1
|
Dijkstra H, van de Kuit A, de Groot T, Canta O, Groot OQ, Oosterhoff JH, Doornberg JN. Systematic review of machine-learning models in orthopaedic trauma. Bone Jt Open 2024; 5:9-19. [PMID: 38226447 PMCID: PMC10790183 DOI: 10.1302/2633-1462.51.bjo-2023-0095.r1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/17/2024] Open
Abstract
Aims Machine-learning (ML) prediction models in orthopaedic trauma hold great promise in assisting clinicians in various tasks, such as personalized risk stratification. However, an overview of current applications and critical appraisal to peer-reviewed guidelines is lacking. The objectives of this study are to 1) provide an overview of current ML prediction models in orthopaedic trauma; 2) evaluate the completeness of reporting following the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement; and 3) assess the risk of bias following the Prediction model Risk Of Bias Assessment Tool (PROBAST) tool. Methods A systematic search screening 3,252 studies identified 45 ML-based prediction models in orthopaedic trauma up to January 2023. The TRIPOD statement assessed transparent reporting and the PROBAST tool the risk of bias. Results A total of 40 studies reported on training and internal validation; four studies performed both development and external validation, and one study performed only external validation. The most commonly reported outcomes were mortality (33%, 15/45) and length of hospital stay (9%, 4/45), and the majority of prediction models were developed in the hip fracture population (60%, 27/45). The overall median completeness for the TRIPOD statement was 62% (interquartile range 30 to 81%). The overall risk of bias in the PROBAST tool was low in 24% (11/45), high in 69% (31/45), and unclear in 7% (3/45) of the studies. High risk of bias was mainly due to analysis domain concerns including small datasets with low number of outcomes, complete-case analysis in case of missing data, and no reporting of performance measures. Conclusion The results of this study showed that despite a myriad of potential clinically useful applications, a substantial part of ML studies in orthopaedic trauma lack transparent reporting, and are at high risk of bias. These problems must be resolved by following established guidelines to instil confidence in ML models among patients and clinicians. Otherwise, there will remain a sizeable gap between the development of ML prediction models and their clinical application in our day-to-day orthopaedic trauma practice.
Collapse
Affiliation(s)
- Hidde Dijkstra
- Department of Orthopaedic Surgery, University Medical Centre Groningen, Groningen, Netherlands
- University Center for Geriatric Medicine, University of Groningen, University Medical Center Groningen, Groningen, Netherlands
| | - Anouk van de Kuit
- Department of Orthopaedic Surgery, University Medical Centre Groningen, Groningen, Netherlands
| | - Tom de Groot
- Department of Orthopaedic Surgery, University Medical Centre Groningen, Groningen, Netherlands
- Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Olga Canta
- Department of Orthopaedic Surgery, University Medical Centre Groningen, Groningen, Netherlands
| | - Olivier Q. Groot
- Department of Orthopaedic Surgery, University Medical Centre Utrecht, University of Utrecht, Utrecht, Netherlands
| | - Jacobien H. Oosterhoff
- Department of Engineering Systems & Services, Faculty Technology Policy and Management, Delft University of Technology, Delft, Netherlands
| | - Job N. Doornberg
- Department of Orthopaedic Surgery, University Medical Centre Groningen, Groningen, Netherlands
- Department of Orthopaedic Trauma Surgery, Flinders Medical Center, Flinders University, Adelaide, Australia
| | | |
Collapse
|
2
|
Yao PF, Diao YD, McMullen EP, Manka M, Murphy J, Lin C. Predicting amputation using machine learning: A systematic review. PLoS One 2023; 18:e0293684. [PMID: 37934767 PMCID: PMC10629636 DOI: 10.1371/journal.pone.0293684] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2023] [Accepted: 10/17/2023] [Indexed: 11/09/2023] Open
Abstract
Amputation is an irreversible, last-line treatment indicated for a multitude of medical problems. Delaying amputation in favor of limb-sparing treatment may lead to increased risk of morbidity and mortality. This systematic review aims to synthesize the literature on how ML is being applied to predict amputation as an outcome. OVID Embase, OVID Medline, ACM Digital Library, Scopus, Web of Science, and IEEE Xplore were searched from inception to March 5, 2023. 1376 studies were screened; 15 articles were included. In the diabetic population, models ranged from sub-optimal to excellent performance (AUC: 0.6-0.94). In trauma patients, models had strong to excellent performance (AUC: 0.88-0.95). In patients who received amputation secondary to other etiologies (e.g.: burns and peripheral vascular disease), models had similar performance (AUC: 0.81-1.0). Many studies were found to have a high PROBAST risk of bias, most often due to small sample sizes. In conclusion, multiple machine learning models have been successfully developed that have the potential to be superior to traditional modeling techniques and prospective clinical judgment in predicting amputation. Further research is needed to overcome the limitations of current studies and to bring applicability to a clinical setting.
