Jerome Niyirora

Dr. Jerome Niyirora

SUNY Polytechnic Institute, Utica, Michigan, USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
18 November 2019 in Health Informatics Journal
Verified
Journal Article
Open access
PDF file
JNJerome Niyirora
Jerome Niyirora
OAOssayne Aragones
Ossayne Aragones
Medical care services can be organized into a network. Understanding the structure of this network cannot only help analyze common clinical protocols but can also help reveal previously unknown patterns of care. The objective of this research is to introduce the concept and methods for constructing and analyzing the network of medical care services. We start by demonstrating how to build the network itself and then develop algorithms, based on principal component analysis and social network analysis, to detect communities of services. Finally, we propose novel graphical techniques for representing and assessing patterns of care. We demonstrate the application of our algorithms using data from an Emergency Department in New York State. One of the implications of our research is that clinical experts could use our algorithms to detect deviations from either existing protocols of care or administrative norms.

9 April 2021 in BMC Medical Informatics and Decision Making
Verified
Journal Article
Open access
PDF file
JNJerome Niyirora
Jerome Niyirora
Transitioning from an old medical coding system to a new one can be challenging, especially when the two coding systems are significantly different. The US experienced such a transition in 2015. This research aims to introduce entropic measures to help users prepare for the migration to a new medical coding system by identifying and focusing preparation initiatives on clinical concepts with more likelihood of adoption challenges. Two entropic measures of coding complexity are introduced. The first measure is a function of the variation in the alphabets of new codes. The second measure is based on the possible number of valid representations of an old code. A demonstration of how to implement the proposed techniques is carried out using the 2015 mappings between ICD-9-CM and ICD-10-CM/PCS. The significance of the resulting entropic measures is discussed in the context of clinical concepts that were likely to pose challenges regarding documentation, coding errors, and longitudinal data comparisons. The proposed entropic techniques are suitable to assess the complexity between any two medical coding systems where mappings or crosswalks exist. The more the entropy, the more likelihood of adoption challenges. Users can utilize the suggested techniques as a guide to prioritize training efforts to improve documentation and increase the chances of accurate coding, code validity, and longitudinal data comparisons.

2 May 2025 in JAMIA Open
Verified
Journal Article
Open access
JNJerome Niyirora
Jerome Niyirora
LLLynne Longtin
Lynne Longtin
CGCynthia Grabski
Cynthia Grabski
DPDavid Patrishkoff
David Patrishkoff
ASAndriana Semko
Andriana Semko
Objective: This study compares the performance of machine learning (ML) models and human experts in mapping unstructured nursing notes to the standardized Nursing Interventions Classification (NIC) system. The aim is to advance automated nursing documentation classification, facilitating cross-facility benchmarking of patient care and organizational outcomes. Materials and Methods: We developed and compared 4 ML models: TF-IDF text-based vectorization, UMLS semantic mapping, fine-tuned GPT-4o mini, and Bio-Clinical BERT. These models were evaluated against classifications provided by 2 expert nurses using a dataset of de-identified home healthcare nursing notes obtained from a Florida, USA-based medical clearinghouse. Model performance was assessed using agreement statistics, precision, recall, F1 scores, and Cohen’s Kappa. Results: Human raters achieved the highest agreement with consensus labels, scoring 0.75 and 0.62, with corresponding F1 scores of 0.61 and 0.45, respectively. In comparison, ML models showed lower performance, with GPT achieving the best among them (agreement: 0.50, F1 score: 0.31). A distribution analysis of NIC categories revealed that ML models performed well in prevalent and clearly defined categories, such as drug management, but struggled with minority classes and context-dependent interventions, like information management. Discussion: Current ML approaches show promise in supporting clinical classification tasks, but the performance gap in handling complex, context-dependent interventions highlights the need for improved methods that can better capture the nuanced nature of clinical documentation. Future research should focus on developing methods to process clinical terminology and context-specific documentation with greater precision and adaptability. Conclusion: Current ML models can aid—but not fully replace—human judgment in classifying nuanced nursing interventions.

