Avatar

Ronald Gangnon

Professor of Biostatistics

University of Wisconsin-Madison

Biography

I am a Professor in the Department of Biostatistics and Medical Informatics and the Department of Population Health Sciences in the School of Medicine and Public Health at the University of Wisconsin-Madison. I have an affiliate appointment in the Department of Statistics.

I grew up in Duluth, Minnesota. I graduated from East High School in 1988. I received a BA in Mathematics and Economics in 1992 from the University of Minnesota-Duluth and an MS in Statistics in 1994 and a PhD in Statistics with emphasis in Biostatistics in 1998 from the University of Wisconsin-Madison. My PhD advisor was Murray Clayton.

I was a research scientist in the Statistical Data Analysis Center(SDAC) in the Department of Biostatistics and Medical Informatics at the University of Wisconsin-Madison, 1998-2005. I joined the faculty with a joint appointment in the Department of Biostatistics and Medical Informatics and the Department of Population Health Sciences in 2005.

I am an applied biostatistician focusing on problems in clinical and epidemiologic research. Current methodologic areas of interest include (1) multi-state models for incidence, progression and regression of ocular (and other) diseases, (2) small area estimation problems, particularly ranking, (3) spatial and spatio-temporal modeling, particularly cluster detection and high-dimensional variable selection and (4) age-period-cohort modeling.

Outside of the office, I’m an avid cyclist. You can check out my recent rides on Strava. I’m also a big movie fan. You’ll definitely see me at the Wisconsin Film Festival, one of my favorite events every year, and you can see lists of my favorite films and what I’ve been watching recently on Letterboxd.

Interests

  • Spatial and Spatio-Temporal Modeling
  • Age-Period-Cohort Models
  • Ranking
  • Multi-State Models

Education

  • PhD in Statistics (emphasis in Biostatistics), 1998

    University of Wisconsin-Madison

  • MS in Statistics, 1994

    University of Wisconsin-Madison

  • BA in Mathematics and Economics, 1992

    University of Minnesota-Duluth

Publications

A flexible method for identifying spatial clusters of breast cancer using individual-level data

Prior research has shown that cancer risk varies by geography, but scan statistic methods for identifying cancer clusters in case-control studies have been limited in their ability to identify multiple clusters and adjust for participant-level risk factors. We develop a method to identify geographic patterns of breast cancer odds using the Wisconsin Women’s Health Study, a series of 5 population-based case-control studies of female Wisconsin residents aged 20-79 enrolled in 1988-2004 (cases=16,076, controls=16,795). We create sets of potential clusters by overlaying a 1 km grid over each county-neighborhood and enumerating a series of overlapping circles. Using a two-step approach, we fi=t a penalized binomial regression model to the number of cases and trials in each grid cell, penalizing all potential clusters by the least absolute shrinkage and selection operator (Lasso). We use BIC to select the number of clusters, which are included in a participant-level logistic regression model. We identify 15 geographic clusters, resulting in 23 areas of unique geographic odds ratios. After adjustment for known risk factors, confidence intervals narrowed but breast cancer odds ratios did not meaningfully change; one additional hotspot was identified. By considering multiple overlapping spatial clusters simultaneously, we discern gradients of spatial odds across Wisconsin.

Regularized spatial and spatio-temporal cluster detection

Spatial and spatio-temporal cluster detection are important tools in public health and many other areas of application. Cluster detection can be approached as a multiple testing problem, typically using a space and time scan statistic. We recast the spatial and spatio-temporal cluster detection problem in a high-dimensional data analytical framework with Poisson or quasi-Poisson regression with the Lasso penalty. We adopt a fast and computationally-efficient method using a novel sparse matrix representation of the effects of potential clusters. The number of clusters and tuning parameters are selected based on (quasi-)information criteria. We evaluate the performance of our proposed method including the false positive detection rate and power using a simulation study. Application of the method is illustrated using breast cancer incidence data from three prefectures in Japan.

Cause-specific student absenteeism monitoring in K-12 schools for detection of increased influenza activity in the surrounding community—Dane County, Wisconsin, 2014– 2020

Background Schools are primary venues of influenza amplification with secondary spread to communities. We assessed K-12 student absenteeism monitoring as a means for early detection of influenza activity in the community. Materials and methods Between September 2014 and March 2020, we conducted a prospective observational study of all-cause (a-TOT), illness-associated (a-I), and influenza-like illness–associated (a- ILI) absenteeism within the Oregon School District (OSD), Dane County, Wisconsin. Absenteeism was reported through the electronic student information system. Students were visited at home where pharyngeal specimens were collected for influenza RT-PCR testing. Surveillance of medically-attended laboratory-confirmed influenza (MAI) occurred in five primary care clinics in and adjoining the OSD. Poisson general additive log linear regression models of daily counts of absenteeism and MAI were compared using correlation analysis. Findings Influenza was detected in 723 of 2,378 visited students, and in 1,327 of 4,903 MAI patients. Over six influenza seasons, a-ILI was significantly correlated with MAI in the community (r =0.57; 95% CI: 0.53–0.63) with a one-day lead time and a-I was significantly correlated with MAI in the community (r = 0.49; 0.44–0.54) with a 10-day lead time, while a-TOT performed poorly (r = 0.27; 0.21–0.33), following MAI by six days. Discussion Surveillance using cause-specific absenteeism was feasible and performed well over a study period marked by diverse presentations of seasonal influenza. Monitoring a-I and a- ILI can provide early warning of seasonal influenza in time for community mitigation efforts.

Efect of semi-recumbent vibration exercise on muscle outcomes in older adults: a pilot randomized controlled clinical trial

Background: Many older adults with physical limitations living in residential care apartments are unable to exercise in a standing position and are at risk for declining in muscle function leading to falls and injury. Novel approaches to achieve exercise benefts are needed. The purpose of this study was to test the efect of semi-recumbent vibration exercise on muscle outcomes in older adults living in residential care apartment complexes (RCACs). Methods: A randomized, crossover design was used to examine the efect of semi-recumbent vibration exercise on muscle function and mass among 32 RCAC residents (mean age 87.5 years) with physical limitations. Participants received a randomized sequence of two study conditions: sham or vibration for 8 weeks each separated by a 4-week washout. Before and after the 8 weeks of vibration treatment and sham treatment, muscle mechanography was used to assess muscle function including jump power, weight-corrected jump power, and jump height. Short physical performance battery (SPPB) and handgrip strength were also used to measure muscle function. Bioelectrical impedance spectroscopy was used to estimate skeletal muscle mass. The efect of the vibration treatment on muscle outcomes was analyzed through mixed efects linear regression models. Results: Vibration exercise leads to better jump height (p<.05) compared to sham exercise but also poorer chair rise performance (p=0.012). Other muscle functions tests and muscle mass parameters showed non-signifcant changes. Conclusion: This small pilot study showed no conclusive results on the efect of semi-recumbent vibration exercise on muscle function and mass in older adults living in RCAC. However, the promising signals of improved jump performance could be used to power larger studies of longer duration with various vibration doses to determine the beneft of vibration exercise in this physically impaired, high-risk population with few exercise capabilities.

Forgoing physician visits due to cost: regional clustering among cancer survivors by age, sex, and race/ethnicity

Background Innovative treatments have improved cancer survival but also increased financial hardship for patients. While demographic factors associated with financial hardship among cancer survivors are known in the USA, the role of geography is less clear. Methods We evaluated prevalence of forgoing care due to cost within 12 months by US Census region (Northeast, North Central/Midwest [NCMW], South, West) by demographic factors (age, sex, race/ethnicity) among 217,981 cancer survivors aged 18 to 82 years from the 2015–2019 Behavioral Risk Factor Surveillance System survey. We summarized region- and group-specific prevalence of forgoing physician visits due to cost and used multilevel logistic regression models to compare regions. Results The prevalence of forgoing physician visits due to cost was highest in the South (aged < 65 years: 19–38%; aged ≥ 65: 4–21%; adjusted odds ratios [OR], NCMW versus South, OR: 0.63 [0.56–0.71]; Northeast versus South, OR: 0.63 [0.55– 0.73]; West versus South, OR: 0.73 [0.64–0.84]). Across the USA, including regions with broad Medicaid expansion, younger, female, and persons of color most often reported cost-related forgoing physician visits. Conclusion Forgoing physician visits due to cost among cancer survivors is regionally clustered, raising concerns for concentrated poor long-term cancer outcomes. Underlying factors likely include variation in regional population compositions and contextual factors, such as Medicaid expansion and social policies. Disproportionate cost burden among survivors of color in all regions highlight systemic barriers, underscoring the need to improve access to the entire spectrum of care for cancer survivors, and especially for those most vulnerable.