Search

ICU readmissions and post-discharge mortality pose significant challenges. Previous studies used EHRs and machine learning models, but mostly focused on structured data. Nursing records contain crucial unstructured information, but their utilization is challenging. Natural language processing (NLP) can extract structured features from clinical text. This study proposes the Crucial Nursing Description Extractor (CNDE) to predict post-ICU discharge mortality rates and identify high-risk patients for unplanned readmission by analyzing electronic nursing records. Developed a deep neural network (NurnaNet) with the ability to perceive nursing records, combined with a bio-clinical medicine pre-trained language model (BioClinicalBERT) to analyze the electronic health records (EHRs) in the MIMIC III dataset to predict the death of patients within six month and two year risk. A cohort and system development design was used. Based on data extracted from MIMIC-III, a database of critically ill in the US between 2001 and 2012, the results were analyzed. We calculated patients' age using admission time and date of birth information from the MIMIC dataset. Patients under 18 or over 89 years old, or who died in the hospital, were excluded. We analyzed 16,973 nursing records from patients' ICU stays. We have developed a technology called the Crucial Nursing Description Extractor (CNDE), which extracts key content from text. We use the logarithmic likelihood ratio to extract keywords and combine BioClinicalBERT. We predict the survival of discharged patients after six months and two years and evaluate the performance of the model using precision, recall, the F 1 -score, the receiver operating characteristic curve (ROC curve), the area under the curve (AUC), and the precision–recall curve (PR curve). The research findings indicate that NurnaNet achieved good F 1 -scores (0.67030, 0.70874) within six months and two years. Compared to using BioClinicalBERT alone, there was an improvement in performance of 2.05 % and 1.08 % for predictions within six months and two years, respectively. CNDE can effectively reduce long-form records and extract key content. NurnaNet has a good F 1 -score in analyzing the data of nursing records, which helps to identify the risk of death of patients after leaving the hospital and adjust the regular follow-up and treatment plan of relevant medical care as soon as possible. [ABSTRACT FROM AUTHOR]

Background: Despite recent advances in the treatment of neonatal infection, mortality rates and comorbidities associated with neonatal sepsis remain high. Hypocalcemia has been reported in critically ill patients, especially in as-sociation with sepsis. However, the importance of hypo-calcemia in neonatal sepsis has not been explored in detail. Objectives: The purpose of this study was to evaluate the prognostic value of hypocalcemia in neonatal sepsis patients and to identify the risk factors associated with sepsis-related mortality. Methods: This retrospective study examined perinatal data from patients in a level IV neonatal in-tensive care unit between January 2010 and June 2016. Univariate analysis was performed to understand the differences in clinical and laboratory characteristics between patients with and without neonatal sepsis. Neonates with sepsis were further stratified as having ionized hypocalcemia (if serum ionized calcium [iCa] <1.0 mmol/L) or not. Uni- and multivariate logistic regression analyses were utilized to evaluate the predictive potential of iCa for identifying sepsis-related mortality. Results: A total of 472 neonates were enrolled in this study, including 169 neonates diagnosed with culture-proven sepsis and 303 neonates without infection (control group). The comparison of neonates with and without sepsis highlighted significant differences in levels of iCa (0.97 ± 0.26 vs. 1.12 ± 0.25 mmol/L), magnesium (0.75 ± 0.22 vs. 0.89 ± 0.12 mmol/L), and phosphate (2.26 ± 1.08 vs. 1.65 ± 0.85 mmol/L; all p < 0.001). When neonates with sepsis were stratified into 2 subgroups based on serum iCa, neonates with hypocalcemia showed higher rates of organ dysfunction than those with normal iCa, as well as higher rates of cardiovascular system dysfunction (37.35 vs. 17.44%), renal dysfunction (34.94 vs. 30.95%), disseminated intravascular coagulation (26.51 vs. 11.63%), and seizure (16.04 vs. 5.8%; all p < 0.05). Among all neonates who had sepsis, the mortality rate was 13.61%, and this rate was higher among neonates with hypocalcemia than among those with normal iCa (20.48 vs. 6.98%, p < 0.05). Uni- and multivariate analyses showed that acidosis, hypoalbuminemia, hypocalcemia, and hyperphosphatemia were independent prognostic markers of sepsis-related mortality. In receiver-operating characteristic curve analysis, the areas under the curve were 0.70 (95% CI 0.624–0.768; p = 0.0004), 0.74 (95% CI 0.671–0.808; p < 0.0001), 0.73 (95% CI 0.653–0.792; p = 0.0002), and 0.67 (95% CI 0.59–0.737; p = 0.0154) for serum albumin, iCa, phosphate, and acidosis, respectively. Based on these findings, we developed a nomogram to predict sepsis-related mortality. Conclusions: Hypocalcemia is common in neonates with sepsis and is significantly associated with organ dysfunction and sepsis-related mortality. [ABSTRACT FROM AUTHOR]

Existing studies cannot evaluate the time-varying properties of frailty and polypharmacy despite raising concerns about their combined effects in older individuals. This study investigated the longitudinal association between different combined statuses of frailty and polypharmacy on risks of adverse outcomes. Retrospective cohort study. Subjects aged between 65 and 100 years (n = 100,000) were identified from Taiwan's National Health Insurance Research Database. Frailty was categorized into fit, mild, moderate, and severe frailty based on the multimorbidity frailty index. Concomitant use of 5 to 9 and ≥10 chronic medications was considered polypharmacy and excessive polypharmacy. We used generalized estimating equation models to examine the association among 12 groups of combined effects of frailty and polypharmacy and risks of all-cause mortality, all-cause hospitalization, and unplanned hospitalization. Age-stratified analyses were conducted for those aged 65 to 74, 75 to 84, and 85+ years. Compared with fit without polypharmacy, severe frailty with excess polypharmacy was associated with increased risks of adverse outcomes, particularly unplanned hospitalization (adjusted relative risk (aRR): 20.01 [95% confidence interval (CI)] 19.30–20.75). However, the combined effects varied in distinct groups. Within each polypharmacy category, there were dose-response associations between frailty category and adverse outcomes. For instance, within the polypharmacy group, the aRRs of mortality were 1.58 (1.52–1.64), 2.70 (2.60–2.80), 4.62 (4.44–4.82), and 6.81 (6.50–7.13) for the fit and mild, moderate, and severe frailty groups, respectively. By contrast, within each frailty category, the dose-response association between polypharmacy and adverse outcomes was limited to fit and mildly frail people. Age-stratified analyses yielded similar results. Both frailty and polypharmacy modified the risks of mortality and hospital admissions in older people, but the combined effects varied in distinct groups. This study thus highlights the potential to optimize care of older people by capturing the dynamic and combined changes related to frailty and polypharmacy. [ABSTRACT FROM AUTHOR]