Cardiovascular health assessment in routine cancer follow-up in community settings: survivor risk awareness and perspectives.

BACKGROUND: Guidelines recommend cardiovascular risk assessment and counseling for cancer survivors. For effective implementation, it is critical to understand survivor cardiovascular health (CVH) profiles and perspectives in community settings. We aimed to (1) Assess survivor CVH profiles, (2) compare self-reported and EHR-based categorization of CVH factors, and (3) describe perceptions regarding addressing CVH during oncology encounters. METHODS: This cross-sectional analysis utilized data from an ongoing NCI Community Oncology Research Program trial of an EHR heart health tool for cancer survivors (WF-1804CD). Survivors presenting for routine care after potentially curative treatment recruited from 8 oncology practices completed a pre-visit survey, including American Heart Association Simple 7 CVH factors (classified as ideal, intermediate, or poor). Medical record abstraction ascertained CVD risk factors and cancer characteristics. Likert-type questions assessed desired discussion during oncology care. RESULTS: Of 502 enrolled survivors (95.6% female; mean time since diagnosis = 4.2 years), most had breast cancer (79.7%). Many survivors had common cardiovascular comorbidities, including high cholesterol (48.3%), hypertension or high BP (47.8%) obesity (33.1%), and diabetes (20.5%); 30.5% of survivors received high cardiotoxicity potential cancer treatment. Less than half had ideal/non-missing levels for physical activity (48.0%), BMI (18.9%), cholesterol (17.9%), blood pressure (14.1%), healthy diet (11.0%), and glucose/ HbA1c (6.0%). While > 50% of survivors had concordant EHR-self-report categorization for smoking, BMI, and blood pressure; cholesterol, glucose, and A1C were unknown by survivors and/or missing in the EHR for most. Most survivors agreed oncology providers should talk about heart health (78.9%). CONCLUSIONS: Tools to promote CVH discussion can fill gaps in CVH knowledge and are likely to be well-received by survivors in community settings. TRIAL REGISTRATION: NCT03935282, Registered 10/01/2020.

Endometrial cancer survivors' perceptions of their cardiovascular disease risk (results from WF-1804CD AH-HA).

OBJECTIVE: Despite considerable burden of cardiovascular disease (CVD), data on endometrial cancer survivors' CVD perceptions are lacking. We assessed survivors' perspectives on addressing CVD risk during oncology care. METHODS: This cross-sectional analysis utilized data from an ongoing trial of an EHR heart health tool (R01CA226078 & UG1CA189824) conducted through the NCI Community Oncology Research Program (NCORP, WF-1804CD). Endometrial cancer survivors post-potentially curative treatment were recruited from community practices and completed a pre-visit baseline survey, including American Heart Association Simple 7 CVD factors. Likert-type questions assessed confidence in understanding CVD risk, CVD risk perception, and desired discussion during oncology care. Medical record abstraction ascertained data on CVD and cancer characteristics. RESULTS: Survivors (N = 55, median age = 62; 62% 0-2 years post-diagnosis) were predominately white, non-Hispanic (87%). Most agreed/strongly agreed heart disease poses a risk to their health (87%) and oncology providers should talk to patients about heart health (76%). Few survivors reported smoking (12%) but many had poor/intermediate values for blood pressure (95%), body mass index (93%), fasting glucose/A1c (60%), diet (60%), exercise (47%) and total cholesterol (53%). 16% had not seen a PCP in the last year; these survivors were more likely to report financial hardship (22% vs 0%; p = 0.02). Most reported readiness to take steps to maintain or improve heart health (84%). CONCLUSIONS: Discussions of CVD risk during routine oncology care are likely to be well received by endometrial cancer survivors. Strategies are needed to implement CVD risk assessment guidelines and to enhance communication and referrals with primary care. Clinical Trials #: NCT03935282.

Leveraging Artificial Intelligence and Synthetic Data Derivatives for Spine Surgery Research.

