Background: Unplanned and potentially avoidable readmission within 30 days post discharge is a major financial burden.

Aim: To use text-based electronic patient records to calculate the Charlson Comorbidity Index (CCI) score using a natural language processing technique to establish the feasibility and usefulness of the text-based electronic patient records in identifying patients at risk for unplanned readmission.

Methods: A retrospective review of electronic patient records for general and trauma surgery in a hospital in South Africa (2012-2022) was conducted using the LACE score. Validated sentiment analysis analyzed free text components of electronic patient records to compute the CCI score and to establish the feasibility and usefulness of the LACE score in identifying patients at risk for unplanned readmission.

Results: Trauma surgery patients had a mean LACE score of 5.91 (SD = 2.41), with 8.44% scoring 10 or higher and a specificity and sensitivity of 91.63% and 13.81%, respectively. The general surgery patients had a mean LACE score of 7.75 (SD = 3.04), with 10.63% scoring 10 or higher and a specificity of 71.47% and a sensitivity of 44.80%, respectively. Logistic regression analysis revealed that LACE scores significantly predicted unplanned readmissions in both trauma (β = 0.11, p < 0.001; OR = 1.112, 95% CI [1.082, 1.143]) and general surgery (β = 0.15, p < 0.001; OR = 1.162, 95% CI [1.130, 1.162]) patients.

Conclusion: The LACE score demonstrated the predictive value for readmission in trauma and general surgery patients. The LACE score was relatively effective in identifying patients who were less likely to be readmitted but showed limitations in identifying patients at higher risk of readmission. However, the successful use of natural language processing for data extraction of comorbidities shows promise on addressing the challenges around text-based medical records.

Download full-text PDF

Source
http://dx.doi.org/10.1002/wjs.12523DOI Listing

Publication Analysis

Top Keywords

electronic patient
16
patient records
16
lace score
16
natural language
8
language processing
8
south africa
8
text-based electronic
8
cci score
8
establish feasibility
8
identifying patients
8

Similar Publications

Pruritus in atopic dermatitis: a cross-sectional study of adult patients from a tertiary university hospital in São Paulo, Brazil.

An Bras Dermatol

March 2025

Department of Dermatology, Faculty of Medicine, Universidade de São Paulo, São Paulo, SP, Brazil. Electronic address:

Background: Chronic pruritus is the defining symptom of atopic dermatitis (AD). Although AD is common in Latin America, there is little data regarding pruritus intensity, characteristics, and effects on quality of life in this population.

Objective: This cross-sectional study aimed to evaluate pruritus in 91 patients with AD at a tertiary university hospital in São Paulo, Brazil.

View Article and Find Full Text PDF

Introduction: The American Urological Association (AUA) recommends urology referral and surgery for undescended testicle (UDT) before 18 months of age, but it has been shown that many referrals occur later, influenced by social factors.

Objective: This study aims to identify key social factors that impact UDT referral timing and appropriateness.

Study Design: Pediatric patients referred to our institution for UDT management from 2018 to 2023 were analyzed.

View Article and Find Full Text PDF

Multi-omics analysis of druggable genes to facilitate Alzheimer's disease therapy: A multi-cohort machine learning study.

J Prev Alzheimers Dis

March 2025

Department of Pathophysiology School of Basic Medicine Key Laboratory of Education Ministry/Hubei Province of China for Neurological Disorders Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China. Electronic address:

Background: The swift rise in the prevalence of Alzheimer's disease (AD) alongside its significant societal and economic impact has created a pressing demand for effective interventions and treatments. However, there are no available treatments that can modify the progression of the disease.

Methods: Eight AD brain tissues datasets and three blood datasets were obtained.

View Article and Find Full Text PDF

Background: Lumen reduction after bioresorbable scaffold implantation has been reported. This study aimed to assess the influence of pre-dilatation with a scoring balloon versus a standard non-compliant balloon prior to implanting a magnesium-based Magmaris bioresorbable scaffold (MgBRS) on lumen measurements using optical coherence tomography (OCT) and on clinical outcomes after 12 months.

Method: In the OPTIMIS-study (Optimal lesion preparation before implantation of a MgBRS in patients with coronary artery stenosis), patients were randomly assigned to pre-dilatation with a scoring balloon or a standard non-compliant balloon before MgBRS implantation.

View Article and Find Full Text PDF

T-cell Engagers in Prostate Cancer.

Eur Urol

March 2025

Division of Medical Oncology, Department of Internal Medicine, Huntsman Cancer Institute, University of Utah, Salt Lake City, UT, USA. Electronic address:

Owing to the "cold" tumor immune microenvironment of prostate cancer, immune-targeting agents have shown limited efficacy in patients with advanced prostate cancer, highlighting the need for new therapies with novel mechanisms of action. In this context, T-cell engagers (TCEs), which induce T-cell-mediated killing of cancer cells by binding the CD3 receptor on T cells and a specific tumor antigen expressed on malignant cells, represent a promising therapeutic option. Multiple studies have explored the use of TCEs in previously treated patients with metastatic castration-resistant prostate cancer, and several ongoing trials are currently assessing novel TCEs either as single agents or in combinatorial regimens with molecules with a distinct mechanism of action (eg, androgen receptor pathway inhibitors and other immune-targeting agents).

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!