Eileen Koski

ORCID: 0000-0003-3621-9613
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Diabetes and associated disorders
  • Pancreatic function and diabetes
  • Diabetes Management and Research
  • Artificial Intelligence in Healthcare and Education
  • Colorectal Cancer Screening and Detection
  • Inflammatory Bowel Disease
  • Ethics in Clinical Research
  • Data-Driven Disease Surveillance
  • Ethics and Social Impacts of AI
  • Health disparities and outcomes
  • Healthcare cost, quality, practices
  • Health Systems, Economic Evaluations, Quality of Life
  • Eicosanoids and Hypertension Pharmacology
  • Free Radicals and Antioxidants
  • Statistical Methods in Clinical Trials
  • Medicine and Dermatology Studies History
  • Machine Learning in Healthcare
  • Chronic Disease Management Strategies
  • Medical Coding and Health Information
  • Electronic Health Records Systems
  • Biomedical and Engineering Education
  • Maternal Mental Health During Pregnancy and Postpartum
  • Microscopic Colitis
  • Global Cancer Incidence and Screening
  • Medical and Biological Ozone Research

IBM (United States)
2021-2024

IBM Research - Thomas J. Watson Research Center
2016-2024

Alliance for Safe Kids
2019-2022

University of Oulu
2021

Helmholtz Zentrum München
2021

University of Colorado Anschutz Medical Campus
2021

Northwest Research Institute of Chemical Industry
2021

Lund University
2021

Faculty of 1000 (United States)
2010

Quest Diagnostics (United States)
2003-2008

Abstract Background Integrating artificial intelligence (AI) in healthcare settings has the potential to benefit clinical decision-making. Addressing challenges such as ensuring trustworthiness, mitigating bias, and maintaining safety is paramount. The lack of established methodologies for pre- post-deployment evaluation AI tools regarding crucial attributes transparency, performance monitoring, adverse event reporting makes this situation challenging. Objectives This paper aims make...

10.1093/jamia/ocae209 article EN cc-by-nc-nd Journal of the American Medical Informatics Association 2024-09-26

<h3>Importance</h3> The lack of standards in methods to reduce bias for clinical algorithms presents various challenges providing reliable predictions and addressing health disparities. <h3>Objective</h3> To evaluate approaches reducing machine learning models using a real-world scenario. <h3>Design, Setting, Participants</h3> Health data this cohort study were obtained from the IBM MarketScan Medicaid Database. Eligibility criteria as follows: (1) Female individuals aged 12 55 years with...

10.1001/jamanetworkopen.2021.3909 article EN cc-by-nc-nd JAMA Network Open 2021-04-15

Recent advances in the science and technology of artificial intelligence (AI) growing numbers deployed AI systems healthcare other services have called attention to need for ethical principles governance. We define provide a rationale that should guide commission, creation, implementation, maintenance, retirement as foundation governance throughout lifecycle. Some are derived from familiar requirements practice research medicine healthcare: beneficence, nonmaleficence, autonomy, justice come...

10.1093/jamia/ocac006 article EN Journal of the American Medical Informatics Association 2021-11-02

OBJECTIVE To combine prospective cohort studies, by including HLA harmonization, and estimate risk of islet autoimmunity progression to clinical diabetes. RESEARCH DESIGN AND METHODS For cohorts in Finland, Germany, Sweden, the U.S., 24,662 children at increased genetic for development autoantibodies type 1 diabetes have been followed. Following outcomes were analyzed 16,709 infants-toddlers enrolled age 2.5 years. RESULTS In infant-toddler cohort, 1,413 (8.5%) developed least one...

10.2337/dc20-1836 article EN Diabetes Care 2021-06-23

The potential value of AI to healthcare, and nursing in particular, ranges from improving quality efficiency care delivering on the promise personalized precision medicine. systems may become virtually indispensable as ever more data is amassed about every aspect health. can help reduce variability care, while precision, accelerating discovery reducing disparities. empower patients potentially allow healthcare professionals relate their healers supported by combined wisdom best medical...

10.3233/shti210726 article EN cc-by-nc Studies in health technology and informatics 2021-12-15

Abstract Development of islet autoimmunity precedes the onset type 1 diabetes in children, however, presence autoantibodies does not necessarily lead to manifest disease and clinical symptoms is hard predict. Here we show, by longitudinal sampling (IAb) insulin, glutamic acid decarboxylase antigen-2 that progression follows distinct trajectories. Of combined Type Data Intelligence cohort 24662 participants, 2172 individuals fulfill criteria two or more follow-up visits IAb positivity at...

10.1038/s41467-022-28909-1 article EN cc-by Nature Communications 2022-03-21

Randomized controlled trials can benefit from proactive assessment of how well their participant selection strategies during the design eligibility criteria influence study generalizability. In this paper, we present a quantitative metric called generalizability index for traits 2.0 (GIST 2.0) to assess priori (based on population representativeness) clinical trial by accounting dependencies among multiple criteria. The was evaluated 16 sepsis identified ClinicalTrials.gov , with adverse...

10.1111/nyas.13195 article EN Annals of the New York Academy of Sciences 2016-09-06

In our previous data-driven analysis of evolving patterns islet autoantibodies (IAb) against insulin (IAA), GAD (GADA), and antigen 2 (IA-2A), we discovered three trajectories, characterized according to multiple IAb (TR1), IAA (TR2), or GADA (TR3) as the first appearing autoantibodies. Here examined evolution levels within these trajectories in 2,145 IAb-positive participants followed from early life compared those who progressed type 1 diabetes (n = 643) with remaining undiagnosed 1,502)....

10.2337/db22-0360 article EN Diabetes 2022-09-16

Although corticosteroids are an important treatment for inflammatory bowel disease (IBD) patients, many subjects develop dependence, leading to serious long-term side effects. We applied causal inference analyses investigate the length of steroid use on reoperations in IBD patients. identified UK Biobank general practice dataset with at least one major GI surgery and followed them 5 years evaluate subsequent operations. defined dependence as 12 weeks (vs. acute use) prior baseline surgery....

10.1038/s41598-024-75215-5 article EN cc-by-nc-nd Scientific Reports 2024-11-25

Abstract Context Rapid growth has been suggested to promote islet autoimmunity and progression type 1 diabetes (T1D). Childhood not analyzed separately from the infant period in most previous studies, but it may have distinct features due differences between stages of development. Objective We aimed analyze association childhood with development T1D diagnosis children 8 years age. Methods Longitudinal data were a prospective cohort study including 10 145 Finland, Germany, Sweden, United...

10.1210/clinem/dgac121 article EN cc-by The Journal of Clinical Endocrinology & Metabolism 2022-03-04

Abstract BACKGROUND AND AIMS The United Kingdom (UK) Biobank (UKBB) is a large-scale biomedical database and research resource, containing in-depth health information from half million participants in UK that have been used for detailed analyses of IBD. Using the UKBB, we examined lab findings prescription medication use IBD subjects to identify trajectory patterns disease with respect surgical relapse. METHODS Of 363 UKBB an established diagnosis (UC, CD, or both) initial GI surgery, 116...

10.1093/ibd/izae020.144 article EN Inflammatory Bowel Diseases 2024-01-25
Coming Soon ...