Collapse
Affiliation(s)
- Patrick Fangping Yao
- Michael G. DeGroote School of Medicine, McMaster University, Hamilton, ON, Canada
| | - Yi David Diao
- Michael G. DeGroote School of Medicine, McMaster University, Hamilton, ON, Canada
| | - Eric P. McMullen
- Michael G. DeGroote School of Medicine, McMaster University, Hamilton, ON, Canada
| | - Marlin Manka
- Department of Computer Science, University of Western Ontario, London, ON, Canada
| | - Jessica Murphy
- Division of Physical Medicine and Rehabilitation, McMaster University, Hamilton, ON, Canada
| | - Celina Lin
- Division of Physical Medicine and Rehabilitation, McMaster University, Hamilton, ON, Canada
- Division of Physical Medicine and Rehabilitation, Hamilton Health Sciences, Hamilton, ON, Canada
| |
Collapse
|
3
|
The Major Extremity Trauma Research Consortium: Development and Impact of an Orthopaedic Trauma Research Program. J Am Acad Orthop Surg 2023; 31:945-956. [PMID: 37671450 DOI: 10.5435/jaaos-d-23-00311] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/07/2023] [Accepted: 06/07/2023] [Indexed: 09/07/2023] Open
Abstract
The Major Extremity Trauma Research Consortium (METRC) is a unique and ongoing military-civilian collaboration that resulted in the largest orthopaedic trauma research enterprise to date. The Consortium was established in September 2009 with funding from the Department of Defense. It employs a centralized data coordinating center and has grown into a network of nearly 400 investigators at 70 clinical centers. METRC conducts large multicenter clinical research studies selected and designed to improve outcomes among severely injured military and civilian patients with extremity trauma. Over the past decade, the consortium has implemented 35 such studies distributed among 19 principal investigators, enrolled more than 23,000 patients, published 61 articles, and received more than $150 million in funding from the Department of Defense, Patient Centered Outcomes Research Institute, and National Institutes of Health. This unique multidisciplinary research platform is a powerful community capable of addressing the challenging issues related to the evaluation, treatment, and recovery after severe extremity trauma. This body of work received the 2023 Elizabeth Winston Lanier Kappa Delta Award. An overview of the METRC development, organization, and research focus areas is presented.
Collapse
|
4
|
Qiu F, Li J, Zhang R, Legerlotz K. Use of artificial neural networks in the prognosis of musculoskeletal diseases-a scoping review. BMC Musculoskelet Disord 2023; 24:86. [PMID: 36726111 PMCID: PMC9890715 DOI: 10.1186/s12891-023-06195-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/15/2022] [Accepted: 01/24/2023] [Indexed: 02/03/2023] Open
Abstract
To determine the current evidence on artificial neural network (ANN) in prognostic studies of musculoskeletal diseases (MSD) and to assess the accuracy of ANN in predicting the prognosis of patients with MSD. The scoping review was reported under the Preferred Items for Systematic Reviews and the Meta-Analyses extension for Scope Reviews (PRISMA-ScR). Cochrane Library, Embase, Pubmed, and Web of science core collection were searched from inception to January 2023. Studies were eligible if they used ANN to make predictions about MSD prognosis. Variables, model prediction accuracy, and disease type used in the ANN model were extracted and charted, then presented as a table along with narrative synthesis. Eighteen Studies were included in this scoping review, with 16 different types of musculoskeletal diseases. The accuracy of the ANN model predictions ranged from 0.542 to 0.947. ANN models were more accurate compared to traditional logistic regression models. This scoping review suggests that ANN can predict the prognosis of musculoskeletal diseases, which has the potential to be applied to different types of MSD.