STUDY DESIGN: Retrospective cohort study. OBJECTIVES: Leveraging electronic health records (EHRs) for spine surgery research is impeded by concerns regarding patient privacy and data ownership. Synthetic data derivatives may help overcome these limitations. This study's objective was to validate the use of synthetic data for spine surgery research. METHODS: Data came from the EHR from 15 hospitals. Patients that underwent anterior cervical or posterior lumbar fusion (2010-2020) were included. Real data were obtained from the EHR. Synthetic data was generated to simulate the properties of the real data, without maintaining a one-to-one correspondence with real patients. Within each cohort, ability to predict 30-day readmissions and 30-day complications was evaluated using logistic regression and extreme gradient boosting machines (XGBoost). RESULTS: We identified 9,072 real and 9,088 synthetic cervical fusion patients. Descriptive characteristics were nearly identical between the 2 datasets. When predicting readmission, models built using real and synthetic data both had c-statistics of .69-.71 using logistic regression and XGBoost. Among 12,111 real and 12,126 synthetic lumbar fusion patients, descriptive characteristics were nearly the same for most variables. Using logistic regression and XGBoost to predict readmission, discrimination was similar with models built using real and synthetic data (c-statistics .66-.69). When predicting complications, models derived using real and synthetic data showed similar discrimination in both cohorts. Despite some differences, the most influential predictors were similar in the real and synthetic datasets. CONCLUSION: Synthetic data replicate most descriptive and predictive properties of real data, and therefore may expand EHR research in spine surgery.

Estrogen hormone is an essential sex factor inhibiting inflammation and immune response in COVID-19.

Although vaccines have been evaluated and approved for SARS-CoV-2 infection prevention, there remains a lack of effective treatments to reduce the mortality of COVID-19 patients already infected with SARS-CoV-2. The global data on COVID-19 showed that men have a higher mortality rate than women. We further observed that the proportion of mortality of females increases starting from around the age of 55 significantly. Thus, sex is an essential factor associated with COVID-19 mortality, and sex related genetic factors could be interesting mechanisms and targets for COVID-19 treatment. However, the associated sex factors and signaling pathways remain unclear. Here, we propose to uncover the potential sex associated factors using systematic and integrative network analysis. The unique results indicated that estrogens, e.g., estrone and estriol, (1) interacting with ESR1/2 receptors, (2) can inhibit SARS-CoV-2 caused inflammation and immune response signaling in host cells; and (3) estrogens are associated with the distinct fatality rates between male and female COVID-19 patients. Specifically, a high level of estradiol protects young female COVID-19 patients, and estrogens drop to an extremely low level in females after about 55 years of age causing the increased fatality rate of women. In conclusion, estrogen, interacting with ESR1/2 receptors, is an essential sex factor that protects COVID-19 patients from death by inhibiting inflammation and immune response caused by SARS-CoV-2 infection. Moreover, medications boosting the down-stream signaling of ESR1/ESR2, or inhibiting the inflammation and immune-associated targets on the signaling network can be potentially effective or synergistic combined with other existing drugs for COVID-19 treatment.

Status of Cardiovascular Health in US Adults and Children Using the American Heart Association's New "Life's Essential 8" Metrics: Prevalence Estimates From the National Health and Nutrition Examination Survey (NHANES), 2013 Through 2018.

BACKGROUND: The American Heart Association recently published an updated algorithm for quantifying cardiovascular health (CVH)-the Life's Essential 8 score. We quantified US levels of CVH using the new score. METHODS: We included individuals ages 2 through 79 years (not pregnant or institutionalized) who were free of cardiovascular disease from the National Health and Nutrition Examination Surveys in 2013 through 2018. For all participants, we calculated the overall CVH score (range, 0 [lowest] to 100 [highest]), as well as the score for each component of diet, physical activity, nicotine exposure, sleep duration, body mass index, blood lipids, blood glucose, and blood pressure, using published American Heart Association definitions. Sample weights and design were incorporated in calculating prevalence estimates and standard errors using standard survey procedures. CVH scores were assessed across strata of age, sex, race and ethnicity, family income, and depression. RESULTS: There were 23 409 participants, representing 201 728 000 adults and 74 435 000 children. The overall mean CVH score was 64.7 (95% CI, 63.9-65.6) among adults using all 8 metrics and 65.5 (95% CI, 64.4-66.6) for the 3 metrics available (diet, physical activity, and body mass index) among children and adolescents ages 2 through 19 years. For adults, there were significant differences in mean overall CVH scores by sex (women, 67.0; men, 62.5), age (range of mean values, 62.2-68.7), and racial and ethnic group (range, 59.7-68.5). Mean scores were lowest for diet, physical activity, and body mass index metrics. There were large differences in mean scores across demographic groups for diet (range, 23.8-47.7), nicotine exposure (range, 63.1-85.0), blood glucose (range, 65.7-88.1), and blood pressure (range, 49.5-84.0). In children, diet scores were low (mean 40.6) and were progressively lower in higher age groups (from 61.1 at ages 2 through 5 to 28.5 at ages 12 through 19); large differences were also noted in mean physical activity (range, 63.1-88.3) and body mass index (range, 74.4-89.4) scores by sociodemographic group. CONCLUSIONS: The new Life's Essential 8 score helps identify large group and individual differences in CVH. Overall CVH in the US population remains well below optimal levels and there are both broad and targeted opportunities to monitor, preserve, and improve CVH across the life course in individuals and the population.

