Blog

Machine learning model significantly improves surgical time predictions

A study utilizing electronic health record data from 16,159 patients has demonstrated that an artificial neural network (ANN) model significantly outperforms traditional scheduling methods for predicting surgical procedure durations. The ANN achieved a root mean squared error of 49.7 minutes and a mean absolute error of 31.8 minutes, compared to an 18.52-minute discrepancy in surgeon estimates. By minimizing subjective bias in scheduling, this approach has the potential to optimize operating room resource utilization.

Journal Article by Kwong M, Noorchenarboo M (…) Elnahas A et 3 al. in Surg Endosc

© 2025. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

read the whole article in Surg Endosc

open it in PubMed

Advanced deep learning framework significantly improves surgical instrument tracking

A novel deep learning framework has achieved a mean average precision of 98.4% for detecting and tracking surgical instruments in laparoscopic surgery. Utilizing the yolov9n model combined with advanced tracking algorithms, it delivers real-time precision, even in challenging conditions such as rapid movements and occlusions. This innovation enhances surgical workflows, reduces the cognitive burden on teams, and improves patient safety, marking a critical advancement in minimally invasive procedures.

Journal Article by Ujjainkar PA and Raut SA in Surg Endosc

© 2025. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

read the whole article in Surg Endosc

open it in PubMed

Technical guidelines established for remote robotic-assisted surgery

Remote robotic-assisted surgery has the potential to enhance healthcare access, improve patient outcomes, and optimize efficiency. By addressing geographic barriers and reducing travel burdens, these procedures can significantly expand access to quality care. Key to their effectiveness is robust networks, reliable connectivity, and strict cybersecurity measures to protect patient data. The established technical guidelines outline essential requirements for the design and implementation of safe, interoperable remote surgical programs, aimed at facilitating the global adoption of this technology.

Journal Article by Wang Y, Buehler M (…) Bernard J et 7 al. in World J Surg

© 2025 The Author(s). World Journal of Surgery published by John Wiley & Sons Ltd on behalf of International Society of Surgery/Société Internationale de Chirurgie (ISS/SIC).

read the whole article in World J Surg

open it in PubMed

Targeted antibiotic program cuts infections after pancreatic surgery

A tailored antimicrobial stewardship program (AMS) in pancreatic surgery cut overall surgical site infections from 30.1% to 20.6% and organ-space infections from 26.3% to 19.3%. It also boosted prophylaxis coverage for rectal screening (87.2% to 100%) and biliary isolates (59.7% to 68.7%). The intervention improved clinical outcomes, reduced antibiotic use and length of stay, and saved €247,460. These results suggest that AMS strategies focused on local resistance patterns can meaningfully improve care and reduce costs in high-risk surgical populations.

Multicenter Study by De Pastena M, Paiella S (…) Salvia R et 27 al. in JAMA Netw Open

read the whole article in JAMA Netw Open

open it in PubMed

Large Language Models Successfully Extract Data for Pancreatic Cyst Surveillance

A study evaluated the efficacy of large language models (LLMs) in extracting clinical variables from radiology reports, revealing high accuracy. An analysis of 3,198 scans from 991 patients demonstrated that LLMs could extract key elements related to pancreatic cysts with categorical variable accuracy reaching up to 99%. Continuous variable accuracy varied, with cyst size (92%) and main pancreatic duct size (97%). The findings suggest that LLMs can facilitate streamlined data curation for surveillance and future AI-based models.

Journal Article by Choubey AP, Eguia E (…) Soares KC et 7 al. in J Am Coll Surg

Copyright © 2025 by the American College of Surgeons. Published by Wolters Kluwer Health, Inc. All rights reserved.

read the whole article in J Am Coll Surg

open it in PubMed

Wide margins and anatomical resection improve outcomes in HCC

In a systematic review of 12 studies involving 6,747 cases of hepatocellular carcinoma (HCC) with microvascular invasion, narrow resection margins (RMs) were identified as significant risk factors for postoperative recurrence and overall survival (OS). Researchers reported that narrow RMs had a pooled hazard ratio of 1.76 for recurrence and 1.99 for OS. Conversely, wide RMs and anatomical resection significantly benefited long-term survival. Japanese studies demonstrated a heightened risk of recurrence compared to Chinese studies, underscoring the need for tailored surgical strategies.

Journal Article by Shi S, Cui X (…) Zhai R et 2 al. in Eur J Gastroenterol Hepatol

Copyright © 2025 Wolters Kluwer Health, Inc. All rights reserved.

read the whole article in Eur J Gastroenterol Hepatol

open it in PubMed

AI model enhances diagnostic accuracy in colorectal cancer

A novel AI model named Coffee was developed to classify histopathological growth patterns in colorectal liver metastases, achieving impressive predictive performance with AUC values up to 1.000 in prospective cohorts. Desmoplastic tumors were linked to improved overall and progression-free survival compared to non-desmoplastic tumors. Additionally, AI-assisted pathology increased diagnostic accuracy to 94.7% for junior pathologists and reduced diagnostic times by 36%, suggesting potential for enhancing precision in patient management and treatment strategies.

Journal Article by Lin R, Chen Y (…) Zhang D et 20 al. in Int J Surg

Copyright © 2025 The Author(s). Published by Wolters Kluwer Health, Inc.

read the whole article in Int J Surg

open it in PubMed

AI model excels in early detection of post-hepatectomy liver failure

A cutting-edge AI model demonstrated significant accuracy in detecting post-hepatectomy liver failure (PHLF) within the first 24 hours post-surgery. The model achieved an AUC of 0.952 in internal validation and 0.884 in external validation among 1,832 patients across six Chinese hospitals. Moreover, it outperformed existing algorithms in challenging cases, showing an AUC of 0.654 within a Western cohort with incomplete health records. This innovation could revolutionize perioperative management of PHLF, enhancing patient outcomes.

Journal Article by Wang K, Yang Q (…) Si W et 17 al. in EClinicalMedicine

© 2025 The Author(s).

read the whole article in EClinicalMedicine

open it in PubMed

Higher cardiovascular health scores linked to lower colorectal cancer risk

A recent population-based study found that higher scores on life’s essential 8 (LE8), a cardiovascular health metric, significantly correlate with a reduced prevalence of colorectal cancer (CRC) among U.S. adults. Those with the highest LE8 scores experienced an 81% lower risk of CRC compared to individuals with the lowest scores. The inverse relationship appears linear, suggesting that promoting optimal cardiovascular health could be an essential strategy in lowering CRC incidence rates.

Journal Article by Ma X, Zhang X (…) Hou E et 5 al. in Medicine (Baltimore)

Copyright © 2025 the Author(s). Published by Wolters Kluwer Health, Inc.

read the whole article in Medicine (Baltimore)

open it in PubMed

Omitting abdominal drainage after left pancreatectomy lowers complications

The PANDRA II trial revealed that patients undergoing left pancreatectomy without routine abdominal drainage had similar morbidity rates compared to those with drainage. The no-drain group demonstrated noninferiority in overall postoperative morbidity, with a comprehensive complication index of 13.90 versus 19.43 for the drain group (p < 0.001). Additionally, the no-drain approach resulted in a significant reduction in overall complication rates (50.41% vs 78.40%, p < 0.001). Specific complications remained comparable.

Randomized Controlled Trial by Kaiser J, Niesen W (…) Probst P et 13 al. in Ann Surg

Copyright © 2025 Wolters Kluwer Health, Inc. All rights reserved.

read the whole article in Ann Surg

open it in PubMed