 consisting of values for BMI (Underweight), age (Elderly) and two original questions (‘I can’t stand up from a chair without supporting myself with my arms’ (Strength) and ‘I feel that my arms and legs are thinner than they were in the past’ (Thin)). The AUC was 0·77 (95 % CI 0·71, 0·83). With the optimal cut-off set at 3 or greater based on Youden’s index, the sensitivity and the specificity were 76·1 and 63·6 %, respectively. In orthopaedic patients, our U-TEST scoring with two questions and two simple clinical variables can help to screen for sarcopenia.

scholarly journals Evaluation of a clinical decision support tool for matching cancer patients to clinical trials using simulation-based research

2021 ◽  
Author(s):  
Clarissa Judith Gardner ◽  
Jack Halligan ◽  
Gianluca Fontana ◽  
Roberto Fernandez Crespo ◽  
Matthew Stewart Prime ◽  
...  
Keyword(s):  
Clinical Trials ◽  
Decision Support ◽  
Cancer Patients ◽  
Clinical Decision Support ◽  
Digital Health ◽  
Decision Support Tool ◽  
Clinical Decision ◽  
Support Tool ◽  
Simulation Based ◽  
The Difference

Simulation-based research (SBR) methods have been proposed as an alternative methodology for evaluating digital health solutions; however, applicability remains to be established. This study used SBR to evaluate a clinical decision support (CDS) tool used for matching cancer patients to clinical trials. 25 clinicians and research staff were recruited to match 10 synthetic patient cases to clinical trials using both the CDS tool and publicly available online trial databases. Participants were significantly more likely to report having sufficient time (p = 0.020) and to require less mental effort (p = 0.001) to complete trial matching with the CDS tool. Participants required less time for trial matching using the CDS tool, but the difference was not significant (p = 0.093). Most participants reported that they had sufficient guidance to participate in the simulations (96%). This study demonstrates the use of SBR methods is a feasible approach to evaluating digital health solutions.

scholarly journals Artificial Intelligence Approach for Variant Reporting

2018 ◽  
pp. 1-13 ◽  
Author(s):  
Michael G. Zomnir ◽  
Lev Lipkin ◽  
Maciej Pacula ◽  
Enrique Dominguez Meneses ◽  
Allison MacLeay ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Logistic Regression ◽  
Decision Support ◽  
Next Generation Sequencing ◽  
Decision Support Tool ◽  
Bioinformatics Pipeline ◽  
Support Tool ◽  
Intelligence Approach ◽  
Artificial Intelligence Approach ◽  
Generation Sequencing

Purpose Next-generation sequencing technologies are actively applied in clinical oncology. Bioinformatics pipeline analysis is an integral part of this process; however, humans cannot yet realize the full potential of the highly complex pipeline output. As a result, the decision to include a variant in the final report during routine clinical sign-out remains challenging. Methods We used an artificial intelligence approach to capture the collective clinical sign-out experience of six board-certified molecular pathologists to build and validate a decision support tool for variant reporting. We extracted all reviewed and reported variants from our clinical database and tested several machine learning models. We used 10-fold cross-validation for our variant call prediction model, which derives a contiguous prediction score from 0 to 1 (no to yes) for clinical reporting. Results For each of the 19,594 initial training variants, our pipeline generates approximately 500 features, which results in a matrix of > 9 million data points. From a comparison of naive Bayes, decision trees, random forests, and logistic regression models, we selected models that allow human interpretability of the prediction score. The logistic regression model demonstrated 1% false negativity and 2% false positivity. The final models’ Youden indices were 0.87 and 0.77 for screening and confirmatory cutoffs, respectively. Retraining on a new assay and performance assessment in 16,123 independent variants validated our approach (Youden index, 0.93). We also derived individual pathologist-centric models (virtual consensus conference function), and a visual drill-down functionality allows assessment of how underlying features contributed to a particular score or decision branch for clinical implementation. Conclusion Our decision support tool for variant reporting is a practically relevant artificial intelligence approach to harness the next-generation sequencing bioinformatics pipeline output when the complexity of data interpretation exceeds human capabilities.

Sign in / Sign up

Export Citation Format

Share Document