Electronic health data concerning implantable medical devices (IMD) opens opportunities for dynamic real-world monitoring to assess associated risks related to implanted materials. Due to population ageing and expanding demands, total hip, knee, and shoulder arthroplasties are increasing. Automating the collection and analysis of orthopedic device features could benefit physicians and public health policies enabling early issue detection, IMD monitoring and patient safety assessment. A machine learning tool using natural language processing (NLP) was developed for the automated extraction of operation information from medical reports in orthopedics. A corpus of 959 orthopaedic operative reports from 5 centres was manually annotated using the Prodigy software® with a strong inter-annotator agreement of 0.80. Data to extract concerned key clinical and procedure information (n= 9) selected by a multidisciplinary group based on the French health authority checklist. Performances parameters of the NLP model estimated an overall strong precision and recall of respectively 97.0 and 96.0 with a F1-score 96.3. Systematic monitoring of orthopedic devices could be ensured by an automated tool, leveraging clinical data warehouses. Traceability of medical devices with implantation modalities will allow detection of implant factors leading to complications. The evidence from real-world data could provide concrete and dynamic insights to surgeons and infectious disease specialists concerning implant follow-up, guiding therapeutic decision-making, and informing public health policymakers. The tool will be applied on clinical data warehouses to automate information extraction and presentation, providing feedback on mandatory information completion and contents of operative reports to support improvements, and thereafter implant research projects.

UNASSIGNED: We aimed to evaluate the prevalence of highly detailed ventral hernia repair (VHR) operative reports and associations between operative report detail and postoperative outcomes in a medico-legal dataset.
UNASSIGNED: VHR are one of the most common surgical procedures performed in the United States. Previous work has shown that VHR operative reports are poorly detailed, however, the relationship between operative report detail and patient outcomes is unknown.
UNASSIGNED: This is a retrospective cross-sectional observational study. Operative reports describing VHR were obtained from a medical-legal database. Medical records were screened and data was extracted including clinical outcomes, such as surgical site infection (SSI), hernia recurrence, and reoperation and the presence of key details in each report. Highly detailed operative reports were defined as having 70% of recommended details. The primary outcome was the prevalence of highly detailed VHR operative reports.
UNASSIGNED: A total of 1011 VHR operative reports dictated by 693 surgeons across 517 facilities in 50 states were included. Median duration of follow-up was 4.6 years after initial surgery. Only 35.7% of operative reports were highly detailed. More recent operative reports, cases with resident involvement, and contaminated procedures were more likely to be highly detailed (all P < 0.05). Compared to poorly detailed operative reports, cases with highly detailed reports had fewer SSIs (13.2% vs 7.5%, P = 0.006), hernia recurrence (65.8% vs 55.4%, P = 0.002), and reoperation (78.9% vs 62.6%, P = 0.001).
UNASSIGNED: In this medico-legal dataset, most VHR operative reports are poorly detailed while highly detailed operative reports were associated with lower rates of complications. Future studies should examine a nationally representative dataset to validate our findings.

Accurate operative notes are imperative to patient care and are used for communication, billing, quality assurance, and medical-legal conflicts. However, operative note quality often varies and many lack critical details. Unfortunately, no standardized training exists in operative dictations for surgical trainees. This pilot study sought to determine resident ability to dictate a comprehensive operative note and to determine a need for a formal operative dictation curriculum.
Thirty-eight surgical residents between post-graduate years (PGY) one to four participated in a ventral hernia repair simulation. One senior (PGY3/4) resident coached two junior residents (PGY1/2). Residents completed an informal needs assessment regarding operative dictations. Post-simulation, residents completed an operative dictation. Notes were graded using a modified validated rubric.
Thirty-five residents completed the needs assessment, and 38 residents submitted an operative note. Eighty-two percent of this group have completed ≤ 25 operative dictations in training and 77% have received minimal feedback on operative dictations. Out of 33 total points, mean overall score was 18.9 ± 5.4 (Junior resident: 17.9 ± 5.4; Senior resident: 20.9 ± 4.8) Total mean scores did not significantly differ between junior and senior residents (p = 0.10). Senior and junior residents scored similarly on the procedural details component (p = 0.29). Senior residents scored higher on relevant patient history and operative note headers (p = 0.04).
Standard surgical training may not provide enough teaching and feedback to residents on operative note dictations. A formal residency training curriculum may bolster trainee ability to learn the components of an effective operative note.

