1
|
Wu YC, Chang CY, Huang YT, Chen SY, Chen CH, Kao HK. Artificial Intelligence Image Recognition System for Preventing Wrong-Site Upper Limb Surgery. Diagnostics (Basel) 2023; 13:3667. [PMID: 38132251 PMCID: PMC10743305 DOI: 10.3390/diagnostics13243667] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/02/2023] [Revised: 11/30/2023] [Accepted: 12/02/2023] [Indexed: 12/23/2023] Open
Abstract
Our image recognition system employs a deep learning model to differentiate between the left and right upper limbs in images, allowing doctors to determine the correct surgical position. From the experimental results, it was found that the precision rate and the recall rate of the intelligent image recognition system for preventing wrong-site upper limb surgery proposed in this paper could reach 98% and 93%, respectively. The results proved that our Artificial Intelligence Image Recognition System (AIIRS) could indeed assist orthopedic surgeons in preventing the occurrence of wrong-site left and right upper limb surgery. At the same time, in future, we will apply for an IRB based on our prototype experimental results and we will conduct the second phase of human trials. The results of this research paper are of great benefit and research value to upper limb orthopedic surgery.
Collapse
Affiliation(s)
- Yi-Chao Wu
- Department of Electronic Engineering, National Yunlin University of Science and Technology, Yunlin 950359, Taiwan;
| | - Chao-Yun Chang
- Interdisciplinary Program of Green and Information Technology, National Taitung University, Taitung 950359, Taiwan; (C.-Y.C.); (Y.-T.H.); (S.-Y.C.)
| | - Yu-Tse Huang
- Interdisciplinary Program of Green and Information Technology, National Taitung University, Taitung 950359, Taiwan; (C.-Y.C.); (Y.-T.H.); (S.-Y.C.)
| | - Sung-Yuan Chen
- Interdisciplinary Program of Green and Information Technology, National Taitung University, Taitung 950359, Taiwan; (C.-Y.C.); (Y.-T.H.); (S.-Y.C.)
| | - Cheng-Hsuan Chen
- Department of Electrical Engineering, National Central University, Taoyuan 320317, Taiwan;
- Department of Electrical Engineering, Fu Jen Catholic University, New Taipei City 242062, Taiwan
| | - Hsuan-Kai Kao
- Department of Orthopedic Surgery, Chang Gung Memorial Hospital at Linkou, Taoyuan 333423, Taiwan
- Bone and Joint Research Center, Chang Gung Memorial Hospital at Linkou, Taoyuan 333423, Taiwan
- College of Medicine, Chang Gung University, Taoyuan 333423, Taiwan
| |
Collapse
|
2
|
Arad D, Rosenfeld A, Magnezi R. Factors contributing to preventing operating room "never events": a machine learning analysis. Patient Saf Surg 2023; 17:6. [PMID: 37004090 PMCID: PMC10067209 DOI: 10.1186/s13037-023-00356-x] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2022] [Accepted: 03/09/2023] [Indexed: 04/03/2023] Open
Abstract
BACKGROUND A surgical "Never Event" is a preventable error occurring immediately before, during or immediately following surgery. Various factors contribute to the occurrence of major Never Events, but little is known about their quantified risk in relation to a surgery's characteristics. Our study uses machine learning to reveal and quantify risk factors with the goal of improving patient safety and quality of care. METHODS We used data from 9,234 observations on safety standards and 101 root-cause analyses from actual, major "Never Events" including wrong site surgery and retained foreign item, and three random forest supervised machine learning models to identify risk factors. Using a standard 10-cross validation technique, we evaluated the models' metrics, measuring their impact on the occurrence of the two types of Never Events through Gini impurity. RESULTS We identified 24 contributing factors in six surgical departments: two had an impact of > 900% in Urology, Orthopedics, and General Surgery; six had an impact of 0-900% in Gynecology, Urology, and Cardiology; and 17 had an impact of < 0%. Combining factors revealed 15-20 pairs with an increased probability in five departments: Gynecology, 875-1900%; Urology, 1900-2600%; Cardiology, 833-1500%; Orthopedics,1825-4225%; and General Surgery, 2720-13,600%. Five factors affected wrong site surgery's occurrence (-60.96 to 503.92%) and five affected retained foreign body (-74.65 to 151.43%): two nurses (66.26-87.92%), surgery length < 1 h (85.56-122.91%), and surgery length 1-2 h (-60.96 to 85.56%). CONCLUSIONS Using machine learning, we could quantify the risk factors' potential impact on wrong site surgeries and retained foreign items in relation to a surgery's characteristics, suggesting that safety standards should be adjusted to surgery's characteristics based on risk assessment in each operating room. . TRIAL REGISTRATION NUMBER MOH 032-2019.
