1
|
Zhong W, Yao PY, Boppana SH, Pacheco FV, Alexander BS, Simpson S, Gabriel RA. Improving case duration accuracy of orthopedic surgery using bidirectional encoder representations from Transformers (BERT) on Radiology Reports. J Clin Monit Comput 2024; 38:221-228. [PMID: 37695448 PMCID: PMC10879219 DOI: 10.1007/s10877-023-01070-w] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Accepted: 08/22/2023] [Indexed: 09/12/2023]
Abstract
PURPOSE A major source of inefficiency in the operating room is the mismatch between scheduled versus actual surgical time. The purpose of this study was to demonstrate a proof-of-concept study for predicting case duration by applying natural language processing (NLP) and machine learning that interpret radiology reports for patients undergoing radius fracture repair. METHODS Logistic regression, random forest, and feedforward neural networks were tested without NLP and with bag-of-words. Another NLP method tested used feedforward neural networks and Bidirectional Encoder Representations from Transformers specifically pre-trained on clinical notes (ClinicalBERT). A total of 201 cases were included. The data were split into 70% training and 30% test sets. The average root mean squared error (RMSE) were calculated (and 95% confidence interval [CI]) from 10-fold cross-validation on the training set. The models were then tested on the test set to determine proportion of times surgical cases would have scheduled accurately if ClinicalBERT was implemented versus historic averages. RESULTS The average RMSE was lowest using feedforward neural networks using outputs from ClinicalBERT (25.6 min, 95% CI: 21.5-29.7), which was significantly (P < 0.001) lower than the baseline model (39.3 min, 95% CI: 30.9-47.7). Using the feedforward neural network and ClinicalBERT on the test set, the percentage of accurately predicted cases, which was defined by the actual surgical duration within 15% of the predicted surgical duration, increased from 26.8 to 58.9% (P < 0.001). CONCLUSION This proof-of-concept study demonstrated the successful application of NLP and machine leaning to extract features from unstructured clinical data resulting in improved prediction accuracy for surgical case duration.
Collapse
Affiliation(s)
- William Zhong
- Division of Perioperative Informatics, Department of Anesthesiology, University of California, La Jolla, San Diego, CA, USA
| | - Phil Y Yao
- Division of Perioperative Informatics, Department of Anesthesiology, University of California, La Jolla, San Diego, CA, USA
| | - Sri Harsha Boppana
- Division of Perioperative Informatics, Department of Anesthesiology, University of California, La Jolla, San Diego, CA, USA
| | - Fernanda V Pacheco
- School of Medicine, University of California, La Jolla, San Diego, CA, USA
| | - Brenton S Alexander
- Division of Perioperative Informatics, Department of Anesthesiology, University of California, La Jolla, San Diego, CA, USA
| | - Sierra Simpson
- Division of Perioperative Informatics, Department of Anesthesiology, University of California, La Jolla, San Diego, CA, USA
| | - Rodney A Gabriel
- Division of Perioperative Informatics, Department of Anesthesiology, University of California, La Jolla, San Diego, CA, USA.
- Department of Biomedical Informatics, University of California San Diego Health, La Jolla, San Diego, CA, USA.