Collapse
Affiliation(s)
- Fanji Qiu
- grid.7468.d0000 0001 2248 7639Movement Biomechanics, Institute of Sport Sciences, Humboldt‐Universität zu Berlin, Unter Den Linden 6, 10099 Berlin, Germany
| | - Jinfeng Li
- grid.34421.300000 0004 1936 7312Department of Kinesiology, Iowa State University, Ames, 50011 IA USA
| | - Rongrong Zhang
- grid.261049.80000 0004 0645 4572School of Control and Computer Engineering, North China Electric Power University, 102206 Beijing, China
| | - Kirsten Legerlotz
- grid.7468.d0000 0001 2248 7639Movement Biomechanics, Institute of Sport Sciences, Humboldt‐Universität zu Berlin, Unter Den Linden 6, 10099 Berlin, Germany
| |
Collapse
|
5
|
Bloomer AK, McKnight RR, Johnson NR, Macknet DM, Wally MK, Yu Z, Seymour RB, Hsu JR. Screws-Only Primary Subtalar Arthrodesis for Calcaneus Fractures. Foot Ankle Int 2022; 43:509-519. [PMID: 34996306 DOI: 10.1177/10711007211058689] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
BACKGROUND The management of displaced intraarticular calcaneus fractures (DIACFs) is a difficult problem with disappointing results from open reduction internal fixation (ORIF). Alternatively, ORIF with primary subtalar arthrodesis (PSTA) has gained increasing popularity. The purpose of this study is to review patient-centered and radiographic outcomes of ORIF plus PSTA using only screws through a sinus tarsi approach. METHODS A retrospective study of patients who underwent ORIF+PSTA for DIACFs was conducted. The same surgical technique was used in all cases consisting of only screws; no plates were used. Delayed surgeries past 8 weeks were excluded. Demographic and radiographic data were collected including worker's compensation claims. Plain radiographs were used to characterize injuries and review outcomes. RESULTS Seventy-nine DIACFs underwent PSTA with a median follow-up of 200 days (n = 69 patients). Median time to weightbearing was 57.5 days postoperatively. Ten fractures were documented as Sanders II, 36 as Sanders III, and 32 as Sanders IV. Sixty-eight fractures (86.1%) achieved fusion on radiographs at a median of 126.5 (range, 54-518) days. Thirty-nine fractures (57.3%) demonstrated radiographic fusion in all 3 predefined locations. Nine of the 14 worker's compensation patients returned to work within the period of observation. There were 8 complications: 3 requiring a secondary operation. Eleven of 79 fractures treated did not go on to achieve radiographic union. CONCLUSION In this retrospective case series, we found that screws-only primary subtalar arthrodesis for the treatment of DIACFs through a sinus tarsi approach was associated with relatively high rates of return to work and radiographic fusion. LEVEL OF EVIDENCE Level IV, retrospective case series.
Collapse
Affiliation(s)
- Ainsley K Bloomer
- Department of Orthopaedic Surgery, Atrium Health Musculoskeletal Institute, Charlotte, NC, USA
| | - R Randall McKnight
- Department of Orthopaedic Surgery, Atrium Health Musculoskeletal Institute, Charlotte, NC, USA
| | - Nicholas R Johnson
- Department of Orthopaedic Surgery, Atrium Health Musculoskeletal Institute, Charlotte, NC, USA
| | - David M Macknet
- Department of Orthopaedic Surgery, Atrium Health Musculoskeletal Institute, Charlotte, NC, USA
| | - Meghan K Wally
- Department of Orthopaedic Surgery, Atrium Health Musculoskeletal Institute, Charlotte, NC, USA
| | - Ziqing Yu
- Department of Orthopaedic Surgery, Atrium Health Musculoskeletal Institute, Charlotte, NC, USA
| | - Rachel B Seymour
- Department of Orthopaedic Surgery, Atrium Health Musculoskeletal Institute, Charlotte, NC, USA
| | - Joseph R Hsu
- Department of Orthopaedic Surgery, Atrium Health Musculoskeletal Institute, Charlotte, NC, USA
| |
Collapse
|
6
|
Schulte SS, Fares AB, Childs BR, Kenney LE, Orr JD. Factors associated with return to duty and need for subsequent procedures after calcaneus open reduction internal fixation in the military. Injury 2022; 53:771-776. [PMID: 34602241 DOI: 10.1016/j.injury.2021.09.032] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/01/2021] [Revised: 08/07/2021] [Accepted: 09/17/2021] [Indexed: 02/02/2023]
Abstract