Collapse
Affiliation(s)
- Dana Arad
- Department of Management, Health Management Program, Faculty of Sciences, Bar-Ilan University, Ramat Gan, Israel.
- Patient Safety Division, Ministry of Health, Ramat Gan, Israel.
| | - Ariel Rosenfeld
- Department of Information Science, Bar-Ilan University, Ramat Gan, Israel
| | - Racheli Magnezi
- Department of Management, Health Management Program, Faculty of Sciences, Bar-Ilan University, Ramat Gan, Israel
| |
Collapse
|
3
|
Vacheron CH, Acker A, Autran M, Fuz F, Piriou V, Friggeri A, Theissen A. Insurance Claims for Wrong-Side, Wrong-Organ, Wrong-Procedure, or Wrong-Person Surgical Errors: A Retrospective Study for 10 Years. J Patient Saf 2023; 19:e13-e17. [PMID: 36538340 PMCID: PMC9788930 DOI: 10.1097/pts.0000000000001080] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
OBJECTIVE Serious adverse events, such as wrong-side, wrong-organ, wrong-procedure, or wrong-person errors, still occur despite the implementation of preventative measures. In France, we describe the claims related to such errors based on the database from one of the main insurance companies. METHODS A retrospective analysis of claims declared between January 2007 and December 2017 to Relyens, a medical liability insurance company (Sham), was performed. Their database was queried using the following keywords: "wrong side," "wrong organ," and "wrong person." RESULTS We collected 219 claims (0.4% of the total claims). The main specialties involved were orthopedics (34% of cases), neurosurgery (14%), and dentistry (14%). The claims were related to wrong organ (44%), side (39%), identity (13%), or procedure (4%). Juridical entity involved were mainly public facility (69%), followed by private facility (19%) or private physician (10%). The mean number of annual claims made has decreased of 20% since the mandatory implementation of the checklist in 2010 (22 versus 17.5 events per year). The main risk factors identified according to the ALARM protocol were factor related to the team (87%) or to the task to accomplish (78%). A direct causal factor was involved in 20% of the files, the main one being the organization (43%) closely related to the medical file (36%). The settlement was performed by conciliation in 69% of the claim and in court in 30%. The compensation was higher during a court settlement. CONCLUSIONS Wrong-side, wrong-organ, wrong-procedure, or wrong-person surgical errors are rare but fully preventable by the implementation of a safety culture.
Collapse
Affiliation(s)
- Charles-Hervé Vacheron
- From the Département d’Anesthésie Réanimation, Centre Hospitalier Lyon Sud, Hospices Civils de Lyon
- Comité Analyse et Maitrise de Risque de la SFAR
| | - Amélie Acker
- Département d’Anesthésie Réanimation, Hôpital Femme Mère Enfant, Hospices Civils de Lyon
| | - Melanie Autran
- Directrice du Marché des Professionnels de Santé, Sham—Relyens Groupe, Lyon, France
| | - Frederic Fuz
- Directeur Risk Management Espagne, Sham—Relyens Groupe, Barcelona, Spain
| | - Vincent Piriou
- From the Département d’Anesthésie Réanimation, Centre Hospitalier Lyon Sud, Hospices Civils de Lyon
| | - Arnaud Friggeri
- From the Département d’Anesthésie Réanimation, Centre Hospitalier Lyon Sud, Hospices Civils de Lyon
| | - Alexandre Theissen
- Comité Analyse et Maitrise de Risque de la SFAR
- Service d’Anesthésie, Clinique Saint François, Groupe Vivalto, Nice, France
| |
Collapse
|
4
|
Omar I, Singhal R, Wilson M, Parmar C, Khan O, Mahawar K. Common general surgical never events: analysis of NHS England never event data. Int J Qual Health Care 2021; 33:6162643. [PMID: 33693752 DOI: 10.1093/intqhc/mzab045] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/02/2020] [Revised: 01/10/2021] [Accepted: 03/08/2021] [Indexed: 11/12/2022] Open
Abstract