| |
Collapse
|
2
|
Muir M, Baric A, Kumta S, Watters D, Hodgson R. Measuring and reporting theatre utilization and efficiency. Br J Surg 2024; 111:znad384. [PMID: 37995260 DOI: 10.1093/bjs/znad384] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2023] [Revised: 10/07/2023] [Accepted: 10/20/2023] [Indexed: 11/25/2023]
Affiliation(s)
- Mathew Muir
- Division of Surgery, Northern Health, Epping, Victoria, Australia
| | - Amanda Baric
- Department of Anaesthetics, Northern Health, Epping, Victoria, Australia
- Department of Medical Education, University of Melbourne, Epping, Victoria, Australia
| | - Shekhar Kumta
- Division of Surgery, Northern Health, Epping, Victoria, Australia
- Department of Surgery, University of Melbourne, Epping, Victoria, Australia
| | - David Watters
- Department of Surgery, University Hospital Geelong, Barwon Health, Geelong, Victoria, Australia
- Department of Surgery, Deakin University, Geelong, Victoria, Australia
| | - Russell Hodgson
- Division of Surgery, Northern Health, Epping, Victoria, Australia
- Department of Surgery, University of Melbourne, Epping, Victoria, Australia
| |
Collapse
|
3
|
Song S, Pei L, Chen H, Zhang Y, Sun C, Yi J, Huang Y. Analysis of hospital and payer costs of care: aggressive warming versus routine warming in abdominal major surgery. Front Public Health 2023; 11:1256254. [PMID: 38026375 PMCID: PMC10652782 DOI: 10.3389/fpubh.2023.1256254] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2023] [Accepted: 10/12/2023] [Indexed: 12/01/2023] Open
Abstract
Background Hypothermia is common and active warming is recommended in major surgery. The potential effect on hospitals and payer costs of aggressive warming to a core temperature target of 37°C is poorly understood. Methods In this sub-analysis of the PROTECT trial (clinicaltrials.gov, NCT03111875), we included patients who underwent radical procedures of colorectal cancer and were randomly assigned to aggressive warming or routine warming. Perioperative outcomes, operation room (OR) scheduling process, internal cost accounting data from the China Statistical yearbook (2022), and price lists of medical and health institutions in Beijing were examined. A discrete event simulation (DES) model was established to compare OR efficiency using aggressive warming or routine warming in 3 months. We report base-case net costs and sensitivity analyses of intraoperative aggressive warming compared with routine warming. Costs were calculated in 2022 using US dollars (USD). Results Data from 309 patients were analyzed. The aggressive warming group comprised 161 patients and the routine warming group comprised 148 patients. Compared to routine warming, there were no differences in the incidence of postoperative complications and total hospitalization costs of patients with aggressive warming. The potential benefit of aggressive warming was in the reduced extubation time (7.96 ± 4.33 min vs. 10.33 ± 5.87 min, p < 0.001), lower incidence of prolonged extubation (5.6% vs. 13.9%, p = 0.017), and decreased staff costs. In the DES model, there is no add-on or cancelation of operations performed within 3 months. The net hospital costs related to aggressive warming were higher than those related to routine warming in one operation (138.11 USD vs. 72.34 USD). Aggressive warming will have an economic benefit when the OR staff cost is higher than 2.37 USD/min/person, or the cost of disposable forced-air warming (FAW) is less than 12.88 USD/piece. Conclusion Despite improving OR efficiency, the economic benefits of aggressive warming are influenced by staff costs and the cost of FAW, which vary from different regions and countries. Clinical trial registration clinicaltrials.gov, identifier (NCT03111875).
Collapse
Affiliation(s)
- Shujia Song
- Department of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Lijian Pei
- Department of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Hongda Chen
- Institute for Clinical Medical Research, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Yuelun Zhang
- Institute for Clinical Medical Research, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Chen Sun
- Department of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Jie Yi
- Department of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Yuguang Huang
- Department of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| |
Collapse
|
4
|
Miller LE, Goedicke W, Crowson MG, Rathi VK, Naunheim MR, Agarwala AV. Using Machine Learning to Predict Operating Room Case Duration: A Case Study in Otolaryngology. Otolaryngol Head Neck Surg 2023; 168:241-247. [PMID: 35133897 DOI: 10.1177/01945998221076480] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2021] [Accepted: 01/07/2022] [Indexed: 12/14/2022]
Abstract
OBJECTIVE Optimizing operating room (OR) efficiency depends on accurate case duration estimates. Machine learning (ML) methods have been used to predict OR case durations in other subspecialties. We hypothesize that ML methods improve projected case lengths over existing non-ML techniques for otolaryngology-head and neck surgery cases. METHODS Deidentified patient information from otolaryngology surgical cases at 1 academic institution were reviewed from 2016 to 2020. Variables collected included patient, surgeon, procedure, and facility data known preoperatively so as to capture all realistic contributors. Available case data were divided into a training and testing data set. Several ML algorithms were evaluated based on best performance of predicted case duration when compared to actual case duration. Performance of all models was compared by the average root mean squared error and mean absolute error (MAE). RESULTS In total, 50,888 otolaryngology surgical cases were evaluated with an average case duration of 98.3 ± 86.9 minutes. Most cases were general otolaryngology (n = 16,620). Case features closely associated with OR duration included procedure performed, surgeon, subspecialty of case, and postoperative destination of the patient. The best-performing ML models were CatBoost and XGBoost, which reduced operative time MAE by 9.6 minutes and 8.5 minutes compared to current methods, respectively. DISCUSSION The incorporation of other easily identifiable features beyond procedure performed and surgeon meaningfully improved our operative duration prediction accuracy. CatBoost provided the best-performing ML model. IMPLICATIONS FOR PRACTICE ML algorithms to predict OR case time duration in otolaryngology can improve case duration accuracy and result in financial benefit.
