1
|
Loos NL, Hoogendam L, Souer JS, van Uchelen JH, Slijper HP, Wouters RM, Selles RW. Algorithm Versus Expert: Machine Learning Versus Surgeon-Predicted Symptom Improvement After Carpal Tunnel Release. Neurosurgery 2024; 95:00006123-990000000-01037. [PMID: 38299861 PMCID: PMC11155572 DOI: 10.1227/neu.0000000000002848] [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: 09/22/2023] [Accepted: 12/12/2023] [Indexed: 02/02/2024] Open
Abstract
BACKGROUND AND OBJECTIVES Surgeons rely on clinical experience when making predictions about treatment effects. Incorporating algorithm-based predictions of symptom improvement after carpal tunnel release (CTR) could support medical decision-making. However, these algorithm-based predictions need to outperform predictions made by surgeons to add value. We compared predictions of a validated prediction model for symptom improvement after CTR with predictions made by surgeons. METHODS This cohort study included 97 patients scheduled for CTR. Preoperatively, surgeons estimated each patient's probability of improvement 6 months after surgery, defined as reaching the minimally clinically important difference on the Boston Carpal Tunnel Syndrome Symptom Severity Score. We assessed model and surgeon performance using calibration (calibration belts), discrimination (area under the curve [AUC]), sensitivity, and specificity. In addition, we assessed the net benefit of decision-making based on the prediction model's estimates vs the surgeon's judgement. RESULTS The surgeon predictions had poor calibration and suboptimal discrimination (AUC 0.62, 95%-CI 0.49-0.74), while the prediction model showed good calibration and appropriate discrimination (AUC 0.77, 95%-CI 0.66-0.89, P = .05). The accuracy of surgeon predictions was 0.65 (95%-CI 0.37-0.78) vs 0.78 (95%-CI 0.67-0.89) for the prediction model ( P = .03). The sensitivity of surgeon predictions and the prediction model was 0.72 (95%-CI 0.15-0.96) and 0.85 (95%-CI 0.62-0.97), respectively ( P = .04). The specificity of the surgeon predictions was similar to the model's specificity ( P = .25). The net benefit analysis showed better decision-making based on the prediction model compared with the surgeons' decision-making (ie, more correctly predicted improvements and/or fewer incorrectly predicted improvements). CONCLUSION The prediction model outperformed surgeon predictions of improvement after CTR in terms of calibration, accuracy, and sensitivity. Furthermore, the net benefit analysis indicated that using the prediction model instead of relying solely on surgeon decision-making increases the number of patients who will improve after CTR, without increasing the number of unnecessary surgeries.
Collapse
Affiliation(s)
- Nina Louisa Loos
- Department of Rehabilitation Medicine, Erasmus MC, Rotterdam, The Netherlands
- Department of Plastic and Reconstructive Surgery and Hand Surgery, Erasmus MC, Rotterdam, The Netherlands
| | - Lisa Hoogendam
- Department of Rehabilitation Medicine, Erasmus MC, Rotterdam, The Netherlands
- Department of Plastic and Reconstructive Surgery and Hand Surgery, Erasmus MC, Rotterdam, The Netherlands
- Hand and Wrist Center, Xpert Clinics, Eindhoven, The Netherlands
| | | | | | | | - Robbert Maarten Wouters
- Department of Rehabilitation Medicine, Erasmus MC, Rotterdam, The Netherlands
- Department of Plastic and Reconstructive Surgery and Hand Surgery, Erasmus MC, Rotterdam, The Netherlands
| | - Ruud Willem Selles
- Department of Rehabilitation Medicine, Erasmus MC, Rotterdam, The Netherlands
- Department of Plastic and Reconstructive Surgery and Hand Surgery, Erasmus MC, Rotterdam, The Netherlands
| |
Collapse
|
2
|
Akpinar EO, Ghaferi AA, Liem RSL, Bonham AJ, Nienhuijs SW, Greve JWM, Marang-van de Mheen PJ. Predicting serious complication risks after bariatric surgery: external validation of the Michigan Bariatric Surgery Collaborative risk prediction model using the Dutch Audit for Treatment of Obesity. Surg Obes Relat Dis 2023; 19:212-221. [PMID: 36274015 DOI: 10.1016/j.soard.2022.09.008] [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: 06/13/2022] [Revised: 08/14/2022] [Accepted: 09/10/2022] [Indexed: 11/30/2022]
