Blog

Congratulations to postdoctoral fellow Jia Li on the publication of "aKNNO: single-cell and spatial transcriptomics clustering with an optimized adaptive k-nearest neighbor graph" in Genome Biology on August 1, with professors Yu Shyr and Qi Liu as corresponding authors. The paper offers a new method "to simultaneously identify abundant and rare cell types based on an adaptive k-nearest neighbor graph with optimization," doing so "more accurately than general and specialized methods." {aKKNO} and related tutorials are free and available on GitHub and Zenodo.

Figure 1 in the paper provides an overview of how aKNNO works.

Congratulations to professor Tatsuki Koyama on the publication of "Long-term air pollution exposure and the risk of primary graft dysfunction after lung transplantation" in The Journal of Heart and Lung Transplantation on July 15. Co-authors include assistant in biostatistics Zhiguo "Alex" Zhao, plus colleagues at the University of California, San Francisco, and the University of Pennsylvania, along with corresponding author Lorraine Ware at Vanderbilt. The study explored whether "long-term exposure of the lung donor and recipient to high levels of ambient air pollutants would increase the risk of PGD in lung transplant recipients."

Figure 2 in the paper: "Location of transplantation recipients in the primary analytical cohort (N = 1,524)." 

Congratulations to assistant professor Amber Hackstadt on the publication of "Effects of a Patient Portal Intervention to Address Diabetes Care Gaps: Protocol for a Pragmatic Randomized Controlled Trial" in JMIR Research Protocols on June 28. Co-authors include senior biostatistician Zhihong Yu, as well as colleagues in Vanderbilt's Division of General Internal Medicine, Department of Ophthalmology and Visual Sciences, and Department of Biomedical Informatics. The study seeks to address consistency in preventive care among people with diabetes by applying "user-centered design sprint methodology to develop a patient portal intervention.

Figure 2 in the paper depicts the study recruitment results as a flow chart. 

Congratulations to associate professor Andrew Spieker on the publication of "The impact of different strategies for modeling associations between medications at low doses and health outcomes: a simulation study and practical application to postpartum opioid use." This article was published online ahead of print on June 21 in the American Journal of Epidemiology. Co-authors include recently retired associate Sharon Phillips, plus colleagues in Vanderbilt's Departments of Health Policy and Obstetrics and Gynecology. It reports on the simulation study conducted by Dr. Spieker and his collaborators "to assess the performance of several regression approaches to model the drug dose-response curve at low doses in a setting where no safe range exists" and to "demonstrate and empirically assess the use of these regression strategies in a practical scenario."

Figure S1 in the paper features graphical representations of various models. 

Panels (A) and (B) illustrate the simple linear model in the absence and presence (respectively) of a spike effect. Panel (C) illustrates the case in which dose group is categorized (with zero included as a category). Panels (C) and (D) illustrate the natural cubic spline model in the absence and presence (respectively) of a spike effect. Panel (F) illustrates the “slab-and-spline” model that is piecewise constant over the low-dose range but otherwise shares the properties of a natural cubic spline. Of note, the models presented in panels (A) and (D) invoke the safe-dose assumption as no spike effect is present.

Michael Matheny, professor of biomedical informatics, medicine, and biostatistics, will lead the Biomedical Informatics and Data Science to Inform LHS Core. As described in this VUMC News article, the core "will support scientists in the design, management and execution of research. This core will advance biomedical informatics, biostatistics and data science supporting information synthesis and interpretation, diagnostic evaluation, clinical workflow and care delivery."

This July 22 feature at VUMC News focuses on a study co-authored by senior biostatistician Elizabeth McNeer (who earned her MS from our program in 2018) and professor William Dupont.

The 2024 Joint Statistical Meetings, which convene in Portland, Oregon, from August 3 through August 8, are expected to bring together more than five thousand attendees from fifty-two countries, with the theme of "Statistics and data science: Informing policy and countering misinformation." We are proud of the department members, trainees, and alumni who will be sharing their work and ideas with colleagues from around the world, as well as participating in assorted research and professional service activities. This year's program includes the following:

Sunday, August 4 

DEPICT: A framework for ethical reasoning for statistics and data science - half-day course taught by associate professor Mario Davidson. 8:30 am – noon.

Modern statistical methods for image analysis - contributed papers session chaired by associate professor Simon Vandekar. 2:00–3:50 pm.