Background: Given the importance of operative documentation, we reviewed operative notes for surgeries that required splenic flexure mobilization (SFM) to determine their accuracy. Materials and Methods: We performed a retrospective review of 51 operative notes for complete SFMs performed at a single institution from January 2015 to June 2020. Results: None of the operative notes reported a rationale for performing SFM, use of preoperative imaging to guide technical approach, reasoning for the operative method and mobilization approach used, or specific steps taken to ensure that SFM was done safely. Most reports did not include technical details, with one-third of the notes merely reporting that \"the splenic flexure was mobilized.\" Conclusions: Increased awareness about the lack of operative documentation of the critical aspects of the SFM could stimulate initiatives to standardize the SFM method and improve the quality of operative notes for SFM.

To improve the quality of cancer operations, the American College of Surgeons published Operative Standards for Cancer Surgery, which has been incorporated into Commission on Cancer (CoC) accreditation requirements. We sought to determine if compliance with operative standards was associated with technical surgical outcomes. Oncologic operative reports from 2017 at a CoC and non-CoC institution were examined for documentation of Operative Standards essential steps. Lymph node (LN) yield for lung and colon cases and re-excision rates for breast cases were recorded. Correct documentation was poor for colon, breast, and lung cases with numerous elements documented in <10% of operative reports at both centers. For lung cases, there was no significant difference in meeting ≥10 LN benchmark or average LN yield between the 2 institutions. For colon cases, average lymph node yield was lower in the non-CoC facility, but there was no significant difference in meeting ≥12 LN benchmark. For breast cases, re-excision rates were similar in both programs. Many essential steps in Operative Standards were poorly documented in operative reports, regardless of CoC status. Achieving benchmark technical surgical outcomes was not associated with documented compliance with these standards. Whether improved documentation leads to better surgical outcomes requires further investigation.

BACKGROUND: Implementation of best practices surgical checklists improves patient safety and outcomes. However, documenting performance of these practices can be challenging. The American Society of Colon and Rectal Surgeons developed a Best Practices for Rectal Cancer Checklist (RCC) to standardize and improve the quality of rectal cancer surgery. This study compared the degree to which synoptic (SR) and narrative (NR) operative reports document RCC items.
METHODS: Two reviewers independently reviewed a cohort of prospectively collected SR for rectal cancer surgery and a case-matched historical cohort of NR. Reports were reviewed for documentation of performance of operative items on the RCC. Abstraction time and inter-rater agreement were also measured.
RESULTS: SR scored significantly higher than NR on the overall checklist score (mean adjusted score ± standard deviation 12.4 ± 0.9 vs. 5.7 ± 1.9, maximum possible score 18, P < 0.001). Reviewers abstracted data significantly faster from SR. Inter-rater agreement between reviewers was high for both types of reports.
CONCLUSIONS: SR were associated with reliable and more complete and reliable documentation of items on the RCC. Use of an SR system standardizes operative reporting, providing the opportunity to enhance checklist compliance, and enable timely feedback to improve surgical outcomes for rectal cancer patients.

BACKGROUND: Full syntactic parsing of clinical text as a part of clinical natural language processing (NLP) is critical for a wide range of applications. Several robust syntactic parsers are publicly available to produce linguistic representations for sentences. However, these existing parsers are mostly trained on general English text and may require adaptation for optimal performance on clinical text. Our objective was to adapt an existing general English parser for the clinical text of operative reports via lexicon augmentation, statistics adjusting, and grammar rules modification based on operative reports.
METHODS: The Stanford unlexicalized probabilistic context-free grammar (PCFG) parser lexicon was expanded with SPECIALIST lexicon along with statistics collected from a limited set of operative notes tagged by two POS taggers (GENIA tagger and MedPost). The most frequently occurring verb entries of the SPECIALIST lexicon were adjusted based on manual review of verb usage in operative notes. Stanford parser grammar production rules were also modified based on linguistic features of operative reports. An analogous approach was then applied to the GENIA corpus to test the generalizability of this approach to biologic text.
RESULTS: The new unlexicalized PCFG parser extended with the extra lexicon from SPECIALIST along with accurate statistics collected from an operative note corpus tagged with GENIA POS tagger improved the F-score by 2.26% from 87.64% to 89.90%. There was a progressive improvement with the addition of multiple approaches. Lexicon augmentation combined with statistics from the operative notes corpus provided the greatest improvement of parser performance. Application of this approach on the GENIA corpus increased the F-score by 3.81% with a simple new grammar and addition of the GENIA corpus lexicon.
CONCLUSIONS: Using statistics collected from clinical text tagged with POS taggers along with proper modification of grammars and lexicons of an unlexicalized PCFG parser may improve parsing performance of existing parsers on specialized clinical text.