BACKGROUND There is little available data on common general surgical never events (NEs). Lack of this information may have affected our attempts to reduce the incidence of these potentially serious clinical incidents. OBJECTIVES The purpose of this study was to identify common general surgical NEs from the data held by the National Health Service (NHS) England. METHODS We analysed the NHS England NE data from April 2012 to February 2020 to identify common general surgical NEs. RESULTS There was a total of 797 general surgical NEs identified under three main categories such as wrong-site surgery (n = 427; 53.58%), retained items post-procedure (n = 355; 44.54%) and wrong implant/prosthesis (n = 15; 1.88%). We identified a total of 56 common general surgical themes-25 each in the wrong-site surgery and retained foreign body categories and six in wrong implants category.Wrong skin condition surgery was the commonest wrong-site surgery (n = 117; 27.4%). There were 18 wrong-side chest drains (4.2%) and 18 (4.2%) wrong-side angioplasty/angiograms. There were seven (1.6%) instances of confusion in pilonidal/perianal/perineal surgeries and six (1.4%) instances of biopsy of the cervix rather than the colon or rectum.Retained surgical swabs were the most common retained items (n = 165; 46.5%). There were 28 (7.9%) laparoscopic retrieval bags with or without the specimen, 26 (7.3%) chest drain guide wires, 26 (7.3%) surgical needles and 9 (2.5%) surgical drains. Wrong stents were the most common (n = 9; 60%) wrong implants followed by wrong breast implants (n = 2; 13.3%). CONCLUSION This study found 56 common general surgical NEs. This information is not available to surgeons around the world. Increased awareness of these common themes of NEs may allow for the adoption of more effective and specific safeguards and ultimately help reduce their incidence.
Collapse
Affiliation(s)
- Islam Omar
- Bariatric Unit, Department of General Surgery, Sunderland Royal Hospital, South Tyneside and Sunderland NHS Trust, Kayll Rd, Sunderland SR4 7TP, UK
| | - Rishi Singhal
- Bariatric & Upper GI Surgery Unit, Birmingham Heartlands Hospital, University Hospital Birmingham NHS Foundation Trust, Bordesley Green E, Birmingham B9 5SS, UK
| | - Michael Wilson
- Upper Surgery Unit, NHS Forth Valley, Stirling Rd, Larbert FK5 4WR, UK
| | - Chetan Parmar
- Upper GI Surgery Unit, Whittington Health NHS Trust, Magdala Ave, Highgate, London N19 5NF, UK
| | - Omar Khan
- Upper GI Surgery Unit, St. George's University Hospitals NHS Foundation Trust, Blackshaw Rd, Tooting, London SW17 0QT, UK
| | - Kamal Mahawar
- Bariatric Unit, Department of General Surgery, Sunderland Royal Hospital, South Tyneside and Sunderland NHS Trust, Kayll Rd, Sunderland SR4 7TP, UK.,Faculty of Health Sciences and Wellbeing, University of Sunderland, Sunderland SR1 3SD, UK
| |
Collapse
|
5
|
Strabismus surgical time-out: an illustrated whiteboard modification. J AAPOS 2021; 25:72.e1-72.e4. [PMID: 33737054 DOI: 10.1016/j.jaapos.2020.10.014] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/01/2020] [Revised: 10/21/2020] [Accepted: 10/30/2020] [Indexed: 11/24/2022]
Abstract
BACKGROUND Errors in strabismus surgery-including wrong eye, wrong muscle, and wrong procedure-can occur when there is confusion about the surgical plan among members of the surgical team, including surgeons, anesthesia staff, nurses, and technicians. The purpose of this study was to assess whether implementation of a strabismus-specific whiteboard combined with oral statement of the surgical plan using nonophthalmological terminology could improve communication among the team before commencement of surgery. METHODS A strabismus-specific whiteboard with labeled diagram of the eyes and extraocular muscles was designed. Patient identifiers, diagnosis, deviation, and procedure name were included. This whiteboard was completed preoperatively and referenced during time-out. The surgeons and operating room staff were trained in its use, and surveys were completed before and 6 months after implementation of the whiteboard time-out. RESULTS The pre-implementation survey was completed by 19 operating room staff members, of whom 15 completed the post-implementation survey. The strabismus specific whiteboard increased staff member understanding of procedure laterality (74% to 93%), muscle(s) to be operated (37% to 93%), and specific procedure(s) planned (37% to 87%). Surgeon surveys also showed increased confidence in staff member understanding of each parameter with whiteboard use. CONCLUSIONS A standardized time-out combined with an illustrated strabismus surgery whiteboard improves communication between team members and has the potential to reduce surgical errors.