The talks in this session include Semiparametric confidence sets for arbitrary effect sizes in longitudinal neuroimaging, with PhD student Xinyu Zhang as first and presenting author. Co-authors include recent graduate Kenneth Liao (MS 2024), with Vandekar plus colleagues at VUMC and the University of Colorado.

Life before and after COVID-19: Changes in relationships, technology use, and well-being - presentation during the contributed speed session SPEED 1: Data challenge 1, statistical applications & statistics in policy, part 1. 2:00–3:50 pm. 

• Presenting author: biostatistician and alumna Caroline Birdrow (MS 2021)
• First author: PhD candidate Jiangmei Xiong
• Co-author: PhD candidate Maximilian Rohde

This speed session also features a paper co-authored by PhD student Yunbi Nam as a MS student at University of Washington.

Advances in functional and spatial data analysis and their applications in biomedical sciences, a contributed papers session, includes a paper co-authored by Vandekar.

Statistical innovations in electronic health records data analysis, a topic-contributed paper session, includes a talk by associate professor Dandan Liu. 4:00–5:00 pm. 

Invited E-Poster Session I (8:30–9:25 pm) includes these presentations by alumni: 

• Choosing an indifference zone for second-generation p-values to maximize the statistical properties - Megan Murray (PhD 2022)
• Combining straight-line and map-based distances to quantify neighborhood-level food access and its impact on health - Sarah Lotspeich (PhD 2021)

Monday, August 5
Recent advances in design and analysis of two-phase studies - invited paper session. 8:30–10:20 am.

• A two-phase study of longitudinal ordinal outcome data in critically ill patients with sepsis - a talk by professor Jonathan Schildcrout. 8:35–9:00 am.
• Efficient designs and analysis of two-phase studies with longitudinal binary data - a talk by associate professor Ran Tao. 9:25–9:50 am.

Recent advances in the analysis of fMRI data - contributed papers session chaired by assistant professor Panpan Zhang. 8:30–10:20 am.

The Contributed poster presentations: ENAR session includes Artificial intelligence for improved patient outcomes. 10:30–11:15 am.

• First and presenting author: lead biostatistician Henry Domenico
• Co-authors: senior biostatistician and alumnus Ryan Moore (MS 2020) and former senior associate Daniel Byrne

The Contributed poster presentations: Biometrics Section session includes Increasing statistical efficiency using ordinal transition models: A simulation study. 2:00–3:50 pm.

• First and presenting author: PhD candidate Maximilian Rohde
• Co-authors: professors Benjamin French and Frank Harrell

New considerations for the four pillars of survival analysis: Estimands, design, estimation, and inference, a contributed papers session, includes a talk co-authored by professor Qingxia Chen.

The invited panel for Synthetic data in preserving privacy: Connections across federal statistics and health data includes Accenture Professor Bradley Malin. 2:00–3:50 pm.

The Student Paper Award and John M. Chambers Statistical Software Award topic-contributed paper session is chaired by Sarah Lotspeich. 2:00–3:50 pm.

Simon Vandekar is coordinating a get-together for department members, trainees, and alumni at JSM. It will take place at 6 pm. Contact him for details.

Tuesday, August 6
The Contributed poster presentations: Section on Statistics in Genomics and Genetics session includes Facilitating valid statistical inference in biomedical image synthesis. 10:30 am – 12:20 pm.

• First and presenting author: PhD candidate Jiangmei Xiong
• Co-authors: associate professor Simon Vandekar, assistant professor Siyuan Ma, and colleagues at VUMC, Regeneron, and GSK

Opportunities and challenges in data sciences with diverse imaging technology, an invited paper session, includes Effect sizes and replicability in longitudinal studies of brain-phenotype associations. 11:35–11:55 am.

• Speaker: Simon Vandekar
• Co-authors include PhD candidates Kaidi Kang and Jiangmei Xiong, PhD student Megan Jones, professor Jonathan Schildcrout, and associate professor Ran Tao, with colleagues at Vanderbilt, Cambridge, Penn, and Minnesota.

The analytical staff plans to gather for happy hour at Deschutes Brewery Portland (210 NW 11th Avenue) at 5:30 pm. According to organizer Andrew Guide, "It's about a 15-minute train ride from the convention center and pretty close to some of the downtown hotels. Feel free to bring significant others or anyone else you may be traveling with." 