Translating Data Analytics Into Improved Spine Surgery Outcomes: A Roadmap for Biomedical Informatics Research in 2021.

STUDY DESIGN: Narrative review. OBJECTIVES: There is growing interest in the use of biomedical informatics and data analytics tools in spine surgery. Yet despite the rapid growth in research on these topics, few analytic tools have been implemented in routine spine practice. The purpose of this review is to provide a health information technology (HIT) roadmap to help translate data assets and analytics tools into measurable advances in spine surgical care. METHODS: We conducted a narrative review of PubMed and Google Scholar to identify publications discussing data assets, analytical approaches, and implementation strategies relevant to spine surgery practice. RESULTS: A variety of data assets are available for spine research, ranging from commonly used datasets, such as administrative billing data, to emerging resources, such as mobile health and biobanks. Both regression and machine learning techniques are valuable for analyzing these assets, and researchers should recognize the particular strengths and weaknesses of each approach. Few studies have focused on the implementation of HIT, and a variety of methods exist to help translate analytic tools into clinically useful interventions. Finally, a number of HIT-related challenges must be recognized and addressed, including stakeholder acceptance, regulatory oversight, and ethical considerations. CONCLUSIONS: Biomedical informatics has the potential to support the development of new HIT that can improve spine surgery quality and outcomes. By understanding the development life-cycle that includes identifying an appropriate data asset, selecting an analytic approach, and leveraging an effective implementation strategy, spine researchers can translate this potential into measurable advances in patient care.

Women and ethnoracial minorities with poor cardiovascular health measures associated with a higher risk of developing mood disorder.

BACKGROUND: Mood disorders (MDS) are a type of mental health illness that effects millions of people in the United States. Early prediction of MDS can give providers greater opportunity to treat these disorders. We hypothesized that longitudinal cardiovascular health (CVH) measurements would be informative for MDS prediction. METHODS: To test this hypothesis, the American Heart Association's Guideline Advantage (TGA) dataset was used, which contained longitudinal EHR from 70 outpatient clinics. The statistical analysis and machine learning models were employed to identify the associations of the MDS and the longitudinal CVH metrics and other confounding factors. RESULTS: Patients diagnosed with MDS consistently had a higher proportion of poor CVH compared to patients without MDS, with the largest difference between groups for Body mass index (BMI) and Smoking. Race and gender were associated with status of CVH metrics. Approximate 46% female patients with MDS had a poor hemoglobin A1C compared to 44% of those without MDS; 62% of those with MDS had poor BMI compared to 47% of those without MDS; 59% of those with MDS had poor blood pressure (BP) compared to 43% of those without MDS; and 43% of those with MDS were current smokers compared to 17% of those without MDS. CONCLUSIONS: Women and ethnoracial minorities with poor cardiovascular health measures were associated with a higher risk of development of MDS, which indicated the high utility for using routine medical records data collected in care to improve detection and treatment for MDS among patients with poor CVH.

Estrogen Hormone Is an Essential Sex Factor Inhibiting Inflammation and Immune Response in COVID-19.