Collapse
|
6
|
Identification of Common Themes from Never Events Data Published by NHS England. World J Surg 2020; 45:697-704. [PMID: 33216170 DOI: 10.1007/s00268-020-05867-7] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 10/31/2020] [Indexed: 01/04/2023]
Abstract
BACKGROUND Never events (NEs) are serious clinical incidents that cause potentially avoidable harm and impose a significant financial burden on healthcare systems. The purpose of this study was to identify common never events. METHODS We analysed the NHS England NE data from 2012 to 2020 to identify common never events category and themes. RESULTS We identified 51 common NE themes in 4 main categories out of a total of 3247 NE reported during this period. Wrong-site surgery was the most common category (n = 1307;40.25%) followed by retained foreign objects (n = 901;27.75%); wrong implant or prosthesis (n = 425;13.09%); and non-surgical/infrequent ones (n = 614; 18.9%). Wrong-side (laterality) and wrong tooth removal were the most common wrong-site NE accounting for 300 (22.95%) and 263 (20.12%) incidents, respectively. There were 197 (15%) wrong-site blocks, 125 (9.56%) wrong procedures, and 96 (7.3%) wrong skin lesions excised. Vaginal swabs were the most commonly retained items (276;30.63%) followed by surgical swabs (164;18.20%) and guidewires (152;16.87%). There were 67 (7.44%) incidents of retained parts of instruments and 48 (5.33%) retained instruments. Wrong intraocular lenses (165; 38.82%) were the most common wrong implants followed by wrong hip prostheses (n = 94; 22.11%) and wrong knees (n = 91; 21.41%). Non-surgical events accounted for 18.9% (n = 614) of the total incidents. Misplaced naso-or oro-gastric tubes (n = 178;29%) and wrong-route administration of medications were the most common events in this category (n = 111;18%), followed by unintentional connection of a patient requiring oxygen to an air flow-meter (n = 93; 15%). CONCLUSION This paper identifies common NE categories and themes. Awareness of these might help reduce their incidence.
Collapse
|
7
|
Wollina U. Preoperative Site Marking in Dermatosurgery. J Cutan Aesthet Surg 2019; 12:191-192. [PMID: 31619893 PMCID: PMC6785962 DOI: 10.4103/jcas.jcas_178_18] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022] Open
Abstract
Dermatosurgery is a growing subspeciality due to increasing numbers of skin cancer and aesthetic procedures. Patient safety is a major issue in dermatosurgery. Quality management, education, and organization are the backbone of patient safety. A simple measure to support patient’s safety and to avoid wrong site surgery is preoperative skin marking. Permanent skin markers offer a painless and cost-effective option. To ensure optimal results, the following problems need careful consideration: good viability after disinfection, sterility of the operation field, no sensitization, or toxic effects of the ink. These issues are discussed in detail to allow a safe and successful procedure.
