Flory Nkoy

Prof. Dr. Flory Nkoy


Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 November 2015 in BMC Medical Informatics and Decision Making
Verified
Journal Article
Open access
PDF file
GLGang Luo
Gang Luo
FNFlory Nkoy
Flory Nkoy
BSBryan L. Stone
Bryan L. Stone
DSDarell Schmick
Darell Schmick
MJMichael D. Johnson
Michael D. Johnson
Background Asthma is the most common pediatric chronic disease affecting 9.6 % of American children. Delay in asthma diagnosis is prevalent, resulting in suboptimal asthma management. To help avoid delay in asthma diagnosis and advance asthma prevention research, researchers have proposed various models to predict asthma development in children. This paper reviews these models. Methods A systematic review was conducted through searching in PubMed, EMBASE, CINAHL, Scopus, the Cochrane Library, the ACM Digital Library, IEEE Xplore, and OpenGrey up to June 3, 2015. The literature on predictive models for asthma development in children was retrieved, with search results limited to human subjects and children (birth to 18 years). Two independent reviewers screened the literature, performed data extraction, and assessed article quality. Results The literature search returned 13,101 references in total. After manual review, 32 of these references were determined to be relevant and are discussed in the paper. We identify several limitations of existing predictive models for asthma development in children, and provide preliminary thoughts on how to address these limitations. Conclusions Existing predictive models for asthma development in children have inadequate accuracy. Efforts to improve these models’ performance are needed, but are limited by a lack of a gold standard for asthma development in children.

1 February 2018 in Hospital Pediatrics
Verified
Journal Article
Closed access
FNFlory Nkoy
Flory Nkoy
BSBryan L. Stone
Bryan L. Stone
AKAndrew J. Knighton
Andrew J. Knighton
BFBernhard A. Fassl
Bernhard A. Fassl
JJJoseph M. Johnson
Joseph M. Johnson
LSLucy A. Savitz
Lucy A. Savitz
OBJECTIVES: Collecting social determinants data is challenging. We assigned patients a neighborhood-level social determinant measure, the area of deprivation index (ADI), by using census data. We then assessed the association between neighborhood deprivation and asthma hospitalization outcomes and tested the influence of insurance coverage.METHODS: A retrospective cohort study of children 2 to 17 years old admitted for asthma at 8 hospitals. An administrative database was used to collect patient data, including hospitalization outcomes and neighborhood deprivation status (ADI scores), which were grouped into quintiles (ADI 1, the least deprived neighborhoods; ADI 5, the most deprived neighborhoods). We used multivariable models, adjusting for covariates, to assess the associations and added a neighborhood deprivation status and insurance coverage interaction term.RESULTS: A total of 2270 children (median age 5 years; 40.6% girls) were admitted for asthma. We noted that higher ADI quintiles were associated with greater length of stay, higher cost, and more asthma readmissions (P < .05 for most quintiles). Having public insurance was independently associated with greater length of stay (β: 1.171; 95% confidence interval [CI]: 1.117–1.228; P < .001), higher cost (β: 1.147; 95% CI: 1.093–1.203; P < .001), and higher readmission odds (odds ratio: 1.81; 95% CI: 1.46–2.24; P < .001). There was a significant deprivation–insurance effect modification, with public insurance associated with worse outcomes and private insurance with better outcomes across ADI quintiles (P < .05 for most combinations).CONCLUSIONS: Neighborhood-level ADI measure is associated with asthma hospitalization outcomes. However, insurance coverage modifies this relationship and needs to be considered when using the ADI to identify and address health care disparities.

21 January 2020 in JMIR Medical Informatics
Verified
Journal Article
Open access
GLGang Luo
Gang Luo
SHShan He
Shan He
BSBryan L Stone
Bryan L Stone
FNFlory Nkoy
Flory Nkoy
MJMichael D Johnson
Michael D Johnson
Background: As a major chronic disease, asthma causes many emergency department (ED) visits and hospitalizations each year. Predictive modeling is a key technology to prospectively identify high-risk asthmatic patients and enroll them in care management for preventive care to reduce future hospital encounters, including inpatient stays and ED visits. However, existing models for predicting hospital encounters in asthmatic patients are inaccurate. Usually, they miss over half of the patients who will incur future hospital encounters and incorrectly classify many others who will not. This makes it difficult to match the limited resources of care management to the patients who will incur future hospital encounters, increasing health care costs and degrading patient outcomes. Objective: The goal of this study was to develop a more accurate model for predicting hospital encounters in asthmatic patients. Methods: Secondary analysis of 334,564 data instances from Intermountain Healthcare from 2005 to 2018 was conducted to build a machine learning classification model to predict the hospital encounters for asthma in the following year in asthmatic patients. The patient cohort included all asthmatic patients who resided in Utah or Idaho and visited Intermountain Healthcare facilities during 2005 to 2018. A total of 235 candidate features were considered for model building. Results: The model achieved an area under the receiver operating characteristic curve of 0.859 (95% CI 0.846-0.871). When the cutoff threshold for conducting binary classification was set at the top 10.00% (1926/19,256) of asthmatic patients with the highest predicted risk, the model reached an accuracy of 90.31% (17,391/19,256; 95% CI 89.86-90.70), a sensitivity of 53.7% (436/812; 95% CI 50.12-57.18), and a specificity of 91.93% (16,955/18,444; 95% CI 91.54-92.31). To steer future research on this topic, we pinpointed several potential improvements to our model. Conclusions: Our model improves the state of the art for predicting hospital encounters for asthma in asthmatic patients. After further refinement, the model could be integrated into a decision support tool to guide asthma care management allocation. International Registered Report Identifier (IRRID): RR2-10.2196/resprot.5039