Abstract
BACKGROUND Risk-prediction tools can support doctor-patient (shared) decision making in clinical practice by providing information on complication risks for different types of bariatric surgery. However, external validation is imperative to ensure the generalizability of predictions in a new patient population. OBJECTIVE To perform an external validation of the risk-prediction model for serious complications from the Michigan Bariatric Surgery Collaborative (MBSC) for Dutch bariatric patients using the nationwide Dutch Audit for Treatment of Obesity (DATO). SETTING Population-based study, including all 18 hospitals performing bariatric surgery in the Netherlands. METHODS All patients registered in the DATO undergoing bariatric surgery between 2015 and 2020 were included as the validation cohort. Serious complications included, among others, abdominal abscess, bowel obstruction, leak, and bleeding. Three risk-prediction models were validated: (1) the original MBSC model from 2011, (2) the original MBSC model including the same variables but updated to more recent patients (2015-2020), and (3) the current MBSC model. The following predictors from the MBSC model were available in the DATO: age, sex, procedure type, cardiovascular disease, and pulmonary disease. Model performance was determined using the area under the curve (AUC) to assess discrimination (i.e., the ability to distinguish patients with events from those without events) and a graphical plot to assess calibration (i.e., whether the predicted absolute risk for patients was similar to the observed prevalence of the outcome). RESULTS The DATO validation cohort included 51,291 patients. Overall, 986 patients (1.92%) experienced serious complications. The original MBSC model, which was extended with the predictors "GERD (yes/no)," "OSAS (yes/no)," "hypertension (yes/no)," and "renal disease (yes/no)," showed the best validation results. This model had a good calibration and an AUC of .602 compared with an AUC of .65 and moderate to good calibration in the Michigan model. CONCLUSION The DATO prediction model has good calibration but moderate discrimination. To be used in clinical practice, good calibration is essential to accurately predict individual risks in a real-world setting. Therefore, this model could provide valuable information for bariatric surgeons as part of shared decision making in daily practice.
Collapse
Affiliation(s)
- Erman O Akpinar
- Department of Surgery, Maastricht University Medical Center, NUTRIM School for Nutrition and Translational Research in Metabolism, Maastricht, The Netherlands; Scientific Bureau, Dutch Institute for Clinical Auditing, Leiden, The Netherlands.
| | - Amir A Ghaferi
- Department of Surgery, University of Michigan, Ann Arbor, Michigan
| | - Ronald S L Liem
- Department of Surgery, Groene Hart Hospital, Gouda, The Netherlands; Dutch Obesity Clinic, The Hague & Gouda, The Netherlands
| | - Aaron J Bonham
- Department of Surgery, University of Michigan, Ann Arbor, Michigan
| | - Simon W Nienhuijs
- Department of Surgery, Catharina Hospital, Eindhoven, The Netherlands
| | - Jan Willem M Greve
- Department of Surgery, Maastricht University Medical Center, NUTRIM School for Nutrition and Translational Research in Metabolism, Maastricht, The Netherlands; Department of Surgery, Zuyderland Medical Centre, Heerlen, The Netherlands; Dutch Obesity Clinic South, Heerlen, The Netherlands
| | - Perla J Marang-van de Mheen
- Department of Biomedical Data Sciences, Medical Decision Making, Leiden University Medical Centre, Leiden, The Netherlands
| | | |
Collapse
|
3
|
Battle C, Giamello J, Hutchings H. The clinical effectiveness of the STUMBL score for the management of ED patients with blunt chest trauma compared to clinical evaluation alone: comment. Intern Emerg Med 2023; 18:337-338. [PMID: 36029397 DOI: 10.1007/s11739-022-03082-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/30/2022] [Accepted: 08/11/2022] [Indexed: 02/01/2023]
Affiliation(s)
- Ceri Battle
- Emergency Department, Swansea Bay University Health Board, Swansea, Wales.