Collapse
Affiliation(s)
- Uwe Wollina
- Department of Dermatology and Allergology, Städtisches Klinikum Dresden, Academic Teaching Hospital, Dresden, Germany
| |
Collapse
|
8
|
Neily J, Soncrant C, Mills PD, Paull DE, Mazzia L, Young-Xu Y, Nylander W, Lynn MM, Gunnar W. Assessment of Incorrect Surgical Procedures Within and Outside the Operating Room: A Follow-up Study From US Veterans Health Administration Medical Centers. JAMA Netw Open 2018; 1:e185147. [PMID: 30646381 PMCID: PMC6324368 DOI: 10.1001/jamanetworkopen.2018.5147] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/12/2022] Open
Abstract
IMPORTANCE Reducing wrong-site surgery is fundamental to safe, high-quality care. This is a follow-up study examining 8 years of reported surgical adverse events and root causes in the nation's largest integrated health care system. OBJECTIVES To provide a follow-up description of incorrect surgical procedures reported from 2010 to 2017 from US Veterans Health Administration (VHA) medical centers, compared with the previous studies of 2001 to 2006 and 2006 to 2009, and to recommend actions for future prevention of such events. DESIGN, SETTING, AND PARTICIPANTS This quality improvement study describes patient safety adverse events and close calls reported from 86 VHA medical centers from the approximately 130 VHA facilities with a surgical program. The surgical procedures and programs vary in size and complexity from small rural centers to large, complex urban facilities. Procedures occurring between January 1, 2010, and December 31, 2017, were included. Data analysis took place in 2018. MAIN OUTCOMES AND MEASURES The categories of incorrect procedure types were wrong patient, side, site (including wrong-level spine), procedure, or implant. Events included those in or out of the operating room, adverse events or close calls, surgical specialty, and harm. These results were compared with the previous studies of VHA-reported wrong-site surgery (2001-2006 and 2006-2009). RESULTS Our review produced 483 reports (277 adverse events and 206 close calls). The rate of in-operating room (in-OR) reported adverse events with harm has continued to trend downward from 1.74 to 0.47 reported adverse events with harm per 100 000 procedures between 2000 and 2017 based on 6 591 986 in-OR procedures. When in-OR events were examined by discipline as a rate, dentistry had 1.54, neurosurgery had 1.53, and ophthalmology had 1.06 reported in-OR adverse events per 10 000 cases. The overall VHA in-OR rate for adverse events during 2010 to 2017 was 0.53 per 10 000 procedures based on 3 234 514 in-OR procedures. The most common root cause for adverse events was related to issues in performing a comprehensive time-out (28.4%). In these cases, the time-out either was conducted incorrectly or was incomplete in some way. CONCLUSIONS AND RELEVANCE Over the period studied, the VHA identified a decrease in the rate of reported adverse events in the OR associated with harm and continued reporting of adverse event close calls. Organizational efforts continue to examine root cause analysis reports, promulgate lessons learned, and enhance policy to promote a culture and behavior that minimizes events and is transparent in reporting occurrences.
Collapse
Affiliation(s)
- Julia Neily
- National Center for Patient Safety, Veterans Health Administration, White River Junction, Vermont
| | - Christina Soncrant
- National Center for Patient Safety, Veterans Health Administration, White River Junction, Vermont
| | - Peter D. Mills
- National Center for Patient Safety, Veterans Health Administration, White River Junction, Vermont
- Geisel School of Medicine at Dartmouth, Hanover, New Hampshire
| | - Douglas E. Paull
- National Center for Patient Safety, Veterans Health Administration, White River Junction, Vermont
- Georgetown University School of Medicine, Washington, DC
| | - Lisa Mazzia
- National Center for Patient Safety, Veterans Health Administration, White River Junction, Vermont
| | - Yinong Young-Xu
- National Center for Patient Safety, Veterans Health Administration, White River Junction, Vermont
| | - William Nylander
- National Surgery Office, Veterans Health Administration, Washington, DC
| | - Marilyn M. Lynn
- National Surgery Office, Veterans Health Administration, Washington, DC
| | - William Gunnar
- National Surgery Office, Veterans Health Administration, Washington, DC
- Loyola University Stritch School of Surgery, Chicago, Illinois
| |
Collapse
|
9
|
Insalaco LF, Spiegel JH. A Surgical Procedure Grid for Safety and Operating Room Communication in Multisite Surgery. JAMA FACIAL PLAST SU 2018; 20:185-186. [PMID: 29327040 DOI: 10.1001/jamafacial.2017.2049] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022]
Affiliation(s)
- Louis F Insalaco
- Department of Otolaryngology-Head and Neck Surgery, Boston University School of Medicine, Boston, Massachusetts
| | - Jeffrey H Spiegel
- Division of Facial Plastic and Reconstructive Surgery, Department of Otolaryngology-Head and Neck Surgery, Boston University School of Medicine, Boston, Massachusetts
| |
Collapse
|