Machine learning and patient-reported outcomes for longitudinal monitoring of disease progression in metastatic breast cancer: a multicenter, retrospective analysis.

BACKGROUND: Assessments of health-related quality of life (HRQoL) play an important role in transition to palliative care for women with metastatic breast cancer. We developed machine learning (ML) algorithms to analyse longitudinal HRQoL data and identify patients who may benefit from palliative care due to disease progression. METHODS: We recruited patients from two institutions and administered the EuroQoL Visual Analog Scale (EQ-VAS) via an online platform over a 6-month period. We trained a regularised regression algorithm using 10-fold cross-validation to determine if a patient was at high or low risk of disease progression based on changes in the EQ-VAS scores using data of one institution and validated the performance on data of the other institution. Progression-free survival (PFS) was the end-point. We conducted Kaplan-Meier and Cox regression analysis adjusted for clinical risk factors. RESULTS: Of 179 patients, 98 (54.7%) had progressive disease after a median follow-up of 14weeks. Using EQ-VAS scores collected at weeks 1-6 to predict disease progression at week 12, in the validation set (n = 63), PFS was significantly lower in the intelligent EQ-VAS high-risk versus low-risk group: median PFS 7 versus 10weeks, log-rank P < 0.038). Intelligent EQ-VAS had the strongest association with PFS (adjusted hazard ratio 2.69, 95% confidence interval 1.17-6.18, P = 0.02). CONCLUSION: ML algorithms can analyse changes in longitudinal HRQoL data to identify patients with disease progression earlier than standard follow-up methods. Intelligent EQ-VAS scores were identified as independent prognostic factor. Future studies may validate these results to remotely monitor patients.

Implementation of an Electronic Patient-Reported Outcome App for Health-Related Quality of Life in Breast Cancer Patients: Evaluation and Acceptability Analysis in a Two-Center Prospective Trial.

BACKGROUND: One in eight women is diagnosed with breast cancer in the course of their life. As systematic palliative treatment has only a limited effect on survival rates, the concept of health-related quality of life (HRQoL) was developed for measurement of patient-centered outcomes. Various studies have already demonstrated the reliability of paper-based patient-reported outcome (pPRO) and electronic patient-reported outcome (ePRO) surveys and that the 2 means of assessment are equally valid. OBJECTIVE: The aim of this study was to analyze the acceptance and evaluation of a tablet-based ePRO app for breast cancer patients and to examine its suitability, effort, and difficulty in the context of HRQoL and sociodemographic factors. METHODS: Overall, 106 women with adjuvant or advanced breast cancer were included in a 2-center study at 2 major university hospitals in Germany. Patients were asked to answer HRQoL and PRO questionnaires both on a tablet on-site using a specific eHealth assessment website and on paper. The suitability, effort, and difficulty of the app and self-reported technical skills were also assessed. Only the results of the electronically acquired data are presented here. The results of the reliability of the pPRO data have already been published elsewhere. RESULTS: Patients regarded the ePRO assessment as more suitable (80/106, 75.5%), less stressful (73/106, 68.9%), and less difficult (69/106, 65.1%) than pPRO. The majority of patients stated that ePRO assessment improves health care in hospitals (87/106, 82.1%). However, evaluation of ePROs depended on the level of education (P=.003) in the dimensions of effort and difficulty (regression analysis). The app was rated highly in all categories. HRQoL data and therapy setting did not show significant correlations with the app's evaluation parameters. CONCLUSIONS: The results indicate that ePRO surveys are feasible for measuring HRQoL in breast cancer patients and that those patients prefer ePRO assessment to pPRO assessment. It can also be seen that patients consider ePRO assessment to improve hospital health care. However, studies with larger numbers of patients are needed to develop apps that address the needs of patients with lower levels of education and technical skills.

Evaluation of Repeated Web-Based Screening for Predicting Postpartum Depression: Prospective Cohort Study.

BACKGROUND: Postpartum depression (PPD) is a severe mental disorder that often results in poor maternal-infant attachment and negatively impacts infant development. Universal screening has recently been recommended to identify women at risk, but the optimal screening time during pregnancy has not been defined so far. Thus, web-based technologies with widespread use among women of childbearing age create new opportunities to detect pregnancies with a high risk for adverse mental health outcomes at an early stage. OBJECTIVE: The aim of this study was to stratify the risk for PPD and to determine the optimal screening time during pregnancy by using a web-based screening tool collecting electronic patient-reported outcomes (ePROs) as the basis for a screening algorithm. METHODS: In total, 214 women were repeatedly tested for depressive symptoms 5 times during and 3 times after pregnancy by using the Edinburgh Postnatal Depression Scale (EPDS), accessible on a web-based pregnancy platform, developed by the authors of this study. For each prenatal assessment, the area under the curve (AUC), sensitivity, specificity, and predictive values for PPD were calculated. Multivariate logistic regression analyses were applied to identify further potential predictors, such as age, education, parity, relationship quality, and anxiety, to increase predictive accuracy. RESULTS: Digitally collected data from 214 pregnant women were analyzed. The predictive accuracy of depressive symptoms 3 and 6 months postpartum was reasonable to good regarding the screening in the second (AUC=0.85) and third (AUC=0.75) trimester. The multivariate logistic regression analyses resulted in an excellent AUC of 0.93 at 3 months and a good AUC of 0.87 at 6 months postpartum. CONCLUSIONS: The best predictive accuracy for PPD has been shown for screening between the 24th and the 28th gestational week (GW) and seems to be beneficial for identifying women at risk. In combination with the aforementioned predictive factors, the discriminatory power improved, particularly at 3 months postpartum. Screening for depression during pregnancy, combined with the women's personal risk profile, can be used as a starting point for developing a digital screening algorithm. Thereby, web-based assessment tools constitute feasible, efficient, and cost-effective approaches. Thus, they seem to be beneficial in detecting high-risk pregnancies in order to improve maternal and infant birth outcomes in the long term.

