Comparison of Expert Vocabulary Usage Patterns between Mental Health and Non-Mental Health Clinicians When Diagnosing Pediatric Anxiety Disorders.
To compare the utilization patterns of expert vocabulary (EVo) in diagnosing pediatric anxiety between mental health and non-mental health clinical notes from electronic health records (EHR) to understand the role of Evo in informing classification and decision-making in anxiety diagnoses.
We conducted a retrospective study using a cohort less than age 25 from Cincinnati Children's Hospital including 897,685 patients with 61,586,446 notes. We analyzed EVo, collected from mental health clinicians, in both mental and non-mental health notes. We compared classification accuracy using EVo-based patient-level embedding from all clinical notes, mental-health notes, and non-mental health notes for two tasks: 1) pre- vs post-diagnosis anxiety patients, and 2) pre-diagnosis anxiety vs non-anxiety patients.
EVo usage was highest in pre-diagnosis anxiety, lower in non-anxiety, and lowest in post-diagnosis. Classification models using EVo features from all, mental-health, and non-mental health notes showed similar F1 scores for pre-diagnosis anxiety (0.70 ± 0.2 for two categories). For anxiety vs non-anxiety classification, all clinical and non-mental health notes had better F1 scores than mental-health notes (above 0.90 for three categories). There was a notable difference in class-wise performance across both tasks.
There are significant differences in anxiety EVo use between mental health and non-mental health clinicians. Despite less anxiety-specific terminology, non-mental health notes still captured key aspects of patient presentations, emphasizing the importance of including all clinicians' notes in analysis. EVo's utility for anxiety classification is most effective in pre-diagnostic phases, suggesting the need for a dedicated diagnostic lexicon and further study before incorporating EVo into classification models.
We conducted a retrospective study using a cohort less than age 25 from Cincinnati Children's Hospital including 897,685 patients with 61,586,446 notes. We analyzed EVo, collected from mental health clinicians, in both mental and non-mental health notes. We compared classification accuracy using EVo-based patient-level embedding from all clinical notes, mental-health notes, and non-mental health notes for two tasks: 1) pre- vs post-diagnosis anxiety patients, and 2) pre-diagnosis anxiety vs non-anxiety patients.
EVo usage was highest in pre-diagnosis anxiety, lower in non-anxiety, and lowest in post-diagnosis. Classification models using EVo features from all, mental-health, and non-mental health notes showed similar F1 scores for pre-diagnosis anxiety (0.70 ± 0.2 for two categories). For anxiety vs non-anxiety classification, all clinical and non-mental health notes had better F1 scores than mental-health notes (above 0.90 for three categories). There was a notable difference in class-wise performance across both tasks.
There are significant differences in anxiety EVo use between mental health and non-mental health clinicians. Despite less anxiety-specific terminology, non-mental health notes still captured key aspects of patient presentations, emphasizing the importance of including all clinicians' notes in analysis. EVo's utility for anxiety classification is most effective in pre-diagnostic phases, suggesting the need for a dedicated diagnostic lexicon and further study before incorporating EVo into classification models.
Authors
Chandra Shekar Chandra Shekar, Tschida Tschida, Strawn Strawn, Hanson Hanson, Santel Santel, Goethert Goethert, Kapadia Kapadia, Glauser Glauser, Pestian Pestian, Agasthya Agasthya
View on Pubmed