neurosurgical_operative_report

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
neurosurgical_operative_report [2025/07/06 20:49] – administradorneurosurgical_operative_report [2025/07/06 20:49] (current) – administrador
Line 3: Line 3:
 {{rss>https://pubmed.ncbi.nlm.nih.gov/rss/search/1B7BQ1Y5fH4hseI_aopdfi6Qqc5LkPt79DksO2voyxUtTKNoFb/?limit=15&utm_campaign=pubmed-2&fc=20250706164808}} {{rss>https://pubmed.ncbi.nlm.nih.gov/rss/search/1B7BQ1Y5fH4hseI_aopdfi6Qqc5LkPt79DksO2voyxUtTKNoFb/?limit=15&utm_campaign=pubmed-2&fc=20250706164808}}
  
-====== The use of generative artificial intelligence–based dictation in a neurosurgical practice: a pilot study ====== 
  
-In a [[pilot]] [[comparative study]]   
-Hopkins et al.   
-from the Keck School of Medicine, USC, Los Angeles (Neurosurgery; Endocrinology)   
-published in [[Neurosurgical Focus]]   
-to evaluate whether a modified [[OpenAI]] [[Generative artificial intelligence]] model can match or improve upon the accuracy of a commercial dictation tool (Nuance Dragon Medical One) in [[neurosurgical operative report]] generation.   
-[[Whisper]]‑based model demonstrated non‑inferior overall word error rate (WER) versus Dragon (1.75% vs 1.54%, p=0.08). Excluding linguistic errors, Whisper outperformed Dragon (0.50% vs 1.34%, p<0.001; total errors 6.1 vs 9.7, p=0.002). Whisper’s performance was robust to faster speech and longer recordings, unlike Dragon 
-((Hopkins BS, Dallas J, Yu J, Briggs RG, Chung LK, Cote DJ, Gomez D, Shah I, Carmichael JD, Liu JC, Mack WJ, Zada G. The use of generative artificial intelligence-based dictation in a neurosurgical practice: a pilot study. Neurosurg Focus. 2025 Jul 1;59(1):E8. doi: 10.3171/2025.4.FOCUS24834. PMID: 40591970.)). 
- 
-----   
-===== Critical Review ===== 
- 
-* **Strengths:**   
-  * Direct comparison of a cutting-edge generative AI (Whisper) to an established clinical tool in a real-world neurosurgical workflow.   
-  * Objective metrics (WER) with appropriate statistical analysis.   
-  * Mixed-case operative reports cover cranial and spinal procedures, enhancing generalizability. 
- 
-* **Weaknesses & Limitations:**   
-  * Small sample size (n=10 reports, 3 physicians) limits statistical power.   
-  * Lack of real-time clinical integration assessments—only offline comparisons.   
-  * No analysis of downstream impact on report quality, clinician satisfaction, or patient safety.   
-  * Commercial Dragon may not represent the latest version or fully optimized settings. 
- 
-* **Methodological concerns:**   
-  * Manual WER calculation introduces potential reviewer bias; no inter‑rater reliability reported.   
-  * Recording conditions and audio quality not standardized across sessions. 
-  * Exclusion of “linguistic errors” may bias interpretation toward AI advantage. 
- 
-* **Clinical relevance:**   
-  * Whisper’s stability with faster dictation may support efficiency gains in high-volume clinical settings.   
-  * Noninferiority demonstrated, but real-world deployment needs integration, EHR compatibility, user training, and error recovery workflow. 
- 
-===== Verdict: 6.5 / 10 ===== 
- 
-| Criteria                 | Score | Comments | 
-| Innovation               | 8     | Novel application of transformer-based AI to dictation | 
-| Methodology              | 6     | Solid but limited by small sample and manual error assessment | 
-| Clinical Applicability   | 6     | Promising, yet lacks prospective implementation data | 
-| Statistical Rigor        | 6     | Basic significance testing performed; confidence intervals absent | 
- 
-**Key Takeaway for Neurosurgeons:**   
-Modified [[Whisper]] offers comparable, or potentially better, transcription accuracy than Dragon in neurosurgical dictation, especially under faster speech rates—but further large-scale, workflow-integrated trials are essential before clinical adoption. 
- 
-**Bottom Line:**   
-This pilot suggests generative AI could reduce documentation burden, but robustness and clinical utility must be validated in real-world settings. 
- 
-----   
-**Title:** The use of generative artificial intelligence–based dictation in a neurosurgical practice: a pilot study   
-**Full Citation:** Hopkins BS, Dallas J, Yu J, Briggs RG, Chung LK, Cote DJ, Gomez D, Shah I, Carmichael JD, Liu JC, Mack WJ, Zada G. *Neurosurg Focus*. 2025 Jul 1;59(1):E8. doi:10.3171/2025.4.FOCUS24834   
-**Publication Date:** July 1, 2025   
-**Corresponding Author Email:** Not explicitly listed; likely accessible via USC Keck directory (e.g. [email protected]) 
- 
-[[Categories]]: Research, AI in Neurosurgery, Clinical Workflow, Pilot Studies   
-[[Tags]]: generative AI, transcription, Whisper model, Dragon Medical One, neurosurgery documentation, word error rate 
- 
- 
-  
  • neurosurgical_operative_report.txt
  • Last modified: 2025/07/06 20:49
  • by administrador