Improving Equity in Deep Learning Medical Applications with the Gerchberg-Saxton Algorithm.

Deep learning (DL) has gained prominence in healthcare for its ability to facilitate early diagnosis, treatment identification with associated prognosis, and varying patient outcome predictions. However, because of highly variable medical practices and unsystematic data collection approaches, DL can unfortunately exacerbate biases and distort estimates. For example, the presence of sampling bias poses a significant challenge to the efficacy and generalizability of any statistical model.

T-DM1 after Pertuzumab plus Trastuzumab: Treatment Sequence-Induced Selection Bias in HER2-Positive Metastatic Breast Cancer.

Real-world studies have suggested decreased trastuzumab emtansine (T-DM1) effectiveness in patients with metastatic breast cancer (mBC) who received prior trastuzumab plus pertuzumab (H + P). However, these studies may have been biased toward pertuzumab-experienced patients with more aggressive disease. Using an electronic health record-derived database, patients diagnosed with mBC on/after 1 January 2011 who initiated T-DM1 in any treatment line (primary cohort) or who initiated second-line T-DM1 following first-line H ± P (secondary cohort) from 22 February 2013 to 31 December 2019 were included.

An overview of real-world data sources for oncology and considerations for research.

Generating evidence on the use, effectiveness, and safety of new cancer therapies is a priority for researchers, health care providers, payers, and regulators given the rapid pace of change in cancer diagnosis and treatments. The use of real-world data (RWD) is integral to understanding the utilization patterns and outcomes of these new treatments among patients with cancer who are treated in clinical practice and community settings. An initial step in the use of RWD is careful study design to assess the suitability of an RWD source.

Adoption and effectiveness of de-escalated radiation and endocrine therapy strategies for older women with low-risk breast cancer.

Purpose: Recent clinical trials support de-escalation of adjuvant radiation therapy following lumpectomy in some older women with low-risk HR+ breast cancers planning to take endocrine therapy. The adoption of these findings into clinical practice, and the effectiveness of de-escalated therapy in real-world populations, remain under investigation.

Materials And Methods: We evaluated use of adjuvant radiation therapy and/or endocrine therapy among older women with T1-2 node-negative, HR+ breast cancer in the United States between 2007 and 2011.

Data linkage in pharmacoepidemiology: A call for rigorous evaluation and reporting.

Purpose: The purpose of this paper is to provide guidance on the evaluation of data linkage quality through the development of a checklist for reporting key elements of the linkage process.

Methods: Responding to a call for manuscripts from the International Society for Pharmacoepidemiology (ISPE), a working group including international representation from the academic, industry, and contract research, and regulatory sectors was formed to develop a checklist for evaluation of data linkage performance and reporting data linkage specifically for pharmacoepidemiologic research. This checklist expands on the reporting of studies conducted using observational routinely collected health data specific to pharmacoepidemiology (RECORD-PE) guidelines.

Development and validation of a 5-year mortality prediction model using regularized regression and Medicare data.

Purpose: De-implementation of low-value services among patients with limited life expectancy is challenging. Robust mortality prediction models using routinely collected health care data can enhance health care stakeholders' ability to identify populations with limited life expectancy. We developed and validated a claims-based prediction model for 5-year mortality using regularized regression methods.

Examining determinants of geographic variation in colorectal cancer mortality in North Carolina: A spatial analysis approach.

Purpose: A recent study using national data from 2000 to 2009 identified colorectal cancer (CRC) mortality "hotspots" in 11 counties of North Carolina (NC). In this study, we used more recent, state-specific data to investigate the county-level determinants of geographic variation in NC through a geospatial analytic approach.

Method: Using NC CRC mortality data from 2003 to 2013, we first conducted clustering analysis to confirm spatial dependence.

The relationship of travel distance with cystectomy access and outcomes.

Purpose: Regionalization of care and travel distance may result in unintended consequences for complex surgery such as cystectomy. Our objective was to evaluate effect of differential distance on cystectomy receipt among patients with muscle-invasive bladder cancer (MIBC) and investigate the association between travel distance and cystectomy outcomes such as readmission.

Methods: Using a linked data resource combining the NC Central Cancer Registry with claims data from Medicare, Medicaid, and private insurance plans, we included 736 patients with MIBC and 1,082 who underwent cystectomy.

Influence of provider factors and race on uptake of breast cancer gene expression profiling.