Although vaccines have been evaluated and approved for SARS-CoV-2 infection prevention, there remains a lack of effective treatments to reduce the mortality of COVID-19 patients already infected with SARS-CoV-2. The global data of COVID-19 showed that men have a higher mortality rate than women. We further observed that the proportion of mortality of female increases starting from around the age of 55 significantly. Thus, sex is an essential factor associated with COVID-19 mortality, and sex related genetic factors could be interesting mechanisms and targets for COVID-19 treatment. However, the associated sex factors and signaling pathways remain unclear. Here, we propose to uncover the potential sex associated factors using systematic and integrative network analysis. The unique results indicated that estrogen hormones (ER), e.g., estrone and estriol, 1) interacting with ESR1/2 receptors, 2) can inhibit SARS-CoV-2 caused inflammation and immune response signaling in host cells; and 3) estrogen hormone is associated with the distinct fatality rates between male and female COVID-19 patients. Specifically, a high level of estradiol protecting young female COVID-19 patients, and estrogen loss to an extremely low level in females after about 55 years of age causing the increased fatality rate of women. In conclusion, estrogen hormone, interacting with ESR1/2 receptors, is an essential sex factor that protects COVID-19 patients by inhibiting inflammation and immune response caused by SARS-CoV-2 infection. Medications perturb the down-stream of ESR1/ESR2 to inhibit the inflammation and immune response can be effective or synergistic combined with other existing drugs for COVID-19 treatment.

Implementing an Electronic Clinical Decision Support Tool Into Routine Care: A Qualitative Study of Stakeholders' Perceptions of a Post-Mastectomy Breast Reconstruction Tool.

Objective. To explore barriers and facilitators to implementing an evidence-based clinical decision support (CDS) tool (BREASTChoice) about post-mastectomy breast reconstruction into routine care. Materials and Methods. A stakeholder advisory group of cancer survivors, clinicians who discuss and/or perform breast reconstruction in women with cancer, and informatics professionals helped design and review the interview guide. Based on the Consolidated Framework for Implementation Research (CFIR), we conducted qualitative semistructured interviews with key stakeholders (patients, clinicians, informatics professionals) to explore intervention, setting characteristics, and process-level variables that can impact implementation. Interviews were transcribed, coded, and analyzed based on the CFIR framework using both inductive and deductive methods. Results. Fifty-seven potential participants were contacted; 49 (85.9%) were eligible, and 35 (71.4%) were enrolled, continuing until thematic saturation was reached. Participants consisted of 13 patients, 13 clinicians, and 9 informatics professionals. Stakeholders thought that BREASTChoice was useful and provided patients with an evidence-based source of information about post-mastectomy breast reconstruction, including their personalized risks. They felt that BREASTChoice could support shared decision making, improve workflow, and possibly save consultation time, but were uncertain about the best time to deliver BREASTChoice to patients. Some worried about cost, data availability, and security of integrating the tool into an electronic health record. Most acknowledged the importance of showing clinical utility to gain institutional buy-in and encourage routine adoption. Discussion and Conclusion. Stakeholders felt that BREASTChoice could support shared decision making, improve workflow, and reduce consultation time. Addressing key questions such as cost, data integration, and timing of delivering BREASTChoice could build institutional buy-in for CDS implementation. Results can guide future CDS implementation studies.

Predicting Incident Heart Failure in Women With Machine Learning: The Women's Health Initiative Cohort.

BACKGROUND: Heart failure (HF) is a leading cause of cardiac morbidity among women, whose risk factors differ from those in men. We used machine-learning approaches to develop risk- prediction models for incident HF in a cohort of postmenopausal women from the Women's Health Initiative (WHI). METHODS: We used 2 machine-learning methods-Least Absolute Shrinkage and Selection Operator (LASSO) and Classification and Regression Trees (CART)-to perform variable selection on 1227 baseline WHI variables for the primary outcome of incident HF. These variables were then used to construct separate Cox proportional hazard models, and we compared these results, using receiver-operating characteristic (ROC) curve analysis, against a comparator model built using variables from the Atherosclerosis Risk in Communities (ARIC) HF prediction model. We analyzed 43,709 women who had 2222 incident HF events; median follow-up was 14.3 years. RESULTS: LASSO selected 10 predictors, and CART selected 11 predictors. The highest correlation between selected variables was 0.46. In addition to selecting well-established predictors such as age, myocardial infarction, and smoking, novel predictors included physical function, number of pregnancies, number of previous live births and age at menopause. In ROC analysis, the CART-derived model had the highest C-statistic of 0.83 (95% confidence interval [CI], 0.81-0.85), followed by LASSO 0.82 (95% CI, 0.81-0.84) and ARIC 0.73 (95% CI, 0.70-0.76). CONCLUSIONS: Machine-learning approaches can be used to develop HF risk-prediction models that can have better discrimination compared with an established HF risk model and may provide a basis for investigating novel HF predictors.

Addressing cancer survivors' cardiovascular health using the automated heart health assessment (AH-HA) EHR tool: Initial protocol and modifications to address COVID-19 challenges.