During the ASA President's Address and Awards, professor Fei Ye will be inducted as an ASA Fellow. 8:00–9:00 pm.

Wednesday, August 7

SPEED 8: Survival outcomes, network analyses, and 'omics applications, part 1 includes these presentations by our students:

• Accounting for unobserved confounding to reduce false discoveries in microbiome research. 8:45–8:50 am.
  • First and presenting author: PhD student Chih-Ting Yang

  • Co-authors: principal application developer Zhouwen Liu, senior associate Tebeb Gebretsadik, professor Yu Shyr, and assistant professor Siyuan Ma, plus colleagues at VUMC and the University of Chicago

     

• PheMIME & Phe-OmicsMIME: Interactive visualizations for phenome, multi-omics multimorbidity analysis. 10:05–10:10 am.
  • First and presenting author: PhD candidate Siwei Zhang

  • Co-authors: alumnus Nick Strayer (PhD 2020) and assistant professor Yaomin Xu, plus colleagues in VUMC's Division of Genetic Medicine and Department of Pharmacology

     

Role play for training effective statistical leadership, communication, and collaboration - Mario Davidson, invited panelist. 10:30 am – 12:20 pm

Future of statistics and data science in the era of ChatGPT and LLMs - Siyuan Ma, chair/moderator of invited panel. 10:30 am – 12:20 pm

Thursday, August 8

Crafting relevant research: Informative and translational statistics for public policy - invited panel organized by PhD candidate Tianyi Sun. 10:30 am – 12:20 pm

The Techniques and case studies to address missing data complications in scientific studies contributed papers session includes Predicting risk for a new patient with missing risk factor: A submodel approach for binary outcome. 10:30 am – 12:20 pm

• First and presenting author: Tianyi Sun
• Co-authors include associate professor Dandan Liu, plus colleagues at VUMC

The Advances in modern logitudinal data analysis and applications contributed papers session includes a talk co-authored by Sarah Lotspeich. 

Also...

• Fei Ye represents the Section of Statistics in Epidemiology on the JSM Program Committee.

Congratulations and best wishes to everyone participating in the conference - we look forward to hearing about your experience, and to welcoming JSM attendees to Nashville in 2025!

We are pleased to announce the promotion of Yajing Li to senior biostatistician, in effect as of June 28. Li earned a bachelor's degree in statistics at East China Normal University in Shanghai, followed by her MS in statistics at the University of Michigan. Since joining our department in 2021, Li has contributed her analytical expertise to studies of the correlation between genetic/environmental factors and the risk of clonal hematopoiesis (CH) transformation; the likelihood of CH mutations among patients undergoing radiation therapy; genotypic-phenotypic links; the interplay between JAK2-V617F mutation and aUPD and their impact on blood cancers; the correlation between human leukocyte antigens, CHIP mutations, and specific diseases in BioVU and UK Biobank cohorts, and more. Her programming experience includes the creation of an R package to facilitate the efficient extraction and processing of data from large data platforms, and her peer-reviewed publications include papers in Blood Cancer Journal, Genetics in Medicine Open, and Transplantation and Cellular Therapy.

Figure 5 from Li's recent paper in Annals of Allergy, Asthma & Immunology: Adrenal steroid metabolites associated with childhood asthma within Kyoto Encyclopedia of Genes and Genomes molecular pathways. Metabolites that were significantly associated with childhood asthma are highlighted in yellow. Green diamonds indicate enzymes involved in the pathway and gray boxes indicate progenitor or downstream steroid metabolites.

We are pleased to announce the promotion of Cara Lwin to biostatistician, in effect as of June 1. Lwin earned a bachelor's degree in microbiology from the University of Pittsburgh in 2017, with minors in chemistry, computer science, neuroscience, and economics, followed by three years as a senior research associate at eyeGENE and the Ophthalmic Genetics Laboratory at the National Eye Institute. Lwin entered our graduate training program in 2020, began working for the department as an associate biostatistician in 2022, and earned her master's degree in biostatistics this May. Her thesis was titled "Bayesian Survival Analysis Using Data from Electronic Health Records: A Study on Cardiovascular Outcomes Leveraging Information from Randomized Clinical Trials" and can be accessed via Vanderbilt's Institutional Repository. Her activities as a student included serving as Biostatistics Graduate Student Association vice president As a staff biostatistician, she is a member of the Vanderbilt Biostatistics Data Coordinating Center Design & Analysis Unit. See her staff profile for links to her peer-reviewed publications on influenza and COVID-19.