| | - Jacopo Giamello
- School of Emergency Medicine, University of Turin, Turin, Italy
- Department of Emergency Medicine, Santa Croce E Carle Hospital, Cuneo, Italy
| | - Hayley Hutchings
- Swansea Trials Unit, Swansea University Medical School, Swansea, Wales
| |
Collapse
|
4
|
Baker E, Xyrichis A, Norton C, Hopkins P, Lee G. Building consensus on inpatient discharge pathway components in the management of blunt thoracic injuries: An e-Delphi study amongst an international professional expert panel. Injury 2021; 52:2551-2559. [PMID: 33849725 DOI: 10.1016/j.injury.2021.03.061] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/21/2021] [Revised: 03/02/2021] [Accepted: 03/30/2021] [Indexed: 02/02/2023]
Abstract
INTRODUCTION Access to a standardised and evidence informed approach to blunt thoracic injury (BTI) management remains challenging across organised trauma systems globally. It remains important to optimise recovery through pathway-based interventions. The aim of this study was to identify components of care that are important in the effective discharge process for patients with BTI and pinpoint core and optional components for a patient pathway-based intervention. METHODS Components of care within the hospital discharge process after BTI were identified using existing literature and expert opinion. These initial data were entered into a three-round e-Delphi consensus method where round one involved further integrating and categorising components of discharge care from the expert panel. The panel comprised of an international interdisciplinary group of healthcare professionals with experience in the management of BTI. All questionnaires were completed anonymously using an online survey and involved rating care components using Likert scales (Range: 1-6). The final consensus threshold for pathway components were defined as a group rating of greater than 70% scoring in either the moderate importance (3-4) or high importance category (5-6) and less than 15% of the panel scoring within the low importance category (1-2). RESULTS Of 88 recruited participants, 67 (76%) participated in round one. Statements were categorised into nine themes: (i) Discharge criteria; (ii) Physical function and Self-care; (iii) Pain management components; (iv) Respiratory function components; (v) General care components; (vi) Follow-up; (vii) Psychological care components; (viii) Patient, family and communication; (ix) 'Red Flag' signs and symptoms. Overall, 70 statements were introduced into the consensus building exercise in round two. In round three, 40 statements from across these categorises achieved consensus amongst the expert panel, forming a framework of core and optional care components within the discharge process after BTI. CONCLUSIONS These data will be used to build a toolkit containing guidance on developing discharge pathways for patients with BTI and for the development of audit benchmarks for analysing healthcare provision in this area. It is important that interventions developed using this framework are validated locally and evaluated for efficacy using appropriate research methodology.
Collapse
Key Words
- Consensus study abbreviations BTI, Blunt thoracic injury
- Delphi method
- FEV1, Forced expiratory volume in 1 second
- IQR, Interquartile range
- Injury
- MDT, Multidisciplinary team
- MTC, Major trauma centre
- OPD, Outpatient department
- OT, Occupational therapist
- PT, Physiotherapist
- Pathway development
- Rib fracture
- SD, Standard deviation
- Trauma
- VAS, Visual analogue scale
Collapse
Affiliation(s)
- Edward Baker
- Florence Nightingale Faculty of Nursing, Midwifery and Palliative Care, King's College London, James Clerk Maxwell Building, 57 Waterloo Road, London SE1 8WA, UK; Emergency Department, King's College Hospital NHS Foundation Trust, Denmark Hill, London SE5 9RS, UK.