BACKGROUND: The purpose of this paper is to describe the Automated Heart-Health Assessment (AH-HA) study protocol, which demonstrates an agile approach to cancer care delivery research. This study aims to assess the effect of a clinical decision support tool for cancer survivors on cardiovascular health (CVH) discussions, referrals, completed visits with primary care providers and cardiologists, and control of modifiable CVH factors and behaviors. The COVID-19 pandemic has caused widespread disruption to clinical trial accrual and operations. Studies conducted with potentially vulnerable populations, including cancer survivors, must shift towards virtual consent, data collection, and study visits to reduce risk for participants and study staff. Studies examining cancer care delivery innovations may also need to accommodate the increased use of virtual visits. METHODS/DESIGN: This group-randomized, mixed methods study will recruit 600 cancer survivors from 12 National Cancer Institute Community Oncology Research Program (NCORP) practices. Survivors at intervention sites will use the AH-HA tool with their oncology provider; survivors at usual care sites will complete routine survivorship visits. Outcomes will be measured immediately after the study visit, with follow-up at 6 and 12 months. The study was amended during the COVID-19 pandemic to allow for virtual consent, data collection, and intervention options, with the goal of minimizing participant-staff in-person contact and accommodating virtual survivorship visits. CONCLUSIONS: Changes to the study protocol and procedures allow important cancer care delivery research to continue safely during the COVID-19 pandemic and give sites and survivors flexibility to conduct study activities in-person or remotely.

Mobile Health Applications, Cancer Survivors, and Lifestyle Modification: An Integrative Review.

Cancer survivors' well-being is threatened by the risk of cancer recurrence and the increased risk of chronic diseases resulting from cancer treatments. Improving lifestyle behaviors attenuates these risks. Traditional approaches to lifestyle modification (ie, counseling) are expensive, require significant human resources, and are difficult to scale. Mobile health interventions offer a novel alternative to traditional approaches. However, to date, systematic reviews have yet to examine the use of mobile health interventions for lifestyle behavior improvement among cancer survivors. The objectives of this integrative review were to synthesize research findings, critically appraise the scientific literature, examine the use of theory in intervention design, and identify survivors' preferences in using mobile health interventions for lifestyle improvement. Nineteen articles met eligibility requirements. Only two studies used quantitative methods. Study quality was low, and only one study reported the use of theory in app design. Unfortunately, the evidence has not yet sufficiently matured, in quality or in rigor, to make recommendations on how to improve health behaviors or outcomes. However, six themes emerged as important considerations for intervention development for cancer survivors (app features/functionality, social relationships/support, provider relationships/support, app content, app acceptability, and barriers to use). These findings underscored the need for rigorous, efficacy studies before the use of mobile health interventions can be safely recommended for cancer survivors.

Electronic clinical decision support for children with minor head trauma and intracranial injuries: a sociotechnical analysis.

BACKGROUND: Current management of children with minor head trauma (MHT) and intracranial injuries is not evidence-based and may place some children at risk of harm. Evidence-based electronic clinical decision support (CDS) for management of these children may improve patient safety and decrease resource use. To guide these efforts, we evaluated the sociotechnical environment impacting the implementation of electronic CDS, including workflow and communication, institutional culture, and hardware and software infrastructure, among other factors. METHODS: Between March and May, 2020 semi-structured qualitative focus group interviews were conducted to identify sociotechnical influences on CDS implementation. Physicians from neurosurgery, emergency medicine, critical care, and pediatric general surgery were included, along with information technology specialists. Participants were recruited from nine health centers in the United States. Focus group transcripts were coded and analyzed using thematic analysis. The final themes were then cross-referenced with previously defined sociotechnical dimensions. RESULTS: We included 28 physicians and four information technology specialists in seven focus groups (median five participants per group). Five physicians were trainees and 10 had administrative leadership positions. Through inductive thematic analysis, we identified five primary themes: (1) clinical impact; (2) stakeholders and users; (3) tool content; (4) clinical practice integration; and (5) post-implementation evaluation measures. Participants generally supported using CDS to determine an appropriate level-of-care for these children. However, some had mixed feelings regarding how the tool could best be used by different specialties (e.g. use by neurosurgeons versus non-neurosurgeons). Feedback from the interviews helped refine the tool content and also highlighted potential technical and workflow barriers to address prior to implementation. CONCLUSIONS: We identified key factors impacting the implementation of electronic CDS for children with MHT and intracranial injuries. These results have informed our implementation strategy and may also serve as a template for future efforts to implement health information technology in a multidisciplinary, emergency setting.

