CAChidimma Doris Azubuike

Chidimma Doris Azubuike

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Chidimma Doris Azubuike has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Blind spots in AI-assisted healthcare evidence search: multiplatform evaluation of clinical retrieval gaps and risk-of-bias

    by Ahmed N. Farrag, Ahmed Soliman, Chidimma Azubuike, Kimia Zandbiglari, Surya Yadavilli, Lauren E. Adkins, Fatemeh Mehrabi, Larisa Cavallari, Amie Goodin, Masoud Rouhizadeh

    Retrieval-augmented and LLM-based (RAG-LLM) evidence-search tools, including Consensus, Ai2 Paper Finder, ChatGPT, Gemini, and Claude, are increasingly used by clinicians and researchers. Whether a realistic query reliably surfaces relevant evidence or leaves systematic gaps that could shape clinical evidence and research synthesis remains unclear. Using a prospectively assembled, non-public gold-standard corpus to avoid benchmark contamination, we assessed five platforms across 15 query formulations. Primary outcomes were formulation-level recall (evidence retrieved per query formulation) and single-query zero-retrieval probability (formulations returning no relevant evidence from a domain); pooled platform recall (evidence retrieved at least once across all formulations) was a secondary capacity benchmark. Median formulation-level recall ranged from 7.2% to 42.2%, while pooled platform recall ranged from 45.8% to 72.3%. For the largest evidence category, single-query zero-retrieval probability ranged from 47% to 80% across platforms; one platform showed a marked pre-2016 evidence gap; and 12.0% of evidence was never retrieved by any platform, with never-retrieval significantly higher for conference proceedings than journal articles (38.9% vs 4.6%; p < 0.001). Evidence gaps varied by platform, evidence category, publication year, and venue type, highlighting potential retrieval bias and visibility blind spots, and supporting domain-specific evaluation before RAG-LLM outputs are used in clinical or research workflows.

  • Natural Language Processing to Identify Substance Use in Electronic Health Records: A Scoping Review

    by Chidimma Doris Azubuike, Ahmed Farrag, Kimia Zandbiglari, Ahmed Soliman, Celina Bagchi, Fatemeh Mehrabi, Lauren E Adkins, Masoud Rouhizadeh, Amie Goodin

    Background: This scoping review aimed to characterize natural language processing (NLP) techniques deployed for identifying substance use in electronic health records (EHRs) and to compare the performance of these techniques by substance type. Methods: We conducted a systematic search of PubMed, the Cochrane Library, Embase, Web of Science, ACM Digital Library, IEEE Xplore, and Scopus for peer-reviewed original research published in English. Studies were eligible if they applied NLP to identify non-prescription or problematic substance use in EHRs, provided full-text access, and reported quantitative performance metrics. Results: A total of 86 studies met the inclusion criteria. NLP-identified substance use included tobacco (n = 42), alcohol (n = 26), non-prescription opioids (n = 30), cannabinoids (n = 9), stimulants (n = 6), and polysubstance use and/or other drugs (n = 16). NLP techniques included rule-based (n = 46), conventional machine learning (n = 39), deep learning (n = 17), and large language/transformer-based models (n = 22), with some studies applying multiple techniques. Annotation guidelines were available for 30 studies, and only 22 published their codes. Most studies reported performance metrics exceeding 0.80. Conclusions: Tobacco, opioids, and alcohol were the most frequently identified substances, whereas stimulants and cannabinoids were markedly underrepresented. Across the reviewed literature, transparency and reproducibility were limited, with few studies publishing code or detailed model specifications. Nevertheless, reported performance metrics were generally high. NLP techniques showed high performance in identifying tobacco, opioids, and alcohol use in EHRs, but stimulants and cannabinoids remain underrepresented. Transparency and reproducibility remain limited, underscoring the need for routine sharing of code, datasets, and model specifications.

  • Open Access

    Protocol for Monitoring Postpartum Hypertension Outcomes via a Smartphone App (MOMitor): Ecological Momentary Assessment

    by Chidimma Doris Azubuike, Jungjun Bae, Deepthi S Varma, Tony Wen, Kay Roussos-Ross, Amie Goodin

    Background: Postpartum hypertension defined as elevated blood pressure after childbirth, affects approximately 20% of women after delivery. Digital health interventions that include remote monitoring therefore, present an important opportunity to facilitate regular blood pressure assessment in this high-risk population. Objective: The primary objective is to assess within- and between-person changes in hypertension status over the first 6 weeks postpartum using a smartphone-based ecological momentary assessment protocol. The secondary objective is to characterize the trajectory of hypertension indicators across the 6-week period and to compare hypertension screening results from week one and week six within participants. Methods: This study uses a time-series design using data from prospectively enrolled patients within a large health system. Patients eligible for recruitment were women aged 18 years or older who spoke English, owned a smartphone, had a liveborn neonate, and were willing to download an app and respond to survey questions within the app. Throughout the study period, all participants received hypertension screening items that asked whether their blood pressure was greater than 140/90 mm Hg and whether they felt dizzy or lightheaded, short of breath, or had a severe headache. A subset of participants were additionally asked to report their blood pressure readings. We estimate within- and between-participant effects using a generalized linear mixed model for a positive hypertension screen during weeks one through six. The model includes both fixed and random effects, controlling for age, race, marital status, education, insurance status, mode of delivery, total number of pregnancies, and history of diabetes mellitus. Results: The study was funded July 2021 and data collection was initiated in November 2021. Data collection for this study, per protocol, was completed in June 2025, though other participants continue to be enrolled in the ongoing parent study. Data analysis is expected to be completed by Spring 2026 with publication planned for Summer 2026. Conclusions: The study findings will provide insight into trajectories of hypertension outcomes in postpartum women and the utility for smartphone app-based remote blood pressure monitoring among postpartum women whose blood pressure was regularly tracked. Findings will provide evidence to support whether widespread implementation of this digital health surveillance approach to improve outcomes in maternal health, especially in the postpartum period, is clinically warranted.