| | - Andreas Xyrichis
- Florence Nightingale Faculty of Nursing, Midwifery and Palliative Care, King's College London, James Clerk Maxwell Building, 57 Waterloo Road, London SE1 8WA, UK.
| | - Christine Norton
- Florence Nightingale Faculty of Nursing, Midwifery and Palliative Care, King's College London, James Clerk Maxwell Building, 57 Waterloo Road, London SE1 8WA, UK.
| | - Philip Hopkins
- Department of Intensive Care Medicine, King's College Hospital NHS Foundation Trust, Denmark Hill, London SE5 9RS, UK.
| | - Geraldine Lee
- Florence Nightingale Faculty of Nursing, Midwifery and Palliative Care, King's College London, James Clerk Maxwell Building, 57 Waterloo Road, London SE1 8WA, UK.
| |
Collapse
|
5
|
Hamm RF, Levine LD, Nelson MN, Beidas R. Implementation of a calculator to predict cesarean delivery during labor induction: a qualitative evaluation of the clinician perspective. Am J Obstet Gynecol MFM 2021; 3:100321. [PMID: 33493705 DOI: 10.1016/j.ajogmf.2021.100321] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2020] [Revised: 01/15/2021] [Accepted: 01/19/2021] [Indexed: 10/22/2022]
Abstract
BACKGROUND We previously conducted a prospective cohort study (n=1610) demonstrating that the implementation of a validated calculator to predict likelihood of cesarean delivery during labor induction was associated with reduced maternal morbidity, reduced cesarean delivery rate, and improved birth satisfaction. OBJECTIVE To optimize future implementation, we used qualitative interviews to understand the clinician perspective on: (1) the cesarean delivery risk calculator implementation and (2) the mechanisms by which the use of the calculator resulted in the observed improved outcomes. STUDY DESIGN After completion of the prospective study (June 30, 2019), 20 trainees and attending clinicians (including nurse-midwives, obstetrical physicians, and family medicine physicians) at the study site participated in a single, brief semistructured interview from March 1, 2020, to June 30, 2020. Transcriptions were coded using a systematic approach. RESULTS Overall, clinicians had favorable perspectives regarding the cesarean delivery risk calculator. Clinicians described the calculator as offering "objective data" and a "standardized snapshot of the labor trajectory." Concerns were raised regarding "overreliance" on calculator output. Barriers to use included time for patient counseling and "awkwardness" around the interactions and perceived patient misunderstanding of the calculator result. Although most senior clinicians (n=8) reported that the calculator did not impact patient management, trainee clinicians (n=12) more often felt that the calculator influenced care at the extremes of cesarean delivery risk. Furthermore, more senior clinicians felt "neutral" regarding any impact of counseling patients on cesarean delivery risk compared with trainee clinicians, who felt that the counseling "built [patient-clinician] trust." CONCLUSION This qualitative evaluation characterized the generally positive clinician perspective around the cesarean delivery risk calculator, while identifying specific facilitators and barriers to implementation. In addition, we elucidated potential mechanisms by which the calculator may have been related to clinician decision making and patient-clinician interactions, leading to reduced maternal morbidity and improved patient birth satisfaction. This information is important as widespread implementation of the cesarean delivery risk calculator begins.
Collapse
Affiliation(s)
- Rebecca F Hamm
- Maternal and Child Health Research Center, Department of Obstetrics and Gynecology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA (Drs Hamm and Levine).
| | - Lisa D Levine
- Maternal and Child Health Research Center, Department of Obstetrics and Gynecology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA (Drs Hamm and Levine)
| | - Maria N Nelson
- Mixed Methods Research Lab, University of Pennsylvania, Philadelphia, PA (Ms Nelson)
| | - Rinad Beidas
- Departments of Psychiatry, Medical Ethics and Health Policy, and Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA (Dr Beidas); Penn Implementation Science Center (PISCE@LDI), Leonard Davis Institute of Health Economics, University of Pennsylvania, Philadelphia, PA (Dr Beidas)
| |
Collapse
|