Gray, Tamryn F.

Abstract Objective Electronic health record documentation by intensive care unit (ICU) clinicians may predict patient outcomes. However, it is unclear whether physician and nursing notes differ in their ability to predict short-term ICU prognosis. We aimed to investigate and compare the ability of physician and nursing notes, written in the first 48 hours of admission, to predict ICU length of stay and mortality using 3 analytical methods. Materials and Methods This was a retrospective cohort study with split sampling for model training and testing. We included patients ≥18 years of age admitted to the ICU at Beth Israel Deaconess Medical Center in Boston, Massachusetts, from 2008 to 2012. Physician or nursing notes generated within the first 48 hours of admission were used with standard machine learning methods to predict outcomes. Results For the primary outcome of composite score of ICU length of stay ≥7 days or in-hospital mortality, the gradient boosting model had better performance than the logistic regression and random forest models. Nursing and physician notes achieved area under the curves (AUCs) of 0.826 and 0.796, respectively, with even better predictive power when combined (AUC, 0.839). Discussion Models using only nursing notes more accurately predicted short-term prognosis than did models using only physician notes, but in combination, the models achieved the greatest accuracy in prediction. Conclusions Our findings demonstrate that statistical models derived from text analysis in the first 48 hours of ICU admission can predict patient outcomes. Physicians’ and nurses’ notes are both uniquely important in mortality prediction and combining these notes can produce a better predictive model.

Abstract BackgroundCancer diagnosis and early treatment may have wide-ranging consequences for a woman’spartner (ie. spouse or significant other). In general, younger caregivers have been found to havegreater unmet needs and higher levels of distress compared to those who are older. To date,there is little known about the unmet needs and experiences of partners who care for youngwomen with breast cancer during active treatment.Trial Design: Cross-sectional survey of partners of young women with breast cancer.Eligibility Criteria: The current analysis focuses on a subset of respondent partners of womenwith breast cancer participating in the Young Womens Breast Cancer Study (NCT01468246)who met the following criteria: diagnosed at age < 40 years; time since diagnosis <12 months;and/or Stage IV disease (at diagnosis or in metastatic setting); and/or local recurrent disease< 12 months.Specific Aims: To explore the experience of partners of women in active treatment or havingvery recently completed treatment for breast cancer.Statistical Methods: We employed descriptive statistics to present sample characteristics,including means or medians for continuous variables and proportions for categorical variables.We assessed partners’ responses re: sociodemographics, perceived social support (MOS-Social Support Survey, Cancer Perceived Agents of Social Support), quality of life (QOL)(Caregiver QOL Index-Cancer), coping (Brief COPE), perceived financial security, perceivedparenting concerns (Parenting Concerns Questionnaire), anxiety and depression symptoms(Hospital Anxiety and Depression Scale), sexual satisfaction (Global Measure of SexualSatisfaction), posttraumatic growth (Posttraumatic Growth Inventory-Short Form), and an open-ended question to explore their experiences and needs.Accrual: 25 participants were included.Results: All partners were male (25/25; 100%), and most were white (n=23/25; 92%), workingfull-time (n=21/25; 91%); and college educated (n=19/25; 86%). Eighteen partners (n=18/25;72%) were parenting children <18 years old and 40% (n=10/25) were partnered with womenwith Stage 4 breast cancer. At the time of the survey, the median age of partners was 44 years(range, 28-69) and of patients was 38 years (range, 25-40). Many partners (57%) reportedsymptoms of anxiety (>8 on the HADS anxiety subscale), fewer (22%) were categorized ashaving symptoms of depression (>8 on the HADS depression subscale). Additionally, 39%reported not being sexually active; 41% reported maladaptive coping; 30% reported financialstrain;30% reported relationship strain. Reported caregiver QOL ranged from 22-116, with amean score of 52.5 (SD, 23.9), similar to population norms, with higher scores indicating lowerquality of life. Parenting concerns scores were generally low indicating less concern, with arange of 12-35, and mean of 20.5 (SD, 7.6). Post-traumatic growth ranged from 4-33, with amean score of 20.7 (SD, 7.4), with higher scores indicating greater personal growthexperienced. 44% (11/25) responded to the open-ended experiences and needs question.Common responses included feeling a lack of support, need for tailored and titrated information,and desire to connect with other men who faced similar experiences. Partners also reportedtheir struggles with uncertainty about the future. Discussion: A subset of partners of young women in active treatment for breast cancerexpressed concerns related to relationship strain, sexuality, need for support, and finances.Future work designed to meet the needs of partners of breast cancer patients includinginformational and psychosocial supports may benefit them and the patients as they manage theprocess of ongoing treatment and challenges about the future. Citation Format: Tamryn F Gray, Nancy Borstelmann, Shoshana Rosenberg, Shari Gelber, Meghan E Meyer, Kathryn J. Ruddy, Lidia Schapira, Steven Come, Virginia Borges, Tamara Cadet, Peter Maramaldi, Ann H. Partridge. The psychosocial impact of caregiving on partners of young women with breast cancer in treatment [abstract]. In: Proceedings of the 2020 San Antonio Breast Cancer Virtual Symposium; 2020 Dec 8-11; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2021;81(4 Suppl):Abstract nr PS9-08.