Cardiovascular Assessment Tool for Breast Cancer Survivors and Oncology Providers: Usability Study.

BACKGROUND: Cardiovascular health is of increasing concern to breast cancer survivors and their health care providers, as many survivors are more likely to die from cardiovascular disease than cancer. Implementing clinical decision support tools to address cardiovascular risk factor awareness in the oncology setting may enhance survivors' attainment or maintenance of cardiovascular health. OBJECTIVE: We sought to evaluate survivors' awareness of cardiovascular risk factors and examine the usability of a novel electronic health record enabled cardiovascular health tool from the perspective of both breast cancer survivors and oncology providers. METHODS: Breast cancer survivors (n=49) recruited from a survivorship clinic interacted with the cardiovascular health tool and completed pre and posttool assessments about cardiovascular health knowledge and perceptions of the tool. Oncologists, physician assistants, and nurse practitioners (n=20) who provide care to survivors also viewed the cardiovascular health tool and completed assessments of perceived usability and acceptability. RESULTS: Enrolled breast cancer survivors (84% White race, 4% Hispanic ethnicity) had been diagnosed 10.8 years ago (SD 6.0) with American Joint Committee on Cancer stage 0, I, or II (45/49, 92%). Prior to viewing the tool, 65% of survivors (32/49) reported not knowing their level for one or more cardiovascular health factors (range 0-4). On average, only 45% (range 0%-86%) of survivors' known cardiovascular health factors were at an ideal level. More than 50% of survivors had ideal smoking status (45/48, 94%) or blood glucose level (29/45, 64%); meanwhile, less than 50% had ideal blood pressure (12/49, 24%), body mass index (12/49, 24%), cholesterol level (17/35, 49%), diet (7/49, 14%), and physical activity (10/49. 20%). More than 90% of survivors thought the tool was easy to understand (46/47, 98%), improved their understanding (43/47, 91%), and was helpful (45/47, 96%); overall, 94% (44/47 survivors) liked the tool. A majority of survivors (44/47, 94%) thought oncologists should discuss cardiovascular health during survivorship care. Most (12/20, 60%) oncology providers (female: 12/20, 60%; physicians: 14/20, 70%) had been practicing for more than 5 years. Most providers agreed the tool provided useful information (18/20, 90%), would help their effectiveness (18/20, 90%), was easy to use (20/20, 100%), and presented information in a useful format (19/20, 95%); and 85% of providers (17/20) reported they would use the tool most or all of the time when providing survivorship care. CONCLUSIONS: These usability data demonstrate acceptability of a cardiovascular health clinical decision support tool in oncology practices. Oncology providers and breast cancer survivors would likely value the integration of such apps in survivorship care. By increasing awareness and communication regarding cardiovascular health, electronic health record-enabled tools may improve survivorship care delivery for breast cancer and ultimately patient outcomes.

Predicting cardiovascular health trajectories in time-series electronic health records with LSTM models.

BACKGROUND: Cardiovascular disease (CVD) is the leading cause of death in the United States (US). Better cardiovascular health (CVH) is associated with CVD prevention. Predicting future CVH levels may help providers better manage patients' CVH. We hypothesized that CVH measures can be predicted based on previous measurements from longitudinal electronic health record (EHR) data. METHODS: The Guideline Advantage (TGA) dataset was used and contained EHR data from 70 outpatient clinics across the United States (US). We studied predictions of 5 CVH submetrics: smoking status (SMK), body mass index (BMI), blood pressure (BP), hemoglobin A1c (A1C), and low-density lipoprotein (LDL). We applied embedding techniques and long short-term memory (LSTM) networks - to predict future CVH category levels from all the previous CVH measurements of 216,445 unique patients for each CVH submetric. RESULTS: The LSTM model performance was evaluated by the area under the receiver operator curve (AUROC): the micro-average AUROC was 0.99 for SMK prediction; 0.97 for BMI; 0.84 for BP; 0.91 for A1C; and 0.93 for LDL prediction. Model performance was not improved by using all 5 submetric measures compared with using single submetric measures. CONCLUSIONS: We suggest that future CVH levels can be predicted using previous CVH measurements for each submetric, which has implications for population cardiovascular health management. Predicting patients' future CVH levels might directly increase patient CVH health and thus quality of life, while also indirectly decreasing the burden and cost for clinical health system caused by CVD and cancers.