Background: Gene expression profiling (GEP) has been rapidly adopted for early breast cancer and can aid in chemotherapy decision making. Study results regarding racial disparities in testing are conflicting, and may reflect different care settings. To the authors' knowledge, data regarding the influence of provider factors on testing are scarce.

Reducing Racial Disparities in Breast Cancer Care: The Role of 'Big Data'.

Advances in a wide array of scientific technologies have brought data of unprecedented volume and complexity into the oncology research space. These novel big data resources are applied across a variety of contexts-from health services research using data from insurance claims, cancer registries, and electronic health records, to deeper and broader genomic characterizations of disease. Several forms of big data show promise for improving our understanding of racial disparities in breast cancer, and for powering more intelligent and far-reaching interventions to close the racial gap in breast cancer survival.

Association of Delays in Surgery for Melanoma With Insurance Type.

Importance: Timely receipt of treatment for cancer is an important aspect of health care quality. It is unknown how delays of surgery for melanoma vary by insurance type.

Objective: To analyze factors associated with delays between diagnosis and surgery for melanoma in patients with Medicare, Medicaid, or private insurance.

Comparative Toxicity and Effectiveness of Trastuzumab-Based Chemotherapy Regimens in Older Women With Early-Stage Breast Cancer.

Purpose The combination of chemotherapy and trastuzumab is the standard of care for adjuvant treatment of human epidermal growth factor receptor 2-positive breast cancer. Two regimens have been widely adopted in the United States: doxorubicin, cyclophosphamide, paclitaxel, and trastuzumab (ACTH) and docetaxel, carboplatin, and trastuzumab (TCH). No head-to-head comparison of these regimens has been conducted in a clinical trial, and existing trial data have limited generalizability to older patients.

Endocrine Therapy Initiation and Medical Oncologist Utilization Among Women Diagnosed with Ductal Carcinoma in Situ.

Background: Though randomized clinical trials have demonstrated a reduction in second breast events with endocrine therapy among women with ductal carcinoma in situ (DCIS), use of these therapies remains highly variable. The purpose of this study was to evaluate patient and treatment-related factors associated with endocrine therapy initiation and medical oncology specialty utilization after DCIS.

Materials And Methods: We identified women with a DCIS diagnosis during 2006-2010 in the North Carolina Central Cancer Registry with linked public and private insurance claims in the University of North Carolina Integrated Cancer Information Surveillance System data resource.

Data Linkage to Improve Geriatric Oncology Research: A Feasibility Study.

Older adults (aged 65 years and older) diagnosed with cancer account for most cancer-related morbidity and mortality in the United States but are often underrepresented on clinical trials. Recent attention from a variety of professional, research, regulatory, and patient advocacy groups has centered on data linkage and data sharing as a means to capture patient information and outcomes outside of clinical trials to accelerate progress in the fight against cancer. The development of a more robust observational research data infrastructure would help to address gaps in the evidence base regarding optimal approaches to treating cancer among the growing and complex population of older adults.

Association Between Choice of Radical Prostatectomy, External Beam Radiotherapy, Brachytherapy, or Active Surveillance and Patient-Reported Quality of Life Among Men With Localized Prostate Cancer.

Importance: Patients diagnosed with localized prostate cancer have to decide among treatment strategies that may differ in their likelihood of adverse effects.

Objective: To compare quality of life (QOL) after radical prostatectomy, external beam radiotherapy, and brachytherapy vs active surveillance.

Design, Setting, And Participants: Population-based prospective cohort of 1141 men (57% participation among eligible men) with newly diagnosed prostate cancer were enrolled from January 2011 through June 2013 in collaboration with the North Carolina Central Cancer Registry.

Cost-Effectiveness Analysis of Four Simulated Colorectal Cancer Screening Interventions, North Carolina.

Introduction: Colorectal cancer (CRC) screening rates are suboptimal, particularly among the uninsured and the under-insured and among rural and African American populations. Little guidance is available for state-level decision makers to use to prioritize investment in evidence-based interventions to improve their population's health. The objective of this study was to demonstrate use of a simulation model that incorporates synthetic census data and claims-based statistical models to project screening behavior in North Carolina.

Multilevel predictors of colorectal cancer testing modality among publicly and privately insured people turning 50.

Understanding multilevel predictors of colorectal cancer (CRC) screening test modality can help inform screening program design and implementation. We used North Carolina Medicare, Medicaid, and private, commercially available, health plan insurance claims data from 2003 to 2008 to ascertain CRC test modality among people who received CRC screening around their 50th birthday, when guidelines recommend that screening should commence for normal risk individuals. We ascertained receipt of colonoscopy, fecal occult blood test (FOBT) and fecal immunochemical test (FIT) from billing codes.

