Oksana Gologorskaya
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Oksana Gologorskaya has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Albert Lee
Academic Research Services, University of California—San Francisco, San Francisco, California, USA
4 shared publications - Jennifer C. Lai
Department of Medicine, Division of Gastroenterology and Hepatology, University of California, San Francisco, San Francisco, California, USA
4 shared publications - Jin Ge
Department of Medicine, Division of Gastroenterology and Hepatology, University of California, San Francisco, San Francisco, California, USA
4 shared publications - Mark J. Pletcher
Department of Epidemiology and Biostatistics, University of California, San Francisco, San Francisco, CA, USA
4 shared publications - Alexander Kingsbury Smith
Division of Geriatrics University of California, San Francisco San Francisco California USA
2 shared publications - Allyson Cook Chapman
Division of Palliative Care, Department of Internal Medicine, University of California, San Francisco, San Francisco
2 shared publications
Latest Publications
- 26 April 2025
- Published by Wolters Kluwer Health in Liver Transplantation
- Vol. 32 (3) , 346-356
Characterizing practice variations in the care of hospitalized patients with cirrhosis across the University of California Health
Despite publicly available practice guidelines, in-hospital cirrhosis care remains highly variable. Prior studies of cirrhosis guideline adherence have been limited by administrative claims data. We aimed to overcome these limitations by using a novel multicenter electronic health record (EHR) database, the University of California Health Data Warehouse (UCHDW), to compare guideline adherence in the 5 medical centers of the University of California Health (UCH). We identified adult patients with cirrhosis hospitalized from 2013 to 2022. We evaluated adherence to 5 care quality measures applicable to inpatients. We used t tests to compare pairwise differences between individual UCH sites. We assessed the impact of patient-level and center-level factors (transplant services) through multivariate logistic regressions. We identified 17,249 patients with cirrhosis with 31,512 admissions: 39% women, 43% White, 31% Hispanic/Latino, 11% Asian, 7% Black/African-American, and 8% Unknown/Other. In pairwise comparisons, we found differences in adherence rates across all measures except for antibiotics for gastrointestinal bleeding. In multivariate modeling, we found positive associations between care at transplant centers and receiving paracenteses for those admitted for ascites or HE, albumin/antibiotics for those admitted for spontaneous bacterial peritonitis, endoscopy for those admitted for gastrointestinal bleeding, and lactulose for those admitted for HE. In addition, we observed negative associations between Black/African-American race and guideline adherence for receiving paracenteses for ascites or HE. Through our analyses of high-dimensional EHR data, we found significant differences in care associated with admissions at the transplant center and race/ethnicity. Our use of high-dimensional EHR data indicates that there is still significant room for improvement in the provision of high-quality cirrhosis care.
- 26 April 2025
- Published by Wolters Kluwer Health in Liver Transplantation
- Vol. 32 (3) , 346-356
Characterizing practice variations in the care of hospitalized patients with cirrhosis across the University of California Health
Despite publicly available practice guidelines, in-hospital cirrhosis care remains highly variable. Prior studies of cirrhosis guideline adherence have been limited by administrative claims data. We aimed to overcome these limitations by using a novel multicenter electronic health record (EHR) database, the University of California Health Data Warehouse (UCHDW), to compare guideline adherence in the 5 medical centers of the University of California Health (UCH). We identified adult patients with cirrhosis hospitalized from 2013 to 2022. We evaluated adherence to 5 care quality measures applicable to inpatients. We used t tests to compare pairwise differences between individual UCH sites. We assessed the impact of patient-level and center-level factors (transplant services) through multivariate logistic regressions. We identified 17,249 patients with cirrhosis with 31,512 admissions: 39% women, 43% White, 31% Hispanic/Latino, 11% Asian, 7% Black/African-American, and 8% Unknown/Other. In pairwise comparisons, we found differences in adherence rates across all measures except for antibiotics for gastrointestinal bleeding. In multivariate modeling, we found positive associations between care at transplant centers and receiving paracenteses for those admitted for ascites or HE, albumin/antibiotics for those admitted for spontaneous bacterial peritonitis, endoscopy for those admitted for gastrointestinal bleeding, and lactulose for those admitted for HE. In addition, we observed negative associations between Black/African-American race and guideline adherence for receiving paracenteses for ascites or HE. Through our analyses of high-dimensional EHR data, we found significant differences in care associated with admissions at the transplant center and race/ethnicity. Our use of high-dimensional EHR data indicates that there is still significant room for improvement in the provision of high-quality cirrhosis care.
