Oropharyngeal Cancer Staging Health Record Extraction Using Artificial Intelligence.

Importance: Accurate, timely, and cost-effective methods for staging oropharyngeal cancers are crucial for patient prognosis and treatment decisions, but staging documentation is often inaccurate or incomplete. With the emergence of artificial intelligence in medicine, data abstraction may be associated with reduced costs but increased efficiency and accuracy of cancer staging. Objective: To evaluate an algorithm using an artificial intelligence engine capable of extracting essential information from medical records of patients with oropharyngeal cancer and assigning tumor, nodal, and metastatic stages according to American Joint Committee on Cancer eighth edition guidelines. Design, Setting, and Participants: This retrospective diagnostic study was conducted among a convenience sample of 806 patients with oropharyngeal squamous cell carcinoma. Medical records of patients with staged oropharyngeal squamous cell carcinomas who presented to a single tertiary care center between January 1, 2010, and August 1, 2020, were reviewed. A ground truth cancer stage dataset and comprehensive staging rule book consisting of 135 rules encompassing p16 status, tumor, and nodal and metastatic stage were developed. Subsequently, 4 distinct models were trained: model T (entity relationship extraction) for anatomical location and invasion state, model S (numerical extraction) for lesion size, model M (sequential classification) for metastasis detection, and a p16 model for p16 status. For validation, results were compared against ground truth established by expert reviewers, and accuracy was reported. Data were analyzed from March to November 2023. Main Outcomes and Measures: The accuracy of algorithm cancer stages was compared with ground truth. Results: Among 806 patients with oropharyngeal cancer (mean [SD] age, 63.6 [10.6] years; 651 males [80.8%]), 421 patients (52.2%) were positive for human papillomavirus. The artificial intelligence engine achieved accuracies of 55.9% (95% CI, 52.5%-59.3%) for tumor, 56.0% (95% CI, 52.5%-59.4%) for nodal, and 87.6% (95% CI, 85.1%-89.7%) for metastatic stages and 92.1% (95% CI, 88.5%-94.6%) for p16 status. Differentiation between localized (stages 1-2) and advanced (stages 3-4) cancers achieved 80.7% (95% CI, 77.8%-83.2%) accuracy. Conclusion and Relevance: This study found that tumor and nodal staging accuracies were fair to good and excellent for metastatic stage and p16 status, with clinical relevance in assigning optimal treatment and reducing toxic effect exposures. Further model refinement and external validation with electronic health records at different institutions are necessary to improve algorithm accuracy and clinical applicability.

An Evaluation of the Impact of High-Fidelity Endovascular Simulation on Surgeon Stress and Technical Performance.

OBJECTIVE: To measure the physiological stress response associated with high-fidelity endovascular team simulation. DESIGN: This is a prospective cohort study. SETTING: This study was performed at St Mary's Hospital (Imperial College London, London, UK), in a tertiary setting. PARTICIPANTS: Thirty-five participants (10 vascular surgical residents, 4 surgical interns, 12 theatre nurses, 2 attending vascular surgeons, 6 medical students and 1 technician) were recruited from the Imperial Vascular Unit at St Mary's Hospital, Imperial College London by direct approach. All participants finished the study. RESULTS: Junior surgeons experienced significantly increased sympathetic tone (Low frequency/high frequency (LF/HF) ratio) during team simulation compared to individual simulation (6.01 ± 1.68 vs. 8.32 ± 2.84, p < 0.001). Within team simulation junior surgeons experienced significantly higher heart rate (beats per minute) than their senior counterparts (82 ± 5.83 vs. 76 ± 6.02, p = 0.033). Subjective workload scores (NASA Task Load Index [NASA-TLX]) correlated moderately and significantly with sympathetic tone in surgeons across all stages of simulation. (r = 0.39, p = 0.01). CONCLUSIONS: A discrete, measurable increase in stress is experienced by surgeons during high-fidelity endovascular simulation and differentially effects junior surgeons. High-fidelity team simulation may have a role to play in improving nontechnical skill, reducing intra-operative stress, and reducing error.

The relationship between physical activity and post-operative length of hospital stay: A systematic review.

BACKGROUND: Recovery from surgery has traditionally been measured using specific outcome measures, such as length of hospital stay. However, advances in technology have enabled the measurement of continuous, objective physical activity data in the perioperative period. The aim of this systematic review was to determine the relationship between length of hospital stay and physical activity data for patients undergoing surgery. METHODS: A systematic search of EMBASE, Medline and the Cochrane Library, from inception until January 2017, was performed to identify all study designs that evaluated physical activity after surgery. Studies were included if a wearable sensor measured patient activity as an in-patient and the length of hospital stay was reported. Only English articles were included. RESULTS: Six studies with a total of 343 participants were included in this review. All the studies were prospective observational studies. Each study used a different sensor, with the commonest being a tri-axial accelerometer, and multiple different physical activity outcome measures were used, thereby prohibiting meta-analysis. Four of the studies demonstrated a relationship between physical activity levels and length of hospital stay, while two studies did not show any significant relationship. CONCLUSION: The amount of physical activity performed post-operatively negatively correlates with the length of hospital stay. This suggests that objective physical activity data collected by body worn sensors may be capable of predicting functional recovery post-operatively.

Understanding The Strengths And Weaknesses Of Public Reporting Of Surgeon-Specific Outcome Data.

Public reporting of outcome data is increasingly being used at the institutional and clinician levels and has become mandatory in some parts of the United States and the United Kingdom. The intended benefits are to drive quality improvement, demonstrate transparency, facilitate patient choice, and allow identification of poor performance. Public reporting of surgeon-specific mortality data, however, may have unintended consequences that include causing surgeons to become risk-averse, discouraging innovation, having an impact on training, and prompting "gaming" in health care. Given the small number of some surgical operations performed by individual surgeons, such data are unlikely to identify outliers or poor performers in a valid way. If metrics are deemed necessary and required to be reported publicly, they should be procedure specific; account for sample size; and focus not solely on mortality but also on other outcomes such as quality of life, patient satisfaction, and experience.