Framework for Deploying a Virtualized Computing Environment for Collaborative and Secure Data Analytics.

Introduction: Large amounts of health data generated by a wide range of health care applications across a variety of systems have the potential to offer valuable insight into populations and health care systems, but robust and secure computing and analytic systems are required to leverage this information.

Framework: We discuss our experiences deploying a Secure Data Analysis Platform (SeDAP), and provide a framework to plan, build and deploy a virtual desktop infrastructure (VDI) to enable innovation, collaboration and operate within academic funding structures. It outlines 6 core components: Security, Ease of Access, Performance, Cost, Tools, and Training.

Distance to a Plastic Surgeon and Type of Insurance Plan Are Independently Predictive of Postmastectomy Breast Reconstruction.

Background: The psychosocial benefits of postmastectomy breast reconstruction are well established; however, health care barriers persist. The authors evaluated statewide patient population to further identify obstacles to reconstruction.

Methods: A linked data set combining the North Carolina Central Cancer Registry with administrative claims from Medicare, Medicaid, and private insurance plans identified women diagnosed with breast cancer from 2003 to 2006.

Statewide geographic variation in outcomes for adults with acute myeloid leukemia in North Carolina.

Background: Population-based studies have demonstrated survival disparities related to socioeconomic factors for patients with acute myeloid leukemia (AML). The objective of the current study was to determine whether the local health care infrastructure, represented by Area Health Education Centers (AHEC) region, or treating center experience, represented by National Cancer Institute Comprehensive Cancer Center (NCICCC) designation, were associated with outcomes among patients with AML in North Carolina.

Methods: Patients who were diagnosed with AML from 2003 to 2009 were identified using the University of North Carolina Lineberger Integrated Cancer Information and Surveillance System, a database linking insurance claims to the North Carolina Cancer Registry.

Clinical Benefits Associated With Medicaid Coverage Before Diagnosis of Gynecologic Cancers.

Purpose: Many low-income patients enroll in Medicaid at the time of cancer diagnosis, which improves survival outcomes. Medicaid enrollment before cancer diagnosis may confer additional benefits. Our objective was to compare stage at diagnosis and overall mortality between women with and without Medicaid enrollment before gynecologic cancer diagnosis.

Referral patterns between high- and low-volume centers and associations with uterine cancer treatment and survival: a population-based study of Medicare, Medicaid, and privately insured women.

Background: High-volume center surgery and gynecologic oncology care are associated with improved outcomes for women with uterine cancer. Referral patterns, from biopsy through to chemotherapy, may have patients interacting with high-volume centers for all, a portion, or none of their care. The relative frequency, the underlying factors that contribute to referral, and the potential impact of these referral patterns on treatment outcomes are unknown.

Video Feedback in Key Word Signing Training for Preservice Direct Support Staff.

Purpose: Research has demonstrated that formal training is essential for professionals to learn key word signing. Yet, the particular didactic strategies have not been studied. Therefore, this study compared the effectiveness of verbal and video feedback in a key word signing training for future direct support staff.

Gynecologic cancer outcomes in the elderly poor: A population-based study.

Background: Adults aged ≥65 years who are dually enrolled in Medicare and Medicaid are an at-risk group in health care. However, to the best of the authors' knowledge, the outcomes of women with gynecologic cancers in this population are unknown.

Methods: The current study was a population-based cohort study of North Carolina state cancer registry cases of uterine, ovarian, cervical, and vulvar/vaginal cancers (2003-2009), with linked enrollment in Medicare and state Medicaid.

Comparative Effectiveness of Oxaliplatin Versus 5-flourouricil in Older Adults: An Instrumental Variable Analysis.

Background: Oxaliplatin was rapidly adopted for treatment of stage III colon cancer after FDA approval in November 2004, thus providing an opportunity to use calendar time as an instrumental variable in nonexperimental comparative effectiveness research. Assuming instrument validity, instrumental variable analyses account for unmeasured confounding and are particularly valuable in sub-populations of unresolved effectiveness, such as older individuals.

Methods: We examined stage III colon cancer patients ages 65+ years initiating chemotherapy between 2003 and 2008 using US population-based cancer registry data linked with Medicare claims (N = 3,660).