- 8 October 2024
- Published by Wolters Kluwer Health in Hepatology
- Vol. 81 (6) , 1753-1763
Evaluating the positive predictive value of code-based identification of cirrhosis and its complications utilizing GPT-4
Background: Diagnosis code classification is a common method for cohort identification in cirrhosis research, but it is often inaccurate and augmented by labor-intensive chart review. Natural language processing (NLP) using large language models (LLMs) is a potentially more accurate method. To assess LLMs’ potential for cirrhosis cohort identification, we compared code-based versus LLM-based classification with chart review as a “gold standard.” Methods: We extracted and conducted a limited chart review of 3,788 discharge summaries of cirrhosis admissions. We engineered zero-shot prompts using Generative Pre-trained Transformer (GPT)-4 to determine whether cirrhosis and its complications were active hospitalization problems. We calculated positive predictive values (PPVs) of LLM-based classification versus limited chart review, and PPVs of code-based versus LLM-based classification as a “silver standard” in all 3,788 summaries. Results: Versus gold standard chart review, code-based classification achieved PPVs of 82.2% for identifying cirrhosis, 41.7% hepatic encephalopathy, 72.8% ascites, 59.8% gastrointestinal bleeding, and 48.8% spontaneous bacterial peritonitis. Compared to chart review, GPT-4 achieved 87.8-98.8% accuracies for identifying cirrhosis and its complications. Using LLM as a silver standard, code-based classification achieved PPVs of 79.8% for identifying cirrhosis, 53.9% hepatic encephalopathy, 55.3% ascites, 67.6% gastrointestinal bleeding, and 65.5% spontaneous bacterial peritonitis. Conclusions: LLM-based classification was highly accurate versus manual chart review in identifying cirrhosis and its complications – this allowed us to assess the performance of code-based classification at scale using LLMs as a silver standard. These results suggest LLMs could augment or replace code-based cohort classification and raise questions regarding the necessity of chart review. Export
- 8 October 2024
- Published by Wolters Kluwer Health in Hepatology
- Vol. 81 (6) , 1753-1763
Evaluating the positive predictive value of code-based identification of cirrhosis and its complications utilizing GPT-4
Background: Diagnosis code classification is a common method for cohort identification in cirrhosis research, but it is often inaccurate and augmented by labor-intensive chart review. Natural language processing (NLP) using large language models (LLMs) is a potentially more accurate method. To assess LLMs’ potential for cirrhosis cohort identification, we compared code-based versus LLM-based classification with chart review as a “gold standard.” Methods: We extracted and conducted a limited chart review of 3,788 discharge summaries of cirrhosis admissions. We engineered zero-shot prompts using Generative Pre-trained Transformer (GPT)-4 to determine whether cirrhosis and its complications were active hospitalization problems. We calculated positive predictive values (PPVs) of LLM-based classification versus limited chart review, and PPVs of code-based versus LLM-based classification as a “silver standard” in all 3,788 summaries. Results: Versus gold standard chart review, code-based classification achieved PPVs of 82.2% for identifying cirrhosis, 41.7% hepatic encephalopathy, 72.8% ascites, 59.8% gastrointestinal bleeding, and 48.8% spontaneous bacterial peritonitis. Compared to chart review, GPT-4 achieved 87.8-98.8% accuracies for identifying cirrhosis and its complications. Using LLM as a silver standard, code-based classification achieved PPVs of 79.8% for identifying cirrhosis, 53.9% hepatic encephalopathy, 55.3% ascites, 67.6% gastrointestinal bleeding, and 65.5% spontaneous bacterial peritonitis. Conclusions: LLM-based classification was highly accurate versus manual chart review in identifying cirrhosis and its complications – this allowed us to assess the performance of code-based classification at scale using LLMs as a silver standard. These results suggest LLMs could augment or replace code-based cohort classification and raise questions regarding the necessity of chart review. Export
- 27 June 2024
- Published by Wolters Kluwer Health in Hepatology
- Vol. 80 (5) , E69-E70
Reply: Refining retrieval and chunking strategies for enhanced clinical reliability of large language models in liver disease
An abstract is unavailable. This article is available as a PDF only.
- 27 June 2024
- Published by Wolters Kluwer Health in Hepatology
- Vol. 80 (5) , E69-E70
Reply: Refining retrieval and chunking strategies for enhanced clinical reliability of large language models in liver disease
An abstract is unavailable. This article is available as a PDF only.
