Psychiatry

Comprehensive Summary

This study, presented by White et. al, looked at the demographic and clinical characteristics of patients with borderline personality disorder (BPD). BPD is a psychiatric disorder that is characterized by a pervasive pattern of emotion dysregulation and instability in identity. For this observational study, de-identified data from MindLinc electronic health records of patients 12 years and older who had been diagnosed with BPD were used. Natural Language Processing (NLP) was used to derive BPD symptoms from unstructured clinician-documented mental state examination (MSE) data. The results found that the most common comorbid disorders were major depressive disorder (45.7%), substance use disorder (34.6%), and post-traumatic stress disorder (29.2%). Patients in this sample were commonly prescribed psychiatric medication (67.7%), and approximately half (46.5%) of patients had been psychiatrically hospitalized in the past year. The study also found that emotional dysregulation (35.8%) and suicidal intent/ideation (31.3%) were the most frequent NLP-derived BPD symptoms, and the relative frequencies of these differed by age. These findings contribute to improving understandings of clinical characteristics associated with BPD.

Outcomes and Implications

Researching the clinical characteristics of disorders like BPD help to improve patient outcomes and can provide better insight on how to properly treat patients with BPD. The use of NLP in this study was stated as a limitation due to possible inaccuracies and there being possible “out of vocabulary” words. Despite being labeled as a limitation, White et. al mention that the overall accuracy of NLP was acceptable. This suggests that as NLP technology advances, it could be used more frequently in studies like this to identify clinical characteristics of other psychiatric disorders from unstructured notes in electronic health records. The study also found that the BPD symptoms were variable with age, potentially indicating that treatment best practices may differ by age among this population.

Our mission is to

Connect medicine with AI innovation.

No spam. Only the latest AI breakthroughs, simplified and relevant to your field.

Our mission is to

Connect medicine with AI innovation.

No spam. Only the latest AI breakthroughs, simplified and relevant to your field.

Our mission is to

Connect medicine with AI innovation.

No spam. Only the latest AI breakthroughs, simplified and relevant to your field.

AIIM Research

Articles

© 2025 AIIM. Created by AIIM IT Team

AIIM Research

Articles

© 2025 AIIM. Created by AIIM IT Team

AIIM Research

Articles

© 2025 AIIM. Created by AIIM IT Team