Elisa Yazdani and Cara Lwin listen to speeches in their honor at the department reception for MS graduates, April 16, 2024

We are delighted to announce the promotion of Afan Swan to senior research data specialist, in effect as of June 1. Swan earned a bachelor's degree in microbiology and master's degree in public health from the University of Alabama, joining our department in 2021 as a health services research analyst. Swan's expertise has been vital to multicenter collaborations with the Investigating Respiratory Viruses in the Acutely Ill (IVY) Network, the Vanderbilt Biostatistics Data Coordinating Center, and elsewhere, and she has co-authored multiple peer-reviewed publications as a VUMC analyst, including the following:

• Surie D et al. Severity of Respiratory Syncytial Virus vs COVID-19 and Influenza Among Hospitalized US Adults. JAMA Netw Open. 2024 Apr 1;7(4):e244954. doi: 10.1001/jamanetworkopen.2024.4954. PMID: 38573635.
• Raglow Z et al. SARS-CoV-2 shedding and evolution in patients who were immunocompromised during the omicron period: a multicentre, prospective analysis. Lancet Microbe. 2024 Mar;5(3):e235-e246. doi: 10.1016/S2666-5247(23)00336-1. Epub 2024 Jan 26. PMID: 38286131.
• DeCuir J et al. Interim Effectiveness of Updated 2023-2024 (Monovalent XBB.1.5) COVID-19 Vaccines Against COVID-19-Associated Emergency Department and Urgent Care Encounters and Hospitalization Among Immunocompetent Adults Aged ≥18 Years - VISION and IVY Networks, September 2023-January 2024. MMWR Morb Mortal Wkly Rep. 2024 Feb 29;73(8):180-188. doi: 10.15585/mmwr.mm7308a5. PMID: 38421945; PMCID: PMC10907041.
• Lewis NM et al. Vaccine Effectiveness Against Influenza A-Associated Hospitalization, Organ Failure, and Death: United States, 2022-2023. Clin Infect Dis. 2024 Apr 10;78(4):1056-1064. doi: 10.1093/cid/ciad677. PMID: 38051664.
• Kojima N et al. Changing Severity and Epidemiology of Adults Hospitalized With Coronavirus Disease 2019 (COVID-19) in the United States After Introduction of COVID-19 Vaccines, March 2021-August 2022. Clin Infect Dis. 2023-08-22; 77(4):547-557. doi:10.1093/cid/ciad276. PubMed PMID: 37255285 
• Dimcheff DE et al. Total and Subgenomic RNA Viral Load in Patients Infected With SARS-CoV-2 Alpha, Delta, and Omicron Variants. J Infect Dis. 2023 Aug 11;228(3):235-244. doi: 10.1093/infdis/jiad061. PMID: 36883903; PMCID: PMC10420395.
• Surie D et al. Comparison of mRNA vaccine effectiveness against COVID-19-associated hospitalization by vaccination source: Immunization information systems, electronic medical records, and self-report-IVY Network, February 1-August 31, 2022. Vaccine. 2023 Jun 29;41(29):4249-4256. doi: 10.1016/j.vaccine.2023.05.028. Epub 2023 May 15. PMID: 37301704; PMCID: PMC10183633.
• Tenforde MW et al. Vaccine Effectiveness Against Influenza A(H3N2)-Associated Hospitalized Illness: United States, 2022. Clin Infect Dis. 2023 Mar 21;76(6):1030-1037. doi: 10.1093/cid/ciac869. PMID: 36327388; PMCID: PMC10226741.
• Surie D et al. Effectiveness of Monovalent mRNA Vaccines Against COVID-19-Associated Hospitalization Among Immunocompetent Adults During BA.1/BA.2 and BA.4/BA.5 Predominant Periods of SARS-CoV-2 Omicron Variant in the United States - IVY Network, 18 States, December 26, 2021-August 31, 2022. MMWR Morb Mortal Wkly Rep. 2022 Oct 21;71(42):1327-1334. doi: 10.15585/mmwr.mm7142a3. PMID: 36264830; PMCID: PMC9590291.

Afan Swan (center) reports on a breakout discussion during a VBDCC meeting, May 2024