Development and application of a weighted change score to evaluate interventions for vasomotor symptoms in patients with breast cancer using regression trees: a cohort study.

PURPOSE: Vasomotor symptoms (VMS) are common among individuals with breast cancer (BC) and poorly managed symptoms are associated with reduced quality of life, treatment discontinuation, and poorer breast cancer outcomes. Direct comparisons among therapies are limited, as prior studies evaluating VMS interventions have utilized heterogeneous change measures which may not fully assess the perceived impact of change in VMS severity. METHODS: We performed a prospective study where BC patients chose one of four categories of interventions to manage VMS. Change in VMS severity at 6 weeks was assessed using the validated Hot Flush Rating Scale (HFRS). A novel weighted change score integrating baseline symptom severity and directionality of change was computed to maximize the correlation between the change score and a perceived treatment effectiveness score. Variables influencing change in VMS severity were included in a regression tree to model factors influencing the weighted change score. RESULTS: 100 baseline and follow-up questionnaires assessing VMS were completed by 88 patients. Correlations between treatment effectiveness and VMS outcomes strengthened following adjustment for baseline symptoms. Patients with low VMS severity at baseline did not perceive change in treatment effectiveness. Intervention category was predictive of change in HFRS at 6 weeks. CONCLUSION: Baseline symptom severity and the directionality of change (improvement or deterioration of symptoms) influenced the perception of clinically meaningful change in VMS severity. Future interventional studies utilizing the weighted change score should target moderate-high baseline severity patients.

Role of sex and gender-related variables in development of metabolic syndrome: A prospective cohort study.

INTRODUCTION: The burden of metabolic syndrome (MetS) and its components has been increasing mainly amongst male individuals. Nevertheless, clinical outcomes related to MetS (i.e., cardiovascular diseases), are worse among female individuals. Whether these sex differences in the components and sequalae of MetS are influenced by gender (i.e., psycho-socio-cultural factors)) is a matter of debate.  Therefore, the purpose of this study was to determine the association between gender-related factors and the development of MetS, and to assess if the magnitude of the associations vary by sex. METHOD: Data from the Colaus/PsyColaus study, a prospective population-based cohort of 6,734 middle-aged participants in Lausanne (Switzerland) (2003-2006) were used. The primary endpoint was the development of MetS as defined by the Adult Treatment Panel III of the National Cholesterol Education Program. Multivariable models were estimated using logistic regression to assess the association between gender-related factors and the development of MetS. Two-way interactions between sex,  age and gender-related factors were also tested. RESULTS: Among 5,195 participants without MetS (mean age=51.3 ± 10.6, 56.1 % females), 27.9 % developed MetS during a mean follow-up of 10.9 years. Female sex (OR:0.48, 95 %CI:0.41-0.55) was associated with decreased risk of developing MetS. Conversely, older age, educational attainment less than university, and low income were associated with an increased risk of developing MetS. Statistically significant interaction between sex and strata of age, education, income, smoking, and employment were identified showing that the reduced risk of MetS in female individuals was attenuated in the lowest education, income, and advanced age strata. However, females who smoke and reported being employed demonstrated a decreased risk of MetS compared to males. Conversely smoking and unemployment were significant risk factors for MetS development among male adults. CONCLUSIONS: Gender-related factors such as income level and educational attainment play a greater role in the development of MetS in female than individuals. These factors represent novel modifiable targets for implementation of sex- and gender-specific strategies to achieve health equity for all people.

Using machine learning to predict individual patient toxicities from cancer treatments.

PURPOSE: Machine learning (ML) is a powerful tool for interrogating datasets and learning relationships between multiple variables. We utilized a ML model to identify those early breast cancer (EBC) patients at highest risk of developing severe vasomotor symptoms (VMS). METHODS: A gradient boosted decision model utilizing cross-sectional survey data from 360 EBC patients was created. Seventeen patient- and treatment-specific variables were considered in the model. The outcome variable was based on the Hot Flush Night Sweats (HFNS) Problem Rating Score, and individual scores were dichotomized around the median to indicate individuals with high and low problem scores. Model accuracy was assessed using the area under the receiver operating curve, and conditional partial dependence plots were constructed to illustrate relationships between variables and the outcome of interest. RESULTS: The model area under the ROC curve was 0.731 (SD 0.074). The most important variables in the model were as follows: the number of hot flashes per week, age, the prescription, or use of drug interventions to manage VMS, whether patients were asked about VMS in routine follow-up visits, and the presence or absence of changes to breast cancer treatments due to VMS. A threshold of 17 hot flashes per week was identified as being more predictive of severe VMS. Patients between the ages of 49 and 63 were more likely to report severe symptoms. CONCLUSION: Machine learning is a unique tool for predicting severe VMS. The use of ML to assess other treatment-related toxicities and their management requires further study.

