Publications by authors named "Jacobien H F Oosterhoff"

8 Publications

  • Page 1 of 1

Availability and reporting quality of external validations of machine-learning prediction models with orthopedic surgical outcomes: a systematic review.

Acta Orthop 2021 Apr 18:1-9. Epub 2021 Apr 18.

Orthopedic Oncology Service, Massachusetts General Hospital, Harvard Medical School, Boston, USA;

Background and purpose - External validation of machine learning (ML) prediction models is an essential step before clinical application. We assessed the proportion, performance, and transparent reporting of externally validated ML prediction models in orthopedic surgery, using the Transparent Reporting for Individual Prognosis or Diagnosis (TRIPOD) guidelines.Material and methods - We performed a systematic search using synonyms for every orthopedic specialty, ML, and external validation. The proportion was determined by using 59 ML prediction models with only internal validation in orthopedic surgical outcome published up until June 18, 2020, previously identified by our group. Model performance was evaluated using discrimination, calibration, and decision-curve analysis. The TRIPOD guidelines assessed transparent reporting.Results - We included 18 studies externally validating 10 different ML prediction models of the 59 available ML models after screening 4,682 studies. All external validations identified in this review retained good discrimination. Other key performance measures were provided in only 3 studies, rendering overall performance evaluation difficult. The overall median TRIPOD completeness was 61% (IQR 43-89), with 6 items being reported in less than 4/18 of the studies.Interpretation - Most current predictive ML models are not externally validated. The 18 available external validation studies were characterized by incomplete reporting of performance measures, limiting a transparent examination of model performance. Further prospective studies are needed to validate or refute the myriad of predictive ML models in orthopedics while adhering to existing guidelines. This ensures clinicians can take full advantage of validated and clinically implementable ML decision tools.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1080/17453674.2021.1910448DOI Listing
April 2021

Augmented and virtual reality in spine surgery, current applications and future potentials.

Spine J 2021 Mar 25. Epub 2021 Mar 25.

Spine Service, Department of Orthopaedic Surgery, Massachusetts General Hospital, Boston, MA, USA; Orthopaedic Oncology Service, Department of Orthopaedic Surgery, Massachusetts General Hospital, Boston, MA, USA.

Background Context: The field of Artificial Intelligence (AI) is rapidly advancing, especially with recent improvements in deep learning (DL) techniques. Augmented (AR) and virtual reality (VR) are finding their place in healthcare, and spine surgery is no exception. The unique capabilities and advantages of AR and VR devices include their low cost, flexible integration with other technologies, user-friendly features and their application in navigation systems, which makes them beneficial across different aspects of spine surgery. Despite the use of AR for pedicle screw placement, targeted cervical foraminotomy, bone biopsy, osteotomy planning, and percutaneous intervention, the current applications of AR and VR in spine surgery remain limited.

Purpose: The primary goal of this study was to provide the spine surgeons and clinical researchers with the general information about the current applications, future potentials, and accessibility of AR and VR systems in spine surgery.

Study Design/setting: We reviewed titles of more than 250 journal papers from google scholar and PubMed with search words: augmented reality, virtual reality, spine surgery, and orthopaedic, out of which 89 related papers were selected for abstract review. Finally, full text of 67 papers were analyzed and reviewed.

Methods: The papers were divided into four groups: technological papers, applications in surgery, applications in spine education and training, and general application in orthopaedic. A team of two reviewers performed paper reviews and a thorough web search to ensure the most updated state of the art in each of four group is captured in the review.

Results: In this review we discuss the current state of the art in AR and VR hardware, their preoperative applications and surgical applications in spine surgery. Finally, we discuss the future potentials of AR and VR and their integration with AI, robotic surgery, gaming, and wearables.

Conclusions: AR and VR are promising technologies that will soon become part of standard of care in spine surgery.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.spinee.2021.03.018DOI Listing
March 2021

Machine learning prediction models in orthopedic surgery: A systematic review in transparent reporting.

J Orthop Res 2021 Mar 18. Epub 2021 Mar 18.

Orthopedic Oncology Service, Department of Orthopedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.

Machine learning (ML) studies are becoming increasingly popular in orthopedics but lack a critically appraisal of their adherence to peer-reviewed guidelines. The objective of this review was to (1) evaluate quality and transparent reporting of ML prediction models in orthopedic surgery based on the transparent reporting of multivariable prediction models for individual prognosis or diagnosis (TRIPOD), and (2) assess risk of bias with the Prediction model Risk Of Bias ASsessment Tool. A systematic review was performed to identify all ML prediction studies published in orthopedic surgery through June 18th, 2020. After screening 7138 studies, 59 studies met the study criteria and were included. Two reviewers independently extracted data and discrepancies were resolved by discussion with at least two additional reviewers present. Across all studies, the overall median completeness for the TRIPOD checklist was 53% (interquartile range 47%-60%). The overall risk of bias was low in 44% (n = 26), high in 41% (n = 24), and unclear in 15% (n = 9). High overall risk of bias was driven by incomplete reporting of performance measures, inadequate handling of missing data, and use of small datasets with inadequate outcome numbers. Although the number of ML studies in orthopedic surgery is increasing rapidly, over 40% of the existing models are at high risk of bias. Furthermore, over half incompletely reported their methods and/or performance measures. Until these issues are adequately addressed to give patients and providers trust in ML models, a considerable gap remains between the development of ML prediction models and their implementation in orthopedic practice.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/jor.25036DOI Listing
March 2021