Collapse
Affiliation(s)
- Lauren E Miller
- Department of Otolaryngology-Head and Neck Surgery, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
| | - William Goedicke
- Department of Otolaryngology-Head and Neck Surgery, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
| | - Matthew G Crowson
- Department of Otolaryngology-Head and Neck Surgery, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
| | - Vinay K Rathi
- Department of Otolaryngology-Head and Neck Surgery, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
| | - Matthew R Naunheim
- Department of Otolaryngology-Head and Neck Surgery, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
| | - Aalok V Agarwala
- Department of Anesthesia, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
| |
Collapse
|
5
|
|
6
|
Hurford WE, Welge JA, Eckman MH. Sugammadex versus neostigmine for routine reversal of rocuronium block in adult patients: A cost analysis. J Clin Anesth 2020; 67:110027. [DOI: 10.1016/j.jclinane.2020.110027] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2020] [Revised: 07/30/2020] [Accepted: 08/15/2020] [Indexed: 12/17/2022]
|
7
|
Athanasiadis DI, Monfared S, Whiteside J, Engle T, Timsina L, Banerjee A, Butler A, Stefanidis D. Comparison of operating room inefficiencies and time variability in laparoscopic gastric bypass. Surg Obes Relat Dis 2020; 16:1226-1235. [DOI: 10.1016/j.soard.2020.04.046] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2019] [Revised: 04/14/2020] [Accepted: 04/26/2020] [Indexed: 11/30/2022]
|
8
|
Aravinthan K, Holmes C, Nair SP, Sharma AR, Murphy RA. Impact of ENT resource nurses in improving operating room efficiency. J Otolaryngol Head Neck Surg 2020; 49:52. [PMID: 32703280 PMCID: PMC7379823 DOI: 10.1186/s40463-020-00431-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2019] [Accepted: 05/24/2020] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Operating room (OR) efficiency is related to minutes spared from surgical time and has been linked to the make up of surgical teams and operating room workplace. The research on the efficiency of surgical nursing staff members is scant. The current study evaluates the effect of ENT trained OR resource nurses on the efficiency of operating time during ENT procedures. METHODS Five hundred seventy-three ENT surgery cases from 4 surgeons were retrospectively reviewed. Two hundred forty-two cases had ENT OR nursing staff and 331 cases had non-ENT OR nursing staff. Requested operative times (ROT) and true operative times (TOT) were analyzed. The difference between the TOT and ROT was used to measure operating time efficiency. RESULTS Cases with ROT < 30 min (M = -1.19, SD = 5.01) required 3.34 min less than planned for when an ENT nurse was present compared to those with non-ENT nursing staff which required on average 2.15 min (M = 2.15, SD = 5.68) longer than ROT. Furthermore, cases with ROT > 30 min (M = -4.32, SD = 10.85) required 10.85 min less than planned for when an ENT nurse was present. Conversely with non-ENT nursing staff cases with a ROT > 30 min required on average 6.53 min (M = 6.53, SD = 11.85) longer than ROT. CONCLUSION ENT resource nurses were shown to improve OR efficiency in cases less than 30 min and greater than 30 min. Cases that were greater than 30 min showed the largest increase in efficiency. Specialized ENT nursing staff improved efficiency during common ENT surgeries.
Collapse
Affiliation(s)
- Kaishan Aravinthan
- Division of Otolaryngology - Head and Neck Surgery, Department of Surgery, College of Medicine, University of Saskatchewan, Saskatoon, Saskatchewan, S7N 5E5, Canada
| | - Connor Holmes
- Division of Otolaryngology - Head and Neck Surgery, Department of Surgery, College of Medicine, University of Saskatchewan, Saskatoon, Saskatchewan, S7N 5E5, Canada
| | - Sreejit P Nair
- Division of Otolaryngology - Head and Neck Surgery, Department of Surgery, College of Medicine, University of Saskatchewan, Saskatoon, Saskatchewan, S7N 5E5, Canada
| | - Anil R Sharma
- Division of Otolaryngology - Head and Neck Surgery, Department of Surgery, College of Medicine, University of Saskatchewan, Saskatoon, Saskatchewan, S7N 5E5, Canada
| | - Russell A Murphy
- Division of Otolaryngology - Head and Neck Surgery, Department of Surgery, College of Medicine, University of Saskatchewan, Saskatoon, Saskatchewan, S7N 5E5, Canada.