Vasomotor symptoms in early breast cancer-a "real world" exploration of the patient experience.

BACKGROUND: Despite the frequency of vasomotor symptoms (VMS) in patients with early breast cancer (EBC), their optimal management remains unknown. A patient survey was performed to determine perspectives on this important clinical challenge. METHODS: Patients with EBC experiencing VMS participated in an anonymous survey. Patients reported on the frequency and severity of VMS using the validated Hot Flush Rating Scale (HFRS) and ranked their most bothersome symptoms. Respondents were also asked to determine endpoints that defined effective treatment of VMS and report on the effectiveness of previously tried interventions. RESULTS: Responses were received from 373 patients, median age 56 years (range 23-83), who experienced an average of 5.0 hot flashes per day (SD 6.57). Patients reported the most bothersome symptoms to be feeling hot/sweating (155/316, 49%) and sleeping difficulties (86/316, 27%). Fifty-five percent (201/365) of patients would consider a treatment to be effective if it reduced night-time awakenings. While 68% of respondents were interested in trying interventions from their healthcare team to manage VMS, only 18% actually did so. Of the 137 patients who had tried an intervention for VMS, pharmacological treatments, exercise, and relaxation strategies were more likely to be effective, while therapies such as melatonin and black cohosh were deemed less effective. CONCLUSION: VMS are a common and bothersome problem for EBC patients, with a minority receiving interventions to manage these symptoms. Further research is needed to identify patient-centered strategies for managing these distressing symptoms.

Sex, Gender, and Cardiovascular Health in Canadian and Austrian Populations.

BACKGROUND: Evidence differentiating the effect of biological sex from psychosociocultural factors (gender) in different societies and its relation to cardiovascular diseases is scarce. We explored the association between sex, gender, and cardiovascular health (CVH) among Canadian (CAN) and Austrian (AT) populations. METHODS: The Canadian Community Health Survey (CCHS) (n = 63,522; 55% female) and Austrian Health Interview Survey (AT-HIS) (n = 15,771; 56% female) were analyzed in a cross-sectional survey design. The CANHEART/ATHEART index, a measure of ideal CVH composed of 6 cardiometabolic risk factors (smoking, physical activity, fruit and vegetable consumption, overweight/obesity, diabetes, and hypertension; range 0-6; higher scores reflecting better CVH) was calculated for both databases. A composite measure of psychosociocultural gender was computed for each country (range 0-1, higher score identifying characteristics traditionally ascribed to women). RESULTS: Median CANHEART 4 (interquartile range 3-5) and CAN gender scores 0.55 (0.49-0.60) were similar to median ATHEART 4 (3-5) and AT gender scores 0.55 (0.46-0.64). Although higher gender scores (CCHS: ß = -1.33, 95% confidence interval [CI] -1.44 to -1.22; AT-HIS: ß = -1.08, 95% CI -1.26 to -0.89)) were associated with worse CVH, female sex (CCHS: ß = 0.35, 95% CI (0.33-0.37); AT-HIS: ß = 0.60, 95% CI (0.55-0.64)) was associated with better CVH in both populations. In addition, higher gender scores were associated with increased prevalence of heart disease compared with female sex. The magnitude of this risk was higher in Austrians. CONCLUSIONS: These results demonstrate that individuals with characteristics typically ascribed to women reported poorer cardiovascular health and higher risk of heart disease, independently from biological sex and baseline CV risk factors, in both countries. Female sex exhibited better CV health and a lower prevalence of heart disease than male in both populations. However, gender factors and magnitude of gender impact varied by country.

Optimizing the synthesis of clinical trial data using sequential trees.