Development of a postoperative delirium risk scoring tool using data from the Australian and New Zealand Hip Fracture Registry: an analysis of 6672 patients 2017-2018.

Arch Gerontol Geriatr 2021 May-Jun;94:104368. Epub 2021 Feb 1.

Department of Orthopaedic & Trauma Surgery, Flinders Medical Centre, Flinders University, Adelaide, SA, Australia. Electronic address:

Background And Purpose: This study aimed to determine the incidence, predictors of postoperative delirium and develop a post-surgery delirium risk scoring tool.

Patients And Methods: A total of 6672 hip fracture patients with documented assessment for delirium were analyzed from the Australia and New Zealand Hip Fracture Registry between June 2017 and December 2018.Thirty-six variables for the prediction of delirium using univariate and multivariate logistic regression were assessed. The models were assessed for diagnostic accuracy using C-statistic and calibration using Hosmer-Lemeshow goodness-of-fit test. A Delirium Risk Score was developed based on the regression coefficients.

Results: Delirium developed in 2599/6672 (39.0%) hip fracture patients. Seven independent predictors of delirium were identified; age above 80 years (OR=1.6 CI 1.4-1.9; p=0.001), male (OR=1.3 CI 1.1-1.5; p=0.007), absent pre-operative cognitive assessment (OR=1.5 CI 1.3-1.9; p=0.001), impaired pre-operative cognitive state (OR=1.7 CI 1.3 -2.1; p=0.001), surgery delay (OR=1.7 CI 1.2-2.5; p=0.002) and mobilisation day 1 post-surgery (OR=1.9 CI 1.4-2.6; p=0.001). The C-statistics for the training and validation datasets were 0.74 and 0.75, respectively. Calibration was good (χ2=35.72 (9); p<0.001). The Delirium Risk Score for patients ranged from 0 to 42 in the validation data and when used alone as a risk predictor, had similar levels of diagnostic accuracy (C-statistic=0.742) indicating its potential for use as a stand-alone risk scoring tool.

Conclusion: We have designed and validated a delirium risk score for predicting delirium following surgery for a hip fracture using seven predicting factors. This could assist clinicians in identifying high risk patients requiring higher levels of observation and post-surgical care.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.archger.2021.104368DOI Listing
February 2021

Artificial intelligence in orthopaedics: false hope or not? A narrative review along the line of Gartner's hype cycle.

EFORT Open Rev 2020 10 26;5(10):593-603. Epub 2020 Oct 26.

Department of Orthopaedic Surgery, Amsterdam UMC, University of Amsterdam, the Netherlands.

Artificial Intelligence (AI) in general, and Machine Learning (ML)-based applications in particular, have the potential to change the scope of healthcare, including orthopaedic surgery.The greatest benefit of ML is in its ability to learn from real-world clinical use and experience, and thereby its capability to improve its own performance.Many successful applications are known in orthopaedics, but have yet to be adopted and evaluated for accuracy and efficacy in patients' care and doctors' workflows.The recent hype around AI triggered hope for development of better risk stratification tools to personalize orthopaedics in all subsequent steps of care, from diagnosis to treatment.Computer vision applications for fracture recognition show promising results to support decision-making, overcome bias, process high-volume workloads without fatigue, and hold the promise of even outperforming doctors in certain tasks.In the near future, AI-derived applications are very likely to assist orthopaedic surgeons rather than replace us. 'If the computer takes over the simple stuff, doctors will have more time again to practice the art of medicine'. Cite this article: 2020;5:593-603. DOI: 10.1302/2058-5241.5.190092.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1302/2058-5241.5.190092DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7608572PMC
October 2020

Recruitment of Women to Anesthesiology: Parallels to Surgery and Interventional Radiology.

J Surg Educ 2021 May-Jun;78(3):753-754. Epub 2020 Sep 15.

Department of Physical Medicine and Rehabilitation, Harvard Medical School; Massachusetts General Hospital, Brigham and Women's Hospital, and Spaulding Rehabilitation Hospital, Boston, Massachusets.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jsurg.2020.08.044DOI Listing
May 2021

Risk factors for musculoskeletal injuries in elite junior tennis players: a systematic review.

J Sports Sci 2019 Jan 18;37(2):131-137. Epub 2018 Jun 18.

h KNLTB , Royal Netherlands Lawn Tennis Association , Amersfoort , the Netherlands.