Predictive Modeling for Clinical Features Associated With Neurofibromatosis Type 1.

OBJECTIVE: To perform a longitudinal analysis of clinical features associated with neurofibromatosis type 1 (NF1) based on demographic and clinical characteristics and to apply a machine learning strategy to determine feasibility of developing exploratory predictive models of optic pathway glioma (OPG) and attention-deficit/hyperactivity disorder (ADHD) in a pediatric NF1 cohort. METHODS: Using NF1 as a model system, we perform retrospective data analyses using a manually curated NF1 clinical registry and electronic health record (EHR) information and develop machine learning models. Data for 798 individuals were available, with 578 comprising the pediatric cohort used for analysis. RESULTS: Males and females were evenly represented in the cohort. White children were more likely to develop OPG (odds ratio [OR]: 2.11, 95% confidence interval [CI]: 1.11-4.00, p = 0.02) relative to their non-White peers. Median age at diagnosis of OPG was 6.5 years (1.7-17.0), irrespective of sex. Males were more likely than females to have a diagnosis of ADHD (OR: 1.90, 95% CI: 1.33-2.70, p < 0.001), and earlier diagnosis in males relative to females was observed. The gradient boosting classification model predicted diagnosis of ADHD with an area under the receiver operator characteristic (AUROC) of 0.74 and predicted diagnosis of OPG with an AUROC of 0.82. CONCLUSIONS: Using readily available clinical and EHR data, we successfully recapitulated several important and clinically relevant patterns in NF1 semiology specifically based on demographic and clinical characteristics. Naive machine learning techniques can be potentially used to develop and validate predictive phenotype complexes applicable to risk stratification and disease management in NF1.

Time-series cardiovascular risk factors and receipt of screening for breast, cervical, and colon cancer: The Guideline Advantage.

BACKGROUND: Cancer is the second leading cause of death in the United States. Cancer screenings can detect precancerous cells and allow for earlier diagnosis and treatment. Our purpose was to better understand risk factors for cancer screenings and assess the effect of cancer screenings on changes of Cardiovascular health (CVH) measures before and after cancer screenings among patients. METHODS: We used The Guideline Advantage (TGA)-American Heart Association ambulatory quality clinical data registry of electronic health record data (n = 362,533 patients) to investigate associations between time-series CVH measures and receipt of breast, cervical, and colon cancer screenings. Long short-term memory (LSTM) neural networks was employed to predict receipt of cancer screenings. We also compared the distributions of CVH factors between patients who received cancer screenings and those who did not. Finally, we examined and quantified changes in CVH measures among the screened and non-screened groups. RESULTS: Model performance was evaluated by the area under the receiver operator curve (AUROC): the average AUROC of 10 curves was 0.63 for breast, 0.70 for cervical, and 0.61 for colon cancer screening. Distribution comparison found that screened patients had a higher prevalence of poor CVH categories. CVH submetrics were improved for patients after cancer screenings. CONCLUSION: Deep learning algorithm could be used to investigate the associations between time-series CVH measures and cancer screenings in an ambulatory population. Patients with more adverse CVH profiles tend to be screened for cancers, and cancer screening may also prompt favorable changes in CVH. Cancer screenings may increase patient CVH health, thus potentially decreasing burden of disease and costs for the health system (e.g., cardiovascular diseases and cancers).

Coronary heart disease and mortality following a breast cancer diagnosis.

BACKGROUND: Coronary heart disease (CHD) is a leading cause of morbidity and mortality for breast cancer survivors, yet the joint effect of adverse cardiovascular health (CVH) and cardiotoxic cancer treatments on post-treatment CHD and death has not been quantified. METHODS: We conducted statistical and machine learning approaches to evaluate 10-year risk of these outcomes among 1934 women diagnosed with breast cancer during 2006 and 2007. Overall CVH scores were classified as poor, intermediate, or ideal for 5 factors, smoking, body mass index, blood pressure, glucose/hemoglobin A1c, and cholesterol from clinical data within 5 years prior to the breast cancer diagnosis. The receipt of potentially cardiotoxic breast cancer treatments was indicated if the patient received anthracyclines or hormone therapies. We modeled the outcomes of post-cancer diagnosis CHD and death, respectively. RESULTS: Results of these approaches indicated that the joint effect of poor CVH and receipt of cardiotoxic treatments on CHD (75.9%) and death (39.5%) was significantly higher than their independent effects [poor CVH (55.9%) and cardiotoxic treatments (43.6%) for CHD, and poor CVH (29.4%) and cardiotoxic treatments (35.8%) for death]. CONCLUSIONS: Better CVH appears to be protective against the development of CHD even among women who had received potentially cardiotoxic treatments. This study determined the extent to which attainment of ideal CVH is important not only for CHD and mortality outcomes among women diagnosed with breast cancer.