INTRODUCTION Calcaneus fractures can be devastating injuries, and operative treatment is fraught with complications. We are unaware of any studies evaluating all calcaneus fractures, both open and closed, treated operatively in the military. The purpose of this study is to evaluate all calcaneus fractures that required open reduction internal fixation to determine soldiers' ability to return to work and the need for additional surgeries. METHODS All active-duty patients undergoing open reduction internal fixation of calcaneus fractures from 2010-2016 were identified utilizing the Military Health System Management Analysis and Reporting Tool (M2). Armed Forces Health Longitudinal Technology Application (AHLTA) was utilized to determine comorbid medical conditions, subsequent procedures, surgical outcomes, and duty status within the military. RESULTS Three hundred seventy-five active-duty service members who met our inclusion/exclusion criteria were identified. One hundred fifty-one patients (55.1%) sustained their calcaneus fracture as a result of a blast injury. One hundred sixty (59.3%) patients required separation from the military as a result of their injury. Among patients who required a subsequent procedure, thirty-four patients (9.1%) required a subtalar arthrodesis, and thirty-two patients (8.5%) eventually required a below knee amputation. Blast as mechanism of injury was the single most predictive variable for patients requiring separation from the military (Odds Ratio 16.2, p< .001), requiring a subsequent procedure (Odds Ratio 8.4, p < .001), and for requiring a below knee amputation (Odds Ratio 47.3, p < .001). CONCLUSION Calcaneus fractures treated operatively in the military are often caused by blast injuries, and have a high rate of requiring subsequent procedures, amputation, and separation from the military.
Collapse
Affiliation(s)
- Spencer S Schulte
- Department of Orthopaedic Surgery and Rehabilitation, Texas Tech University Health Sciences Center, El Paso, Texas; Department of Orthopaedic Surgery and Rehabilitation, William Beaumont Army Medical Center, El Paso, Texas; Department of Orthopedics, Madigan Army Medical Center, Tacoma, WA.
| | - Austin B Fares
- Department of Orthopaedic Surgery and Rehabilitation, Texas Tech University Health Sciences Center, El Paso, Texas; Department of Orthopaedic Surgery and Rehabilitation, William Beaumont Army Medical Center, El Paso, Texas
| | - Benjamin R Childs
- Department of Orthopaedic Surgery and Rehabilitation, Texas Tech University Health Sciences Center, El Paso, Texas; Department of Orthopaedic Surgery and Rehabilitation, William Beaumont Army Medical Center, El Paso, Texas
| | - Lauren E Kenney
- Department of Orthopaedic Surgery and Rehabilitation, Texas Tech University Health Sciences Center, El Paso, Texas; Department of Orthopaedic Surgery and Rehabilitation, William Beaumont Army Medical Center, El Paso, Texas
| | - Justin D Orr
- Department of Orthopaedic Surgery and Rehabilitation, Texas Tech University Health Sciences Center, El Paso, Texas; Department of Orthopaedic Surgery and Rehabilitation, William Beaumont Army Medical Center, El Paso, Texas
| |
Collapse
|
7
|
Lalehzarian SP, Gowd AK, Liu JN. Machine learning in orthopaedic surgery. World J Orthop 2021; 12:685-699. [PMID: 34631452 PMCID: PMC8472446 DOI: 10.5312/wjo.v12.i9.685] [Citation(s) in RCA: 28] [Impact Index Per Article: 9.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/17/2021] [Revised: 05/12/2021] [Accepted: 08/05/2021] [Indexed: 02/06/2023] Open
Abstract
Artificial intelligence and machine learning in orthopaedic surgery has gained mass interest over the last decade or so. In prior studies, researchers have demonstrated that machine learning in orthopaedics can be used for different applications such as fracture detection, bone tumor diagnosis, detecting hip implant mechanical loosening, and grading osteoarthritis. As time goes on, the utility of artificial intelligence and machine learning algorithms, such as deep learning, continues to grow and expand in orthopaedic surgery. The purpose of this review is to provide an understanding of the concepts of machine learning and a background of current and future orthopaedic applications of machine learning in risk assessment, outcomes assessment, imaging, and basic science fields. In most cases, machine learning has proven to be just as effective, if not more effective, than prior methods such as logistic regression in assessment and prediction. With the help of deep learning algorithms, such as artificial neural networks and convolutional neural networks, artificial intelligence in orthopaedics has been able to improve diagnostic accuracy and speed, flag the most critical and urgent patients for immediate attention, reduce the amount of human error, reduce the strain on medical professionals, and improve care. Because machine learning has shown diagnostic and prognostic uses in orthopaedic surgery, physicians should continue to research these techniques and be trained to use these methods effectively in order to improve orthopaedic treatment.