Verified
Journal Article
Open access
PDF file
ABAlison Christine Bested
Alison Christine Bested
ARArif M. Rana
Arif M. Rana
PHPatrick Hardigan
Patrick Hardigan
JNJerome Niyirora
Jerome Niyirora
ACAmanpreet Cheema
Amanpreet Cheema
CMCalixto Machado
Calixto Machado
Importance: The Defense and Veterans Brain Injury Center reported 358,088 mild traumatic brain injury (mTBI) among U.S. service members worldwide between the years 2000 and 2020. Veterans with mTBI have higher rates of Post-Traumatic Stress Disorder (PTSD), depressive disorder, substance use disorder, anxiety disorder, and suicide than their healthy counterparts. Currently, there is no effective treatment for mTBI. Objective: To assess the efficacy of hyperbaric oxygen therapy (HBOT) as a treatment option for mTBI. Design, Setting, Participants: This is a case series of 39 U.S. Veterans diagnosed with mTBI and treated with HBOT. Of these participants, 36 were men and 3 women, and their ages ranged between 28 and 69. The treatment was administered by The 22 Project (a veteran-centered nonprofit organization) using monoplace hyperbaric chambers located in Delray Beach, Florida. Neuroimaging using Single Photon Emission Computer Tomography (SPECT) brain scans performed pre- and post-HBOT were made available for secondary analysis. Nilearn Python Library was utilized to visualize the corresponding neuroimaging data. A two-sided paired t-test in R was used to compare the pre- and post-treatment results. Intervention: A full treatment of HBOT involved 40 sessions. Each session consisted of the administration of 100% oxygen at 1.5 atmospheres for 90 min, twice a day, for 20 days, Mondays to Fridays only. Main Outcome and Measure: Perfusion in the brain’s Brodmann Areas (BA) comparing pre- and post-HBOT using NeuroGam software analysis from brain SPECT scan neuroimaging and multi-symptom self-reports. Results: A comparison between the pre- and post-HBOT brain scans showed significant improvement in the brain perfusion, and the difference was statistically significant (p < 0.001). Separately, participants reported reduced pain, improved mood, and better sleep, an outcome that translated into an average of about 46.6% improvement in the measured symptoms. Conclusions and Relevance: This series demonstrated that HBOT could be a useful treatment for mTBI in U.S. veterans. The participants in the study showed marked improvement in both brain perfusion measured on SPECT scan imaging and measured mTBI symptoms. This is the first study to use brain SPECT scans with quantitative numerical measurements to demonstrate improvement in brain perfusion in veterans with mild TBI treated with HBOT and measured mTBI symptoms. Future research studies are currently being done to validate these important findings.

28 February 2023 in Journal of the American Nurses Association - New York
Verified
Journal Article
Open access
LMLinda Millenbach
Linda Millenbach
RMRhonda Maneval
Rhonda Maneval
DRDoreen Rogers
Doreen Rogers
KSKathleen Sellers
Kathleen Sellers
DEDeborah Elliott
Deborah Elliott
JNJerome Niyirora
Jerome Niyirora

22 December 2025 in OJIN: The Online Journal of Issues in Nursing
Verified
Journal Article
Closed access
FCFrances Crosby
Frances Crosby
JNJerome Niyirora
Jerome Niyirora
RMRhonda Maneval
Rhonda Maneval
LMLinda Millenbach
Linda Millenbach
NBNoreen Brennan
Noreen Brennan
DEDeborah Elliott
Deborah Elliott
In Spring 2020, some nurses in the United States experienced financial hardship associated with the COVID-19 pandemic. Nurses House, Inc. responded and provided $2,734,500 in emergency grants to the 2,484 nurses who applied and met the eligibility criteria. The question arose, How long did this experience continue to impact the financial well-being of these nurses? Studies have been reported about the long-term physical, psychological, social, and workforce impact of the COVID-19 pandemic on nurses, but little was found about its long-term financial impact. An electronic survey was conducted to explore the endurance of the COVID-19 related financial hardship the grant recipient nurses had experienced and to determine if the financial crisis was more enduring for some nurses than others. The survey consisted of five categories of variables presented in 38 statements, along with 9 items eliciting demographic information. Specific categories measured included Current Personal Physical Health, Personal Emotional Health, Family Health and Well Being, Economic Well Being, and Support Systems. Aggregated data about demographic characteristics, along with statistically significant correlations and factor analyses, offered information about which nurses may be more vulnerable in times of financial crisis. The survey findings can inform proactive planning and advocacy for a safety net for nurses whose financial well-being may be threatened in times of an unanticipated crisis, such as a pandemic.