Addressing Cancer Readmission Prediction Model Drift: A Case Study

The cancer readmission prediction model classifies patients as high-risk or low-risk for readmittance. Consequently, intervention strategies focus on high-risk patients. Nevertheless, the performance of machine learning models generally degrades over time due to changes in the environment that violates models' assumptions, which include statistical data changes and process changes. This research introduces a framework that improves the sensitivity of the cancer readmission prediction model by identifying new features of cancer readmission, such as Diabetes and Anti-Nausea, which potentially cause the model's sensitivity to drift. The proposed model considers these 20 new factors with the 35 original factors that use the most recent dataset to predict cancer readmissions. Recursive feature elimination was used to identify key features. Some of the most popular classification algorithms, which include logistic regression and adaptive boosting, were used to retrain and classify cancer readmissions. The best algorithm was validated on a new dataset that was collected over 11 months, which covered three different waves of Covid-19. The results suggested K-Nearest Neighbors (KNN) algorithm performs the best among all eight studied algorithms. The KNN model incorporated new dominant features that did not exist in the original Random Forest (RF) model. The KNN model has an improvement of 8.05% in sensitivity compared to the RF model. The presence of Covid-19 does not have a significant impact on the performance of the KNN model. The suggested framework identifies potential admitted patients for intervention actions, helps reduce cancer readmission rates, costs, and improves the quality of care for cancer patients. © 2022 IISE Annual Conference and Expo 2022. All rights reserved.

Running Community Solidarity and Well-Being Motivated by Instagram Multimodal Communications Under the COVID-19 Pandemic

This paper investigates how the city runners of a local running group maintain a sense of belonging and commitment to the running group and running exercises under the new abnormal living situations by the COVID-19 pandemic. A netnographic approach to study the running group’s Instagram posts and the members’ responses shows how community-based solidarity and interventions provide both intrinsic and extrinsic motivations to shape the members’ self-regulated behaviours and running practices by interactive and multimodal communications. Their self-regulated physical exercises and collective and connective activities help to promote community health and well-being when the formal community-based running exercises are suspended. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Diagnostic utility of additional whole-chest CT as part of an acute abdominal pain CT imaging pathway during the COVID-19 pandemic.

AIM: To evaluate the diagnostic utility of additional whole-chest computed tomography (CT) in identifying otherwise unheralded COVID-19 lung disease as part of an acute abdominal pain CT imaging pathway in response to the COVID-19 pandemic. MATERIALS AND METHODS: Consecutive patients (n=172) who underwent additional whole-chest CT via a COVID-19 acute abdominal pain CT imaging pathway between 27 March and 3 May 2020 were evaluated in this retrospective single-centre study. Chest CT examinations were graded as non-COVID-19, indeterminate for, or classic/probable for COVID-19. CT examinations in the latter two categories were further divided into one of three anatomical distributions (lung base, limited chest [below carina], whole chest [above carina]) based on location of findings. Reverse transcriptase-polymerase chain reaction (RT-PCR) results and clinical features of COVID-19 were assessed to determine if COVID-19 was clinically suspected at the time of CT referral. RESULTS: Twenty-seven of the 172 (15.7%) patients had CT features potentially indicative of COVID-19 pneumonia, 6/27 (3.5%) demonstrating a classic/probable pattern and 21/27 (12.2%) demonstrating an indeterminate pattern. After correlation with clinical features and RT-PCR 8/172 (4.7%) were defined as COVID-19 positive, of which only 1/172 (0.6%) was clinically unsuspected of COVID-19 at the time of CT referral. All COVID-19 positive cases could be identified on review of the lung base alone. CONCLUSION: Whole-chest CT as part of an acute abdominal pain CT imaging pathway has a very low diagnostic yield for our cohort of patients. All COVID-19-positive patients in our cohort were identified on review of the lung bases on the abdominal CT and this offers an alternative imaging approach in this patient group.