Collapse
Affiliation(s)
- Simon P Lalehzarian
- The Chicago Medical School, Rosalind Franklin University of Medicine and Science, North Chicago, IL 60064, United States
| | - Anirudh K Gowd
- Department of Orthopaedic Surgery, Wake Forest Baptist Medical Center, Winston-Salem, NC 27157, United States
| | - Joseph N Liu
- USC Epstein Family Center for Sports Medicine, Keck Medicine of USC, Los Angeles, CA 90033, United States
| |
Collapse
|
8
|
Outcomes Following Severe Distal Tibial, Ankle, and/or Mid/Hindfoot Trauma: Comparison of Limb Salvage and Transtibial Amputation (OUTLET). J Bone Joint Surg Am 2021; 103:1588-1597. [PMID: 33979309 DOI: 10.2106/jbjs.20.01320] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
BACKGROUND Selecting the best treatment for patients with severe terminal lower-limb injury remains a challenge. For some injuries, amputation may result in better outcomes than limb salvage. This study compared the outcomes of patients who underwent limb salvage with those that would have been achieved had they undergone amputation. METHODS This multicenter prospective observational study included patients 18 to 60 years of age in whom a Type-III pilon or IIIB or C ankle fracture, a Type-III talar or calcaneal fracture, or an open or closed blast/crush foot injury had been treated with limb salvage (n = 488) or amputation (n = 151) and followed for 18 months. The primary outcome was the Short Musculoskeletal Function Assessment (SMFA). Causal effect estimates of the improvement that amputation would have provided if it had been performed instead of limb salvage were calculated for the SMFA score, physical performance, pain, participation in vigorous activities, and return to work. RESULTS The patients who underwent limb salvage would have had small differences in most outcomes had they undergone amputation. The most notable difference was an improvement in the SMFA mobility score of 7 points (95% confidence interval [CI] = 2.0 to 10.7). Improvements were largest for pilon/ankle fractures and complex injury patterns. CONCLUSIONS Amputation should be considered a treatment option rather than a last resort for the most complex terminal lower-limb injuries. LEVEL OF EVIDENCE Therapeutic Level II. See Instructions for Authors for a complete description of levels of evidence.
Collapse
|
9
|
Effect of Severe Distal Tibia, Ankle, and Mid- to Hindfoot Trauma on Meeting Physical Activity Guidelines 18 Months After Injury. Arch Phys Med Rehabil 2021; 103:409-417.e2. [PMID: 34425087 DOI: 10.1016/j.apmr.2021.07.805] [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: 01/14/2021] [Revised: 07/09/2021] [Accepted: 07/15/2021] [Indexed: 11/02/2022]
Abstract
OBJECTIVE To examine the effect of severe lower extremity trauma on meeting Physical Activity Guidelines for Americans (PAGA) 18 months after injury and perform an exploratory analysis to identify demographic, clinical, and psychosocial factors associated with meeting PAGA. DESIGN Secondary analysis of observational cohort study. SETTING A total of 34 United States trauma centers PARTICIPANTS: A total of 328 adults with severe distal tibia, ankle and mid- to hindfoot injuries treated with limb reconstruction (N=328). INTERVENTIONS None. MAIN OUTCOME MEASURES The Paffenbarger Physical Activity Questionnaire was used to assess physical activity levels 18 months after injury. Meeting PAGA was defined as combined moderate- and vigorous-intensity activity ≥150 minutes per week or vigorous-intensity activity ≥75 minutes per week. RESULTS Fewer patients engaged in moderate- or vigorous-intensity activity after injury compared with before injury (moderate: 44% vs 66%, P<.001; vigorous: 18% vs 29%; P<.001). Patients spent 404±565 minutes per week in combined moderate- to vigorous-intensity activity before injury compared with 224±453 minutes postinjury (difference: 180min per week; 95% confidence interval [CI], 103-256). The adjusted odds of meeting PAGA were lower for patients with depression (adjusted odds ratio [AOR], 0.45; 95% CI, 0.28-0.73), women (AOR, 0.59; 95% CI, 0.35-1.00), and Black or Hispanic patients (AOR, 0.49; 95% CI, 0.28-0.85). Patients meeting PAGA prior to injury were more likely to meet PAGA after injury (odds ratio, 2.0; 95% CI, 1.20-3.31). CONCLUSIONS Patients spend significantly less time in moderate- to vigorous-intensity physical activity after injury. Patients with depression are less likely to meet PAGA. Although the causal relationship is unclear, results highlight the importance of screening for depression.
