Dataset Information

Text Processing for Detection of Fungal Ocular Involvement in Critical Care Patients: Cross-Sectional Study.

ABSTRACT: BACKGROUND:Fungal ocular involvement can develop in patients with fungal bloodstream infections and can be vision-threatening. Ocular involvement has become less common in the current era of improved antifungal therapies. Retrospectively determining the prevalence of fungal ocular involvement is important for informing clinical guidelines, such as the need for routine ophthalmologic consultations. However, manual retrospective record review to detect cases is time-consuming. OBJECTIVE:This study aimed to determine the prevalence of fungal ocular involvement in a critical care database using both structured and unstructured electronic health record (EHR) data. METHODS:We queried microbiology data from 46,467 critical care patients over 12 years (2000-2012) from the Medical Information Mart for Intensive Care III (MIMIC-III) to identify 265 patients with culture-proven fungemia. For each fungemic patient, demographic data, fungal species present in blood culture, and risk factors for fungemia (eg, presence of indwelling catheters, recent major surgery, diabetes, immunosuppressed status) were ascertained. All structured diagnosis codes and free-text narrative notes associated with each patient's hospitalization were also extracted. Screening for fungal endophthalmitis was performed using two approaches: (1) by querying a wide array of eye- and vision-related diagnosis codes, and (2) by utilizing a custom regular expression pipeline to identify and collate relevant text matches pertaining to fungal ocular involvement. Both approaches were validated using manual record review. The main outcome measure was the documentation of any fungal ocular involvement. RESULTS:In total, 265 patients had culture-proven fungemia, with Candida albicans (n=114, 43%) and Candida glabrata (n=74, 28%) being the most common fungal species in blood culture. The in-hospital mortality rate was 121 (46%). In total, 7 patients were identified as having eye- or vision-related diagnosis codes, none of whom had fungal endophthalmitis based on record review. There were 26,830 free-text narrative notes associated with these 265 patients. A regular expression pipeline based on relevant terms yielded possible matches in 683 notes from 108 patients. Subsequent manual record review again demonstrated that no patients had fungal ocular involvement. Therefore, the prevalence of fungal ocular involvement in this cohort was 0%. CONCLUSIONS:MIMIC-III contained no cases of ocular involvement among fungemic patients, consistent with prior studies reporting low rates of ocular involvement in fungemia. This study demonstrates an application of natural language processing to expedite the review of narrative notes. This approach is highly relevant for ophthalmology, where diagnoses are often based on physical examination findings that are documented within clinical notes.

SUBMITTER: Baxter SL

PROVIDER: S-EPMC7455861 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Text Processing for Detection of Fungal Ocular Involvement in Critical Care Patients: Cross-Sectional Study.

Baxter Sally L SL Klie Adam R AR Radha Saseendrakumar Bharanidharan B Ye Gordon Y GY Hogarth Michael M

Journal of medical Internet research 20200814 8

<h4>Background</h4>Fungal ocular involvement can develop in patients with fungal bloodstream infections and can be vision-threatening. Ocular involvement has become less common in the current era of improved antifungal therapies. Retrospectively determining the prevalence of fungal ocular involvement is important for informing clinical guidelines, such as the need for routine ophthalmologic consultations. However, manual retrospective record review to detect cases is time-consuming.<h4>Objective ...[more]

PMID: 32795984

Similar Datasets

Project description:Objective: To describe the utility and patterns of COVID-19 simulation scenarios across different international healthcare centers. Methods: This is a cross-sectional, international survey for multiple simulation centers team members, including team-leaders and healthcare workers (HCWs), based on each center's debriefing reports from 30 countries in all WHO regions. The main outcome measures were the COVID-19 simulations characteristics, facilitators, obstacles, and challenges encountered during the simulation sessions. Results: Invitation was sent to 343 simulation team leaders and multidisciplinary HCWs who responded; 121 completed the survey. The frequency of simulation sessions was monthly (27.1%), weekly (24.8%), twice weekly (19.8%), or daily (21.5%). Regarding the themes of the simulation sessions, they were COVID-19 patient arrival to ER (69.4%), COVID-19 patient intubation due to respiratory failure (66.1%), COVID-19 patient requiring CPR (53.7%), COVID-19 transport inside the hospital (53.7%), COVID-19 elective intubation in OR (37.2%), or Delivery of COVID-19 mother and neonatal care (19%). Among participants, 55.6% reported the team's full engagement in the simulation sessions. The average session length was 30-60 min. The debriefing process was conducted by the ICU facilitator in (51%) of the sessions followed by simulation staff in 41% of the sessions. A total of 80% reported significant improvement in clinical preparedness after simulation sessions, and 70% were satisfied with the COVID-19 sessions. Most perceived issues reported were related to infection control measures, followed by team dynamics, logistics, and patient transport issues. Conclusion: Simulation centers team leaders and HCWs reported positive feedback on COVID-19 simulation sessions with multidisciplinary personnel involvement. These drills are a valuable tool for rehearsing safe dynamics on the frontline of COVID-19. More research on COVID-19 simulation outcomes is warranted; to explore variable factors for each country and healthcare system.

Project description:BackgroundData on emergency and critical care (ECC) capacity in low-income countries (LICs) are needed to improve outcomes and make progress towards realizing the goal of Universal Health Coverage.MethodsWe developed a novel research instrument to assess public sector ECC capacity and service readiness in LICs. From January 20th to February 18th, 2020 we administered the instrument at all four central hospitals and a simple random sample of nine of 24 district hospitals in Malawi, a landlocked and predominantly rural LIC of 19·1 million people in Southern Africa. The instrument contained questions on the availability of key resources across three domains and was administered to hospital administrators and clinicians from outpatient departments, emergency departments, and inpatient units. Results were used to generate an ECC Readiness Score, with a possible range of 0 to 1, for each facility.FindingsA total of 114 staff members across 13 hospitals completed interviews for this study. Three (33%) district hospitals and all four central hospitals had ECC Readiness Scores above 0·5 (p-value 0·070). Absent equipment was identified as the most common barrier to ECC Readiness. Central hospitals had higher median ECC Readiness Scores with less variability 0·82 (interquartile range: 0·80-0·89) than district hospitals (0·33, 0·23 to 0·50, p-value 0·021).InterpretationThis is the first study to employ a systematic approach to assessing ECC capacity and service readiness at both district and central hospitals in Malawi and provides a framework for measuring ECC capacity in other LICs. Prior ECC assessments potentially overestimated equipment availability and our methodology may provide a more accurate approach. There is an urgent need for investments in ECC services, particularly at district hospitals which are more accessible to Malawi's predominantly rural population. These findings highlight the need for long-term investments in health systems strengthening and underscore the importance of understanding capacity in LIC settings to inform these efforts.FundingDivision of Pulmonary and Critical Care Medicine, Brigham and Women's Hospital and Department of Emergency Medicine, Brigham and Women's Hospital.

Dataset Information

Text Processing for Detection of Fungal Ocular Involvement in Critical Care Patients: Cross-Sectional Study.

Publications

Text Processing for Detection of Fungal Ocular Involvement in Critical Care Patients: Cross-Sectional Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets