Related Experiment Video
Updated: Jul 1, 2026
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
Published on: September 20, 2018
Effectiveness of natural language intelligence technology in chronic diseases nursing: A systematic review and
Jiang Zeng1, Yuxin Xu2, Piaopiao Chen3
1Geriatric Medicine Center, Department of Pulmonary and Critical Care Medicine, Zhejiang Provincial People's Hospital (Affiliated People's Hospital, Hangzhou Medical College), Hangzhou, Zhejiang, 310014, China.
Background:
Chronic diseases pose a heavy global burden, with challenges in utilizing unstructured data for continuous care. Natural language intelligence technology (NLIT) shows potential in addressing these issues.
Methods:
This systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, with its protocol registered on PROSPERO (CRD420251006387). We searched PubMed, Web of Science, Embase, and Scopus databases for studies published between January 2014 and January 2024. The risk of bias in included studies was assessed using the Newcastle-Ottawa Scale (NOS) for cohort studies and the Quality Assessment of Diagnostic Accuracy Studies-Comparative (QUADAS-C) scale for diagnostic accuracy studies.
Results:
A total of 6 studies involving 28,323 participants were included. NLIT showed beneficial effectiveness: in chronic obstructive pulmonary disease (COPD) management, NLIT was delivered via an Artificial Neural Network (ANN)-powered smartphone app (Re-Admit) that processed patient symptom reports and EHR data, reducing 30-day readmission rates by 27.9%; in diabetes care, it improved self-management behaviors (P < 0.05) and diabetic retinopathy referral compliance by 19.34% (P < 0.01); in stroke rehabilitation, it enhanced motor function (Wolf test, P = 0.02) and shoulder range of motion (P ≤ 0.01). Technical performance included 88.46% accuracy in predicting COPD exacerbations and 92% diagnostic accuracy for diabetes using Generative Pre-trained Transformer 4 (GPT-4). Meta-analysis of binary compliance data from two studies (Musculoskeletal [MSK] conditions and diabetes care) showed that NLIT demonstrated measurable benefits for clinical outcomes, with a pooled relative risk (RR) of 1.20 (95% confidence interval [CI]: 1.03-1.40, P = 0.02); however, substantial heterogeneity was observed (I2 = 75%, P = 0.05). Five studies were rated as low risk of bias, with one having moderate risk due to hypothetical data.
Conclusions:
NLIT is valuable for personalized care and resource optimization but faces challenges like data heterogeneity and bias, requiring further refinement.
Related Concept Videos
01:30Current Trends in Nursing II
01:25Role of Communication in the Nursing Process I: Assessment and Diagnosis
The nursing process considers the patient's emotional and physical well-being. The process can be repeated or stopped at any point if judged essential. Assessment is the first step in the nursing process.
01:10Documentation of Nursing Diagnosis
In some settings, data-driven computerized decision support systems are in place, allowing for more accurate nursing diagnoses. The database within one of these systems includes diagnostic labels defining characteristics, activities, and indicators for nursing. A nurse enters assessment...
01:29Nursing Interventions II: Selecting and Classifying the Nursing Interventions
01:27Nursing Clinical Information System
A Nursing Clinical Information System (NCIS) is a specialized type of healthcare information system tailored to meet the unique needs of nursing practice. It incorporates the principles of nursing informatics to streamline information management and improve the quality of care delivery.
Critical attributes of NCIS include:
01:30Chronic Obstructive Pulmonary Disease-V: Nursing Management
Assessment