| |
Collapse
|
9
|
Tsai MH, Breidenstein MW, Flanagan TF, Seong A, Kadry B, Rizzo DM, Urman RD. Applying Performance Frontiers in Operating Room Management: A Tutorial Using Data From an Academic Medical Center. A A Pract 2019; 11:321-327. [PMID: 30169380 DOI: 10.1213/xaa.0000000000000873] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
Abstract
Although the primary goal of operating room (OR) management is to minimize inefficiencies, it may be difficult for OR managers to track metrics when one extrapolates possible scenarios across every OR on a daily basis. With the ability to visualize the statistical relationships to help simplify the analysis of large datasets, a more elaborate efficiency framework can be established using Pareto optimality (or performance frontiers), a multicriteria framework that includes variables that serve as proxies for a variety of outcomes. Applied to OR management, performance frontiers allow for the evaluation of common and well-understood issues of under- and over-utilized time.
Collapse
Affiliation(s)
- Mitchell H Tsai
- From the Departments of Anesthesiology.,Orthopaedics and Rehabilitation (by courtesy).,Surgery (by courtesy), University of Vermont Larner College of Medicine, Burlington, Vermont
| | | | - Timothy F Flanagan
- Department of Anesthesiology & Interventional Pain Medicine, Lahey Hospital & Medical Center, Burlington, Massachusetts
| | - Andrew Seong
- Department of Surgery, University of Washington School of Medicine, Seattle, Washington
| | - Bassam Kadry
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, California
| | - Donna M Rizzo
- Department of Civil & Environmental Engineering, University of Vermont, Burlington, Vermont
| | - Richard D Urman
- Department of Anesthesiology, Perioperative and Pain Medicine, Brigham and Women's Hospital, Boston, Massachusetts
| |
Collapse
|
10
|
Tuwatananurak JP, Zadeh S, Xu X, Vacanti JA, Fulton WR, Ehrenfeld JM, Urman RD. Machine Learning Can Improve Estimation of Surgical Case Duration: A Pilot Study. J Med Syst 2019; 43:44. [PMID: 30656433 DOI: 10.1007/s10916-019-1160-5] [Citation(s) in RCA: 30] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/24/2018] [Accepted: 01/08/2019] [Indexed: 11/30/2022]
Abstract
Operating room (OR) utilization is a significant determinant of hospital profitability. One aspect of this is surgical scheduling, which depends on accurate predictions of case duration. This has been done historically by either the surgeon based on personal experience, or by an electronic health record (EHR) based on averaged historical means for case duration. Here, we compare the predicted case duration (pCD) accuracy of a novel machine-learning algorithm over a 3-month period. A proprietary machine learning algorithm was applied utilizing operating room factors such as patient demographic data, pre-surgical milestones, and hospital logistics and compared to that of a conventional EHR. Actual case duration and pCD (Leap Rail vs EHR) was obtained at one institution over the span of 3 months. Actual case duration was defined as time between patient entry into an OR and time of exit. pCD was defined as case time allotted by either Leap Rail or EHR. Cases where Leap Rail was unable to generate a pCD were excluded. A total of 1059 surgical cases were performed during the study period, with 990 cases being eligible for the study. Over all sub-specialties, Leap Rail showed a 7 min improvement in absolute difference between pCD and actual case duration when compared to conventional EHR (p < 0.0001). In aggregate, the Leap Rail method resulted in a 70% reduction in overall scheduling inaccuracy. Machine-learning algorithms are a promising method of increasing pCD accuracy and represent one means of improving OR planning and efficiency.
Collapse
Affiliation(s)
- Justin P Tuwatananurak
- Department of Anesthesiology, Perioperative and Pain Medicine, Brigham and Women's Hospital, Boston, MA, 02115, USA
| | | | - Xinling Xu
- Department of Anesthesiology, Perioperative and Pain Medicine, Brigham and Women's Hospital, Boston, MA, 02115, USA
| | - Joshua A Vacanti
- Department of Anesthesiology, Perioperative and Pain Medicine, Brigham and Women's Hospital, Boston, MA, 02115, USA
| | | | - Jesse M Ehrenfeld
- Department of Anesthesiology, Vanderbilt University School of Medicine, Nashville, TN, USA
| | - Richard D Urman
- Department of Anesthesiology, Perioperative and Pain Medicine, Brigham and Women's Hospital, Boston, MA, 02115, USA. .,Center for Perioperative Research, Brigham and Women's Hospital, Boston, MA, USA.
| |
Collapse
|