The objective was to systematically review the literature on risk factors and prevention programs for musculoskeletal injuries among tennis players. PubmedMedline, Embase, CINAHL, Cochrane, SportDiscus were searched up to February 2017. Experts in clinical and epidemiological medicine were contacted to obtain additional studies. For risk factors, prospective cohort studies (n > 20) with a statistical analysis for injured and non-injured players were included and studies with a RCT design for prevention programs. Downs&Black checklist was assessed for risk of bias for risk factors. From a total of 4067 articles, five articles met our inclusion criteria for risk factors. No studies on effectiveness of prevention programs were identified. Quality of studies included varied from fair to excellent. Best evidence synthesis revealed moderate evidence for previous injury regardless of body location in general and fewer years of tennis experience for the occurrence of upper extremity injuries. Moderate evidence was found for lower back injuries, a previous back injury, playing >6hours/week and low lateral flexion of the neck for risk factors. Limited evidence was found for male gender as a risk factor. The risk factors identified can assist clinicians in developing prevention-strategies. Further studies should focus on risk factor evaluation in recreational adult tennis players.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1080/02640414.2018.1485620DOI Listing
January 2019

Do Injured Adolescent Athletes and Their Parents Agree on the Athletes' Level of Psychologic and Physical Functioning?

Clin Orthop Relat Res 2018 04;476(4):767-775

J. H. F. Oosterhoff, R. Bexkens, L. S. Oh, Department of Orthopaedic Surgery, Sports Medicine Service, Massachusetts General Hospital, Boston, MA, USA A. M. Vranceanu, Department of Psychiatry, Integrated Brain Health Clinical and Research Program, Massachusetts General Hospital, Boston, MA, USA.

Background: Although a parent's perception of his or her child's physical and emotional functioning may influence the course of the child's medical care, including access to care and decisions regarding treatment options, no studies have investigated whether the perceptions of a parent are concordant with that of an adolescent diagnosed with a sports-related orthopaedic injury. Identifying and understanding the potential discordance in coping and emotional distress within the athlete adolescent-parent dyads are important, because this discordance may have negative effects on adolescents' well-being.

Questions/purposes: The purposes of this study were (1) to compare adolescent and parent proxy ratings of psychologic symptoms (depression and anxiety), coping skills (catastrophic thinking about pain and pain self-efficacy), and upper extremity physical function and mobility in a population of adolescent-parent dyads in which the adolescent had a sport-related injury; and (2) to compare scores of adolescents and parent proxies with normative scores when such are available.

Methods: We enrolled 54 dyads (eg, pairs) of adolescent patients (mean age 16 years; SD = 1.6) presenting to a sports medicine practice with sports-related injuries as well as their accompanying parent(s). We used Patient-reported Outcomes Measurement Information System questionnaires to measure adolescents' depression, anxiety, upper extremity physical function, and mobility. We used the Pain Catastrophizing Scale short form to assess adolescents' catastrophic thinking about pain and the Pain Self-efficacy Scale short form to measure adolescents' pain self-efficacy. The accompanying parent, 69% mothers (37 of 54) and 31% fathers (17 of 54), completed parent proxy versions of each questionnaire.

Results: Parents reported that their children had worse scores (47 ± 9) on depression than what the children themselves reported (43 ± 9; mean difference 4.0; 95% confidence interval [CI], -7.0 to 0.91; p = 0.011; medium effect size -0.47). Also, parents reported that their children engaged in catastrophic thinking about pain to a lesser degree (8 ± 5) than what the children themselves reported (13 ± 4; mean difference 4.5; 95% CI, 2.7-6.4; p < 0.001; large effect size 1.2). Because scores on depression and catastrophic thinking were comparable to the general population, and minimal clinically important difference scores are not available for these measures, it is unclear whether the relatively small observed differences between parents' and adolescents' ratings are clinically meaningful. Parents and children were concordant on their reports of the child's upper extremity physical function (patient perception 47 ± 10, parent proxy 47 ± 8, mean difference -0.43, p = 0.70), mobility (patient perception 43 ± 9, parent proxy 44 ± 9, mean difference -0.59, p = 0.64), anxiety (patient perception 43 ± 10, parent proxy 46 ± 8, mean difference -2.1, p = 0.21), and pain self-efficacy (patient perception 16 ± 5, parent proxy 15 ± 5, mean difference 0.70, p = 0.35).

Conclusions: Parents rated their children as more depressed and engaging in less catastrophic thinking about pain than the adolescents rated themselves. Although these differences are statistically significant, they are of a small magnitude making it unclear as to how clinically important they are in practice. We recommend that providers keep in mind that parents may overestimate depressive symptoms and underestimate the catastrophic thinking about pain in their children, probe for these potential differences, and consider how they might impact medical care.

Level Of Evidence: Level I, prognostic study.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s11999.0000000000000071DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6260074PMC
April 2018