- Top Cited Papers
- 7 March 2024
- Published by Wolters Kluwer Health in Hepatology
- Vol. 80 (5) , 1158-1168
Development of a liver disease–specific large language model chat interface using retrieval-augmented generation
Background: Large language models (LLMs) have significant capabilities in clinical information processing tasks. Commercially available LLMs, however, are not optimized for clinical uses and are prone to generating hallucinatory information. Retrieval-augmented generation (RAG) is an enterprise architecture that allows embedding of customized data into LLMs. This approach “specializes” the LLMs and is thought to reduce hallucinations. Methods: We developed “LiVersa,” a liver disease-specific LLM, by using our institution’s protected health information (PHI)-complaint text embedding and LLM platform, “Versa.” We conducted RAG on 30 publicly available American Association for the Study of Liver Diseases guidance documents to be incorporated into LiVersa. Results: We evaluated LiVersa’s performance by conducting two rounds of testing. First, we compared LiVersa’s outputs versus those of trainees from a previously published knowledge assessment. LiVersa answered all 10 questions correctly. Second, we asked 15 hepatologists to evaluate the outputs to ten hepatology topic questions generated by LiVersa, OpenAI’s ChatGPT 4, and Meta’s LLaMA 2. LiVersa’s outputs were more accurate but were rated less comprehensive and safe compared to those of ChatGPT 4. Discussion: In this demonstration, we built a disease-specific and PHI-compliant LLMs using RAG. While LiVersa demonstrated higher accuracy in answering questions related to hepatology – there were some deficiencies due to limitations set by the number of documents used for RAG. LiVersa will likely require further refinement before potential live deployment. The LiVersa prototype, however, is a proof of concept for utilizing RAG to customize LLMs for clinical use cases. Export
- 7 March 2024
- Published by Wolters Kluwer Health in Hepatology
- Vol. 80 (5) , 1158-1168
Top Cited PapersDevelopment of a liver disease–specific large language model chat interface using retrieval-augmented generation
Background: Large language models (LLMs) have significant capabilities in clinical information processing tasks. Commercially available LLMs, however, are not optimized for clinical uses and are prone to generating hallucinatory information. Retrieval-augmented generation (RAG) is an enterprise architecture that allows embedding of customized data into LLMs. This approach “specializes” the LLMs and is thought to reduce hallucinations. Methods: We developed “LiVersa,” a liver disease-specific LLM, by using our institution’s protected health information (PHI)-complaint text embedding and LLM platform, “Versa.” We conducted RAG on 30 publicly available American Association for the Study of Liver Diseases guidance documents to be incorporated into LiVersa. Results: We evaluated LiVersa’s performance by conducting two rounds of testing. First, we compared LiVersa’s outputs versus those of trainees from a previously published knowledge assessment. LiVersa answered all 10 questions correctly. Second, we asked 15 hepatologists to evaluate the outputs to ten hepatology topic questions generated by LiVersa, OpenAI’s ChatGPT 4, and Meta’s LLaMA 2. LiVersa’s outputs were more accurate but were rated less comprehensive and safe compared to those of ChatGPT 4. Discussion: In this demonstration, we built a disease-specific and PHI-compliant LLMs using RAG. While LiVersa demonstrated higher accuracy in answering questions related to hepatology – there were some deficiencies due to limitations set by the number of documents used for RAG. LiVersa will likely require further refinement before potential live deployment. The LiVersa prototype, however, is a proof of concept for utilizing RAG to customize LLMs for clinical use cases. Export
- 1 May 2023
- Published by Oxford University Press (OUP)
- p. A4974
Machine Learning Algorithm to Improve Cohort Identification in Interstitial Lung Disease
- 1 May 2023
- Published by Oxford University Press (OUP)
- p. A4974
Machine Learning Algorithm to Improve Cohort Identification in Interstitial Lung Disease
- Open Access
- 1 November 2020
- Published by American Society of Clinical Oncology (ASCO) in JCO Clinical Cancer Informatics
- Vol. 4 (4) , 454-463
Electronic Medical Record Search Engine (EMERSE): An Information Retrieval Tool for Supporting Cancer Research
PURPOSEThe Electronic Medical Record Search Engine (EMERSE) is a software tool built to aid research spanning cohort discovery, population health, and data abstraction for clinical trials. EMERSE i...
- 1 November 2020
- Published by American Society of Clinical Oncology (ASCO) in JCO Clinical Cancer Informatics
- Vol. 4 (4) , 454-463
Open AccessElectronic Medical Record Search Engine (EMERSE): An Information Retrieval Tool for Supporting Cancer Research
PURPOSEThe Electronic Medical Record Search Engine (EMERSE) is a software tool built to aid research spanning cohort discovery, population health, and data abstraction for clinical trials. EMERSE i...