Enhancing Pressure Injury Surveillance Using Natural Language Processing.

OBJECTIVE: This study assessed the feasibility of nursing handoff notes to identify underreported hospital-acquired pressure injury (HAPI) events. METHODS: We have established a natural language processing-assisted manual review process and workflow for data extraction from a corpus of nursing notes across all medical inpatient and intensive care units in a tertiary care pediatric center. This system is trained by 2 domain experts. Our workflow started with keywords around HAPI and treatments, then regular expressions, distributive semantics, and finally a document classifier. We generated 3 models: a tri-gram classifier, binary logistic regression model using the regular expressions as predictors, and a random forest model using both models together. Our final output presented to the event screener was generated using a random forest model validated using derivation and validation sets. RESULTS: Our initial corpus involved 70,981 notes during a 1-year period from 5484 unique admissions for 4220 patients. Our interrater human reviewer agreement on identifying HAPI was high ( κ = 0.67; 95% confidence interval [CI], 0.58-0.75). Our random forest model had 95% sensitivity (95% CI, 90.6%-99.3%), 71.2% specificity (95% CI, 65.1%-77.2%), and 78.7% accuracy (95% CI, 74.1%-83.2%). A total of 264 notes from 148 unique admissions (2.7% of all admissions) were identified describing likely HAPI. Sixty-one described new injuries, and 64 describe known yet possibly evolving injuries. Relative to the total patient population during our study period, HAPI incidence was 11.9 per 1000 discharges, and incidence rate was 1.2 per 1000 bed-days. CONCLUSIONS: Natural language processing-based surveillance is proven to be feasible and high yield using nursing handoff notes.

Electronic surveillance of patient safety events using natural language processing.

OBJECTIVE: We describe our approach to surveillance of reportable safety events captured in hospital data including free-text clinical notes. We hypothesize that a) some patient safety events are documented only in the clinical notes and not in any other accessible source; and b) large-scale abstraction of event data from clinical notes is feasible. MATERIALS AND METHODS: We use regular expressions to generate a training data set for a machine learning model and apply this model to the full set of clinical notes and conduct further review to identify safety events of interest. We demonstrate this approach on peripheral intravenous (PIV) infiltrations and extravasations (PIVIEs). RESULTS: During Phase 1, we collected 21,362 clinical notes, of which 2342 were reviewed. We identified 125 PIV events, of which 44 cases (35%) were not captured by other patient safety systems. During Phase 2, we collected 60,735 clinical notes and identified 440 infiltrate events. Our classifier demonstrated accuracy above 90%. CONCLUSION: Our method to identify safety events from the free text of clinical documentation offers a feasible and scalable approach to enhance existing patient safety systems. Expert reviewers, using a machine learning model, can conduct routine surveillance of patient safety events.

Reduced visits to pediatric eye care among socioeconomically disadvantaged patients during the COVID-19 pandemic.

We hypothesized that children with low socioeconomic status (SES) had disproportionately fewer eye care visits during the early COVID-19 pandemic and that these children would be less likely to use synchronous provider-to-patient telemedicine eye care visits. This study investigated changes in patient demographics at a large, academic pediatric eye center before and after the pandemic. A retrospective review of all visits from March 18, 2019, to May 31, 2019 (pre-COVID period) and of the same date range in 2020 (COVID period) was performed. Patient addresses were used to calculate the Area Deprivation Index (ADI), a validated measure of a neighborhood's SES. Patients who identified as non-White, and those requiring an interpreter had relatively fewer visits during the COVID period compared to the pre-COVID period. In addition, relatively fewer telemedicine visits were performed with patients who lived in a neighborhood classified as at or above the 50th ADI percentile (more disadvantaged).

Timing of Ocular Hypertension After Pediatric Closed-Globe Traumatic Hyphema: Implications for Surveillance.

PURPOSE: To evaluate the timing of ocular hypertension (OHT) after pediatric closed-globe injury (CGI) and traumatic hyphema. We hypothesize that OHT will occur at different times based on injury characteristics. DESIGN: Retrospective, cohort study. METHODS: Setting: Single-center, tertiary-care, pediatric hospital. PARTICIPANTS: Subjects included patients ≤18 years of age at the time of injury who suffered CGI and traumatic hyphema between 2002 and 2019. Observation Procedure(s): Intraocular pressure and injury demographics were abstracted for every visit after injury. OHT was defined as >21 mm Hg at presentation or after a reading of ≤21 mm Hg at a prior visit. MAIN OUTCOME MEASURES: The primary outcome measure was the timing of OHT categorized into 4 periods: presentation, acute (days 1-7), subacute (days 8-28), or late (day >28). Secondary outcome measures were identification of risks factors for OHT by multivariable logistic regression. RESULTS: OHT occurred in 119 of the 305 (39%) subject eyes. OHT occurred in 35 patients at presentation, 69 times acutely, 35 times subacutely, and 36 times late. Pupil damage predicted acute-period OHT (P = .004). OHT at presentation predicted subacute period OHT (P = .004). Iridodialysis and cataract predicted late-period OHT (P = .007 and P < .001, respectively). CONCLUSIONS: OHT after CGI and traumatic hyphema in pediatric patients is common. Injury demographics predict this complication. Integration of these risk factors with current literature allows proposal of a risk-stratification tool to guide efficient surveillance for OHT.