A Randomized Controlled Trial Evaluating the BREASTChoice Tool for Personalized Decision Support About Breast Reconstruction After Mastectomy.

OBJECTIVE: To evaluate a web-based breast reconstruction decision aid, BREASTChoice. SUMMARY AND BACKGROUND DATA: Although postmastectomy breast reconstruction can restore quality of life and body image, its morbidity remains substantial. Many patients lack adequate knowledge to make informed choices. Decisions are often discordant with patients' preferences. METHODS: Adult women with stages 0-III breast cancer considering postmastectomy breast reconstruction with no previous reconstruction were randomized to BREASTChoice or enhanced usual care (EUC). RESULTS: Three hundred seventy-six patients were screened; 120 of 172 (69.8%) eligible patients enrolled. Mean age = 50.7 years (range 25-77). Most were Non-Hispanic White (86.3%) and had a college degree (64.3%). Controlling for health literacy and provider seen, BREASTChoice users had higher knowledge than those in EUC (84.6% vs. 58.2% questions correct; P < 0.001). Those using BREASTChoice were more likely to know that reconstruction typically requires more than 1 surgery, delayed reconstruction lowers one's risk, and implants may need replacement over time (all ps < 0.002). BREASTChoice compared to EUC participants also felt more confident understanding reconstruction information (P = 0.009). There were no differences between groups in decisional conflict, decision process quality, shared decision-making, quality of life, or preferences (all ps > 0.05). There were no differences in consultation length between BREASTChoice and EUC groups (mean = 29.7 vs. 30.0 minutes; P > 0.05). BREASTChoice had high usability (mean score = 6.3/7). Participants completed BREASTChoice in about 27 minutes. CONCLUSIONS: BREASTChoice can improve breast reconstruction decision quality by improving patients' knowledge and providing them with personalized risk estimates. More research is needed to facilitate point-of-care decision support and examine BREASTChoice's impact on patients' decisions over time.

Cardiovascular Health Trends in Electronic Health Record Data (2012-2015): A Cross-Sectional Analysis of The Guideline Advantage™.

BACKGROUND: Electronic health record (EHR) data can measure cardiovascular health (CVH) of patient populations, but have limited generalizability when derived from one health care system. OBJECTIVE: We used The Guideline Advantage™ (TGA) data repository, comprising EHR data of patients from 8 diverse health care systems, to describe CVH of adult patients and progress towards the American Heart Association's (AHA's) 2020 Impact Goals. METHODS: Our analysis included 203,488 patients with 677,733 encounters recorded in TGA from 2012 to 2015. Five measures from EHRs [cigarette smoking status, body mass index (BMI), blood pressure (BP), cholesterol, and diabetes mellitus (DM)] were categorized as poor/intermediate/ideal according to AHA's Life's Simple 7 algorithm. We presented distributions and trends of CVH for each metric over time, first using all available data, and then in a subsample (n = 1,890) of patients with complete data on all metrics. RESULTS: Among all patients, the greatest stride towards ideal CVH attainment from 2012 to 2015 was for cigarette smoking (50.6 percent to 65 percent), followed by DM (17.3 percent to 20.7 percent) and BP (21.1 percent to 23.2 percent). Overall, prevalence of ideal CVH did not increase for any metric in the subsample. Males slightly improved in ideal CVH for BMI and cholesterol; meanwhile, females saw no improvement in ideal CVH for any metric. As ideal CVH for BP and cholesterol increased slightly among white patients, ideal CVH for BP, cholesterol, BMI, and DM worsened for non-whites. CONCLUSION: Despite improvements in some CVH metrics in the outpatient setting, more tangible progress is needed to meet AHA's 2020 Impact Goals.