PURPOSE: The purpose of this study was to evaluate the use of telemedicine amid the SARS-CoV-2 pandemic in patients with cancer and assess barriers to its implementation. PATIENTS AND METHODS: Telehealth video visits, using the Houston Methodist MyChart platform, were offered to patients with cancer as an alternative to in-person visits. Reasons given by patients who declined to use video visits were documented, and demographic information was collected from all patients. Surveys were used to assess the levels of satisfaction of treating physicians and patients who agreed to video visits. RESULTS: Of 1,762 patients with cancer who were offered telehealth video visits, 1,477 (83.8%) participated. The patients who declined participation were older (67.7 v 60.2 years; P < .0001), lived in significantly lower-income areas ( P = .0021), and were less likely to have commercial insurance ( P < .0001) than patients who participated. Most participating patients (92.6%) were satisfied with telehealth video visits. A majority of physicians (65.2%) were also satisfied with its use, and 74% indicated that they would likely use telemedicine in the future. Primary concerns that physicians had in using this technology were inadequate patient interactions and acquisition of medical data, increased potential for missing significant clinical findings, decreased quality of care, and potential medical liability. CONCLUSION: Oncology/hematology patients and their physicians expressed high levels of satisfaction with the use of telehealth video visits. Despite recent advances in technology, there are still opportunities to improve the equal implementation of telemedicine for the medical care of vulnerable older, low-income, and underinsured patient populations.

PURPOSE: The Breast Imaging Reporting and Data System (BI-RADS) lexicon was developed to standardize mammographic reporting to assess cancer risk and facilitate the decision to biopsy. Because of substantial interobserver variability in the application of the BI-RADS lexicon, the decision to biopsy varies greatly and results in overdiagnosis and excessive biopsies. The false-positive rate from mammograms is estimated to be 7% to approximately 10% overall, but within the BI-RADS 4 category, it is greater than 70%. Therefore, we developed the Breast Cancer Risk Calculator (BRISK) to target a well-characterized and specific patient subgroup (BI-RADS 4) rather than a broad heterogeneous group in assessing breast cancer risk.METHODS: BRISK provides a novel precise risk assessment model to reduce overdiagnosis and unnecessary biopsies. It was developed by applying natural language processing and deep learning methods on 5,147 patient records archived in the Houston Methodist systemwide data warehouse from 2006 to May 2015, including imaging and pathology reports, mammographic images, and patient demographics. Key characteristics for BI-RADS 4 patients were collected and computed to output an index measure for biopsy recommendation that is clinically relevant and informative and improves upon the traditional BI-RADS 4 scores.RESULTS: For the validation set, we assessed data from 1,247 BI-RADS 4 patients, including mammographic images and medical reports. The BRISK model sensitivity to predict malignancy was 100%, whereas the specificity was 74%. The total accuracy of our implemented model in BRISK was 81%. Overall area under the curve was 0.93.CONCLUSION: BRISK for abnormal mammogram uses integrative artificial intelligence technology and has demonstrated high sensitivity in the prediction of malignancy. Prospective evaluation is under way and can lead to improvement in patient-physician engagement in making informed decisions with regard to biopsy.

Purpose: Only 34% of breast cancer survivors engage in the recommended level of physical activity because of a lack of accountability and motivation. Methodist Hospital Cancer Health Application (MOCHA) is a smartphone tool created specifically for self-reinforcement for patients with cancer through the daily accounting of activity and nutrition and direct interaction with clinical dietitians. We hypothesize that use of MOCHA will improve the accountability of breast cancer survivors and help them reach their personalized goals. Patients and Methods: Women with stages I to III breast cancer who were at least 6 months post–active treatment with a body mass index (BMI) greater than 25 kg/m² were enrolled in a 4-week feasibility trial. The primary objective was to demonstrate adherence during weeks 2 and 3 of the 4-week study period (14 days total). The secondary objective was to determine the usability of MOCHA according to the system usability scale. The exploratory objective was to determine weight loss and dietitian-participant interaction. Results: We enrolled 33 breast cancer survivors who had an average BMI of 31.6 kg/m². Twenty-five survivors completed the study, and the average number of daily uses was approximately 3.5 (range, 0 to 12) times/day; participants lost an average of 2 lbs (+4 lbs to −10.6 lbs). The average score of usability (the second objective) was 77.4, which was greater than the acceptable level. More than 90% of patients found MOCHA easy to navigate, and 84% were motivated to use MOCHA daily. Conclusion: This study emphasizes the importance of technology use to improve goal adherence for patients by providing real-time feedback and accountability with the health care team. MOCHA focuses on the engagement of the health care team and is integrated into clinical workflow. Future directions will use MOCHA in a long-term behavior modification study.

Breast cancer is a pervasive global health concern among women. Leveraging multimodal data from enterprise patient databases-including Picture Archiving and Communication Systems (PACS) and Electronic Health Records (EHRs)-holds promise for improving prediction. This study introduces a multimodal deep-learning model leveraging mammogram datasets to evaluate breast cancer prediction. Our approach integrates frozen large-scale pretrained vision-language models, showcasing superior performance and stability compared to traditional image-tabular models across two public breast cancer datasets. The model consistently outperforms conventional full fine-tuning methods by using frozen pretrained vision-language models alongside a lightweight trainable classifier. The observed improvements are significant. In the CBIS-DDSM dataset, the Area Under the Curve (AUC) increases from 0.867 to 0.902 during validation and from 0.803 to 0.830 for the official test set. Within the EMBED dataset, AUC improves from 0.780 to 0.805 during validation. In scenarios with limited data, using Breast Imaging-Reporting and Data System category three (BI-RADS 3) cases, AUC improves from 0.91 to 0.96 on the official CBIS-DDSM test set and from 0.79 to 0.83 on a challenging validation set. This study underscores the benefits of vision-language models in jointly training diverse image-clinical datasets from multiple healthcare institutions, effectively addressing challenges related to non-aligned tabular features. Combining training data enhances breast cancer prediction on the EMBED dataset, outperforming all other experiments. In summary, our research emphasizes the efficacy of frozen large-scale pretrained vision-language models in multimodal breast cancer prediction, offering superior performance and stability over conventional methods, reinforcing their potential for breast cancer prediction.

This paper presents a novel Lasso Logistic Regression model based on feature-based time series data to determine disease severity and when to administer drugs or escalate intervention procedures in patients with coronavirus disease 2019 (COVID-19). Advanced features were extracted from highly enriched and time series vital sign data of hospitalized COVID-19 patients, including oxygen saturation readings, and with a combination of patient demographic and comorbidity information, as inputs into the dynamic feature-based classification model. Such dynamic combinations brought deep insights to guide clinical decision-making of complex COVID-19 cases, including prognosis prediction, timing of drug administration, admission to intensive care units, and application of intervention procedures like ventilation and intubation. The COVID-19 patient classification model was developed utilizing 900 hospitalized COVID-19 patients in a leading multi-hospital system in Texas, United States. By providing mortality prediction based on time-series physiologic data, demographics, and clinical records of individual COVID-19 patients, the dynamic feature-based classification model can be used to improve efficacy of the COVID-19 patient treatment, prioritize medical resources, and reduce casualties. The uniqueness of our model is that it is based on just the first 24 hours of vital sign data such that clinical interventions can be decided early and applied effectively. Such a strategy could be extended to prioritize resource allocations and drug treatment for futurepandemic events.