Measuring the Time to Deterioration for Health-Related Quality of Life in Patients With Metastatic Breast Cancer Using a Web-Based Monitoring Application: Longitudinal Cohort Study.

BACKGROUND: Health-related quality of life (HRQoL) is used to evaluate the treatment of metastatic breast cancer. In a long-term therapy setting, HRQoL can be used as an important benchmark for treatment success. With the help of digital apps, HRQoL monitoring can be extended to more remote areas and be administered on a more frequent basis. OBJECTIVE: This study aims to evaluate 3 common HRQoL questionnaires in metastasized breast cancer in terms of TTD in a digital, web-based setting. We further aim to examine the development of the HRQoL in different systemic treatment groups in each of these evaluation instruments. METHODS: A total of 192 patients with metastatic breast cancer were analyzed in this bicentric prospective online cohort study at two German university hospitals. Patients completed questionnaires on HRQoL (EuroQol Visual Analog Scale [EQ-VAS], EuroQol 5 Dimension 5 Level [EQ-5D-5L], European Organization for Research and Treatment of Cancer Quality of Life Questionnaire-Core 30 item [EORTC QLQ-C30]) via an online platform over a 6-month period. Treatment schedules and medical history were retrieved from medical records. Unadjusted Cox regression analysis on treatment-related factors was performed. We conducted subgroup analyses in regard to TTD events between different treatments. RESULTS: The EQ-VAS showed a higher rate of deterioration after 8 weeks (84/179, 46.9%) than the EQ-5D-5L (47/163, 28.8%) and EORTC QLQ-C30 (65/176, 36.9%). Unadjusted Cox regression revealed significant connections between known metastases in the liver (P=.03, HR 1.64, 95% CI 1.06-2.52) and pleura (P=.04, HR 0.42, 95% CI 0.18-0.96) in the EQ-VAS. Significant relations between EQ-VAS events and single EQ-5D-5L items and the EQ-5D-5L summary score were demonstrated. All treatment groups significantly differed from the CDK4/6 inhibition subgroup in the EQ-VAS. CONCLUSIONS: Compared to the EQ-5D-5L and QLQ-C30, the EQ-VAS showed a higher rate of deterioration after 8 weeks. Significant connections to certain metastatic locations were only detected in the EQ-VAS. The EQ-VAS is capable of reflecting the distinctive HRQoL profiles of different systemic treatments as well as the different aspects of HRQoL presented in the EQ-5D-5L. TTD with the EQ-VAS is an adequate mean of examining longitudinal development of HRQoL among breast cancer patients.

Challenges in Acceptance and Compliance in Digital Health Assessments During Pregnancy: Prospective Cohort Study.

BACKGROUND: Pregnant women are increasingly using mobile apps to access health information during the antenatal period. Therefore, digital health solutions can potentially be used as monitoring instruments during pregnancy. However, a main factor of success is high user engagement. OBJECTIVE: The aim of this study was to analyze engagement and factors influencing compliance in a longitudinal study targeting pregnant women using a digital health app with self-tracking. METHODS: Digitally collected data concerning demographics, medical history, technical aspects, and mental health from 585 pregnant women were analyzed. Patients filling out ≥80% of items at every study visit were considered to be highly compliant. Factors associated with high compliance were identified using logistic regression. The effect of a change in mental and physical well-being on compliance was assessed using a one-sample t test. RESULTS: Only 25% of patients could be considered compliant. Overall, 63% left at least one visit blank. Influential variables for higher engagement included higher education, higher income, private health insurance, nonsmoking, and German origin. There was no relationship between a change in the number of physical complaints or depressive symptoms and study dropout. CONCLUSIONS: Maintaining high engagement with digital monitoring devices over a long time remains challenging. As cultural and socioeconomic background factors had the strongest influence, more effort needs to be directed toward understanding the needs of patients from different demographic backgrounds to ensure high-quality care for all patients. More studies need to report on compliance to disclose potential demographic bias.

Reduction in physical activity significantly increases depression and anxiety in the perinatal period: a longitudinal study based on a self-report digital assessment tool.

PURPOSE: Physical activity can reduce pregnancy-related complications and contributes substantially to improving maternal mental health. A reduction in activity encompassing exercise and daily household tasks throughout the course of pregnancy increases the risk of depression and anxiety. The following research examines the longitudinal interaction between exercise, general physical activity, and mental health outcomes in pregnant women. METHODS: This prospective longitudinal study was conducted at the maternity departments of two major university hospitals in Germany. Self-reported data of 597 women were digitally assessed every 4 weeks from the second trimester until birth as well as 3 and 6 months postnatally. Depressive and anxiety symptoms were assessed using the EPDS, PRAQ, and STAI and physical activity levels were measured using the PPAQ questionnaire. Cross-sectional and longitudinal analyses using Pearson's correlation coefficient and multiple regression models were conducted. RESULTS: We found a significant reduction in general physical activity in the period from the 20th to 32nd gestational week. Women who reported a greater decline during pregnancy showed significantly higher depression and anxiety scores. In stratified analyses, only baseline mental health scores proved to be variables with stronger impact on postnatal depression and anxiety outcomes. CONCLUSION: General physical activity and maternal mental health significantly influence each other during and after pregnancy. Both physical activity and the prevention of perinatal mental disorders should be systematically encouraged during perinatal care to prevent adverse maternal and fetal birth outcomes.