OBJECTIVE: With the growing demand for sharing clinical trial data, scalable methods to enable privacy protective access to high-utility data are needed. Data synthesis is one such method. Sequential trees are commonly used to synthesize health data. It is hypothesized that the utility of the generated data is dependent on the variable order. No assessments of the impact of variable order on synthesized clinical trial data have been performed thus far. Through simulation, we aim to evaluate the variability in the utility of synthetic clinical trial data as variable order is randomly shuffled and implement an optimization algorithm to find a good order if variability is too high. MATERIALS AND METHODS: Six oncology clinical trial datasets were evaluated in a simulation. Three utility metrics were computed comparing real and synthetic data: univariate similarity, similarity in multivariate prediction accuracy, and a distinguishability metric. Particle swarm was implemented to optimize variable order, and was compared with a curriculum learning approach to ordering variables. RESULTS: As the number of variables in a clinical trial dataset increases, there is a pattern of a marked increase in variability of data utility with order. Particle swarm with a distinguishability hinge loss ensured adequate utility across all 6 datasets. The hinge threshold was selected to avoid overfitting which can create a privacy problem. This was superior to curriculum learning in terms of utility. CONCLUSIONS: The optimization approach presented in this study gives a reliable way to synthesize high-utility clinical trial datasets.

Geospatial cryptography: enabling researchers to access private, spatially referenced, human subjects data for cancer control and prevention.

As the volume, accuracy and precision of digital geographic information have increased, concerns regarding individual privacy and confidentiality have come to the forefront. Not only do these challenge a basic tenet underlying the advancement of science by posing substantial obstacles to the sharing of data to validate research results, but they are obstacles to conducting certain research projects in the first place. Geospatial cryptography involves the specification, design, implementation and application of cryptographic techniques to address privacy, confidentiality and security concerns for geographically referenced data. This article defines geospatial cryptography and demonstrates its application in cancer control and surveillance. Four use cases are considered: (1) national-level de-duplication among state or province-based cancer registries; (2) sharing of confidential data across cancer registries to support case aggregation across administrative geographies; (3) secure data linkage; and (4) cancer cluster investigation and surveillance. A secure multi-party system for geospatial cryptography is developed. Solutions under geospatial cryptography are presented and computation time is calculated. As services provided by cancer registries to the research community, de-duplication, case aggregation across administrative geographies and secure data linkage are often time-consuming and in some instances precluded by confidentiality and security concerns. Geospatial cryptography provides secure solutions that hold significant promise for addressing these concerns and for accelerating the pace of research with human subjects data residing in our nation's cancer registries. Pursuit of the research directions posed herein conceivably would lead to a geospatially encrypted geographic information system (GEGIS) designed specifically to promote the sharing and spatial analysis of confidential data. Geospatial cryptography holds substantial promise for accelerating the pace of research with spatially referenced human subjects data.

Evaluating the Risk of Re-identification of Patients from Hospital Prescription Records.

BACKGROUND: Pharmacies often provide prescription records to private research firms, on the assumption that these records are de-identified (i.e., identifying information has been removed). However, concerns have been expressed about the potential that patients can be re-identified from such records. Recently, a large private research firm requested prescription records from the Children's Hospital of Eastern Ontario (CHEO), as part of a larger effort to develop a database of hospital prescription records across Canada. OBJECTIVE: To evaluate the ability to re-identify patients from CHEO'S prescription records and to determine ways to appropriately de-identify the data if the risk was too high. METHODS: The risk of re-identification was assessed for 18 months' worth of prescription data. De-identification algorithms were developed to reduce the risk to an acceptable level while maintaining the quality of the data. RESULTS: The probability of patients being re-identified from the original variables and data set requested by the private research firm was deemed quite high. A new de-identified record layout was developed, which had an acceptable level of re-identification risk. The new approach involved replacing the admission and discharge dates with the quarter and year of admission and the length of stay in days, reporting the patient's age in weeks, and including only the first character of the patient's postal code. Additional requirements were included in the data-sharing agreement with the private research firm (e.g., audit requirements and a protocol for notification of a breach of privacy). CONCLUSIONS: Without a formal analysis of the risk of re-identification, assurances of data anonymity may not be accurate. A formal risk analysis at one hospital produced a clinically relevant data set that also protects patient privacy and allows the hospital pharmacy to explicitly manage the risks of breach of patient privacy.