14 October 2015 in BMC Medical Informatics and Decision Making
Verified
Journal Article
Open access
PDF file
GLGang Luo
Gang Luo
BSBryan L. Stone
Bryan L. Stone
BFBernhard Fassl
Bernhard Fassl
CMChristopher G. Maloney
Christopher G. Maloney
PGPer H. Gesteland
Per H. Gesteland
FNFlory Nkoy
Flory Nkoy
Pediatric asthma affects 7.1 million American children incurring an annual total direct healthcare cost around 9.3 billion dollars. Asthma control in children is suboptimal, leading to frequent asthma exacerbations, excess costs, and decreased quality of life. Successful prediction of risk for asthma control deterioration at the individual patient level would enhance self-management and enable early interventions to reduce asthma exacerbations. We developed and tested the first set of models for predicting a child’s asthma control deterioration one week prior to occurrence.

1 December 2015 in Pediatrics
Verified
Journal Article
Closed access
PDF file
FNFlory Nkoy
Flory Nkoy
BFBernhard Fassl
Bernhard Fassl
BSBryan Stone
Bryan Stone
DUDerek A. Uchida
Derek A. Uchida
JJJoseph Johnson
Joseph Johnson
CMChristopher G. Maloney
Christopher G. Maloney
Gaps exist in inpatient asthma care. Our aims were to assess the impact of an evidence-based care process model (EB-CPM) 5 years after implementation at Primary Children's Hospital (PCH), a tertiary care facility, and after its dissemination to 7 community hospitals. Participants included asthmatics 2 to 17 years admitted at 8 hospitals between 2003 and 2013. The EB-CPM was implemented at PCH between January 2008 and March 2009, then disseminated to 7 community hospitals between January and June 2011. We measured compliance using a composite score (CS) for 8 quality measures. Outcomes were compared between preimplementation and postimplementation periods. Confounding was addressed through multivariable regression analyses. At PCH, the CS increased and remained at >90% for 5 years after implementation. We observed sustained reductions in asthma readmissions (P = .026) and length of stay (P < .001), a trend toward reduced costs (P = .094), and no change in hospital resource use, ICU transfers, or deaths. The CS also increased at the 7 community hospitals, reaching 80% to 90% and persisting >2 years after dissemination, with a slight but not significant readmission reduction (P = .119), a significant reduction in length of stay (P < .001) and cost (P = .053), a slight increase in hospital resource use (P = .032), and no change in ICU transfers or deaths. Our intervention resulted in sustained, long-term improvement in asthma care and outcomes at the tertiary care hospital and successful dissemination to community hospitals.

29 August 2017 in JMIR Research Protocols
Verified
Journal Article
Open access
GLGang Luo
Gang Luo
BSBryan L Stone
Bryan L Stone
MJMichael D Johnson
Michael D Johnson
PTPeter Tarczy-Hornoch
Peter Tarczy-Hornoch
AWAdam B Wilcox
Adam B Wilcox
FNFlory Nkoy
Flory Nkoy
To improve health outcomes and cut health care costs, we often need to conduct prediction/classification using large clinical datasets (aka, clinical big data), for example, to identify high-risk patients for preventive interventions. Machine learning has been proposed as a key technology for doing this. Machine learning has won most data science competitions and could support many clinical activities, yet only 15% of hospitals use it for even limited purposes. Despite familiarity with data, health care researchers often lack machine learning expertise to directly use clinical big data, creating a hurdle in realizing value from their data. Health care researchers can work with data scientists with deep machine learning knowledge, but it takes time and effort for both parties to communicate effectively. Facing a shortage in the United States of data scientists and hiring competition from companies with deep pockets, health care systems have difficulty recruiting data scientists. Building and generalizing a machine learning model often requires hundreds to thousands of manual iterations by data scientists to select the following: (1) hyper-parameter values and complex algorithms that greatly affect model accuracy and (2) operators and periods for temporally aggregating clinical attributes (eg, whether a patient's weight kept rising in the past year). This process becomes infeasible with limited budgets. This study's goal is to enable health care researchers to directly use clinical big data, make machine learning feasible with limited budgets and data scientist resources, and realize value from data. This study will allow us to achieve the following: (1) finish developing the new software, Automated Machine Learning (Auto-ML), to automate model selection for machine learning with clinical big data and validate Auto-ML on seven benchmark modeling problems of clinical importance; (2) apply Auto-ML and novel methodology to two new modeling problems crucial for care management allocation and pilot one model with care managers; and (3) perform simulations to estimate the impact of adopting Auto-ML on US patient outcomes. We are currently writing Auto-ML's design document. We intend to finish our study by around the year 2022. Auto-ML will generalize to various clinical prediction/classification problems. With minimal help from data scientists, health care researchers can use Auto-ML to quickly build high-quality models. This will boost wider use of machine learning in health care and improve patient outcomes.