Publications by authors named "Bas J J Bindels"

5 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

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

Flow cytometric evaluation of the neutrophil compartment in COVID-19 at hospital presentation: A normal response to an abnormal situation.

J Leukoc Biol 2021 01;109(1):99-114

Department of Respiratory Medicine, University Medical Center Utrecht, Heidelberglaan, Utrecht, The Netherlands.

Coronavirus disease 2019 (COVID-19) is a rapidly emerging pandemic disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Critical COVID-19 is thought to be associated with a hyper-inflammatory process that can develop into acute respiratory distress syndrome, a critical disease normally mediated by dysfunctional neutrophils. This study tested the hypothesis whether the neutrophil compartment displays characteristics of hyperinflammation in COVID-19 patients. Therefore, a prospective study was performed on all patients with suspected COVID-19 presenting at the emergency room of a large academic hospital. Blood drawn within 2 d after hospital presentation was analyzed by point-of-care automated flow cytometry and compared with blood samples collected at later time points. COVID-19 patients did not exhibit neutrophilia or eosinopenia. Unexpectedly neutrophil activation markers (CD11b, CD16, CD10, and CD62L) did not differ between COVID-19-positive patients and COVID-19-negative patients diagnosed with other bacterial/viral infections, or between COVID-19 severity groups. In all patients, a decrease was found in the neutrophil maturation markers indicating an inflammation-induced left shift of the neutrophil compartment. In COVID-19 this was associated with disease severity.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/JLB.5COVA0820-520RRRDOI Listing
January 2021

An increase in CD62L neutrophils precedes the development of pulmonary embolisms in COVID-19 patients.

Scand J Immunol 2021 Jan 22:e13023. Epub 2021 Jan 22.

Department of Respiratory Medicine, University Medical Center Utrecht, Utrecht, The Netherlands.

Objectives: A high incidence of pulmonary embolism (PE) is reported in patients with critical coronavirus disease 2019 (COVID-19). Neutrophils may contribute to this through a process referred to as immunothrombosis. The aim of this study was to investigate the occurrence of neutrophil subpopulations in blood preceding the development of COVID-19 associated PE.

Methods: We studied COVID-19 patients admitted to the ICU of our tertiary hospital between 19-03-2020 and 17-05-2020. Point-of-care fully automated flow cytometry was performed prior to ICU admission, measuring the neutrophil activation/maturation markers CD10, CD11b, CD16 and CD62L. Neutrophil receptor expression was compared between patients who did or did not develop PE (as diagnosed on CT angiography) during or after their ICU stay.

Results: Among 25 eligible ICU patients, 22 subjects were included for analysis, of whom nine developed PE. The median (IQR) time between neutrophil phenotyping and PE occurrence was 9 (7-12) days. A significant increase in the immune-suppressive neutrophil phenotype CD16 /CD62L was observed on the day of ICU admission (P = 0.014) in patients developing PE compared to patients who did not.

Conclusion: The increase in this neutrophil phenotype indicates that the increased number of CD16 /CD62L neutrophils might be used as prognostic marker to predict those patients that will develop PE in critical COVID-19 patients.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1111/sji.13023DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7995011PMC
January 2021

Thirty-day Postoperative Complications After Surgery For Metastatic Long Bone Disease Are Associated With Higher Mortality at 1 Year.

Clin Orthop Relat Res 2020 02;478(2):306-318

B. J. J. Bindels, Q. C. B. S. Thio, K. A. Raskin, S. A. Lozano Calderón, J. H. Schwab, Department of Orthopedic Surgery, Massachusetts General Hospital, Boston, MA, USA.

Background: The benefits of surgical treatment of a metastasis of the extremities may be offset by drawbacks such as potential postoperative complications. For this group of patients, the primary goal of surgery is to improve quality of life in a palliative setting. A better comprehension of factors associated with complications and the impact of postoperative complications on mortality may prevent negative outcomes and help surgeons in surgical decision-making.

Questions/purposes: (1) What is the risk of 30-day postoperative complications after surgical treatment of osseous metastatic disease of the extremities? (2) What predisposing factors are associated with a higher risk of 30-day complications? (3) Are minor and major 30-day complications associated with higher mortality at 1 year?

Methods: Between 1999 and 2016, 1090 patients with osseous metastatic disease of the long bones treated surgically at our institution were retrospectively included in the study. Surgery included intramedullary nailing (58%), endoprosthetic reconstruction (22%), plate-screw fixation (14%), dynamic hip screw fixation (2%), and combined approaches (4%). Surgery was performed if patients were deemed healthy enough to proceed to surgery and wished to undergo surgery. All data were retrieved by manually reviewing patients' records. The overall frequency of complications, which were defined using the Clavien-Dindo classification system, was calculated. We did not include Grade I complications as postoperative complications and complications were divided into minor (Grade II) and major (Grades III-V) complications. A multivariate logistic regression analysis was used to identify factors associated with 30-day postoperative complications. A Cox regression analysis was used to assess the association between postoperative complications and overall survival.

Results: Overall, 31% of the patients (333 of 1090) had a postoperative complication within 30 days. The following factors were independently associated with 30-day postoperative complications: rapidly growing primary tumors classified according to the modified Katagiri classification (odds ratio 1.6; 95% confidence interval, 1.1-2.2; p = 0.011), multiple bone metastases (OR 1.6; 95% CI, 1.1-2.3; p = 0.008), pathologic fracture (OR 1.5; 95% CI, 1.1-2.0; p = 0.010), lower-extremity location (OR 2.2; 95% CI, 1.6-3.2; p < 0.001), hypoalbuminemia (OR 1.7; 95% CI, 1.2-2.4; p = 0.002), hyponatremia (OR 1.5; 95% CI, 1.0-2.2; p = 0.044), and elevated white blood cell count (OR 1.6; 95% CI, 1.1-2.4; p = 0.007). Minor and major postoperative complications within 30 days after surgery were both associated with greater 1-year mortality (hazard ratio 1.6; 95% CI, 1.3-1.8; p < 0.001 and HR 3.4; 95% CI, 2.8-4.2, respectively; p < 0.001).

Conclusion: Patients with metastatic disease in the long bones are vulnerable to postoperative adverse events. When selecting patients for surgery, surgeons should carefully assess a patient's cancer status, and several preoperative laboratory values should be part of the standard work-up before surgery. Furthermore, 30-day postoperative complications decrease survival within 1 year after surgery. Therefore, patients at a high risk of having postoperative complications are less likely to profit from surgery and should be considered for nonoperative treatment or be monitored closely after surgery.

Level Of Evidence: Level III, therapeutic study.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1097/CORR.0000000000001036DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7438145PMC
February 2020