Collapse
|
10
|
American Academy of Orthopaedic Surgeons Clinical Practice Guideline Summary for Limb Salvage or Early Amputation. J Am Acad Orthop Surg 2021; 29:e628-e634. [PMID: 33878076 DOI: 10.5435/jaaos-d-20-00188] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/03/2020] [Accepted: 02/21/2021] [Indexed: 02/01/2023] Open
Abstract
Clinical Practice Guideline for Limb Salvage or Early Amputation is based on a systematic review of current scientific and clinical research. The purpose of this clinical practice guideline is to address treatment for severe lower limb trauma below the distal femur by either amputation or limb salvage by providing evidence-based recommendations for key decisions that affect the management of patients with lower extremity trauma. This guideline contains 11 recommendations to evaluate the decision factors important for limb salvage versus early amputation. In addition, the work group highlighted the need for better research in the treatment and the shared decision making process of high-energy lower extremity trauma.
Collapse
|
11
|
Hindfoot blast injuries caused by improvised explosive devices: long-term functional assessment in French military personnel. INTERNATIONAL ORTHOPAEDICS 2020; 45:751-757. [PMID: 32770349 DOI: 10.1007/s00264-020-04766-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/09/2020] [Accepted: 07/28/2020] [Indexed: 10/23/2022]
Abstract
PURPOSE The chosen treatment and long-term evaluation of hindfoot blast injuries are not well-represented in the literature. The first objective of this retrospective study was to evaluate functional outcomes in French service personnel who had sustained such injuries caused by improvised explosive devices. The second objective was to compare the results for patients who had amputations with those who did not. The hypothesis was that amputee recovered better function. METHODS Long-term functional evaluations were carried out using the American Orthopaedic Foot and Ankle Society scale (AOFAS), the Foot and Ankle Ability Measure (FAAM), and the Short Form 12 health survey (SF-12). RESULTS Eight servicemen with ten hindfoot blast injuries were reviewed at a mean follow-up time of seven years. Primary management was always conservative although half of the patients required late amputation for chronic pain. The patients who underwent amputation reported significantly lower levels of pain than those who did not have an amputation, with higher FAAM and SF-12 scores. CONCLUSION In this series, long-term functional results appear better in the amputated group.
Collapse
|
12
|
Poduval M, Ghose A, Manchanda S, Bagaria V, Sinha A. Artificial Intelligence and Machine Learning: A New Disruptive Force in Orthopaedics. Indian J Orthop 2020; 54:109-122. [PMID: 32257027 PMCID: PMC7096590 DOI: 10.1007/s43465-019-00023-3] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/10/2019] [Accepted: 09/18/2019] [Indexed: 02/04/2023]
Abstract
Orthopaedics as a surgical discipline requires a combination of good clinical acumen, good surgical skill, a reasonable physical strength and most of all, good understanding of technology. The last few decades have seen rapid adoption of new technologies into orthopaedic practice, power tools, new implants, CAD-CAM design, 3-D printing, additive manufacturing just to name a few. The new disruption in orthopaedics in the current time and era is undoubtedly the advent of artificial intelligence and robotics. As these technologies take root and innovative applications continue to be incorporated into the main-stream orthopedics, as we know it today, it is imperative to look at and understand the basics of artificial intelligence and what work is being done in the field today. This article takes the form of a loosely structured narrative review and will introduce the reader to key concepts in the field of artificial intelligence as well as some of the directions in application of the same in orthopaedics. Some of the recent work has been summarised and we present our viewpoint at the conclusion as to why we must consider artificial intelligence as a disrupting positive influence on orthopaedic surgery.
Collapse
Affiliation(s)
- Murali Poduval
- Tata Consultancy Services, Unit 129/130, SDF V, SEEPZ, Andheri East, Mumbai, 400093 India
| | - Avik Ghose
- TCS Research and Innovation, Tata Consultancy Services, Kolkata, 700160 India
| | - Sanjeev Manchanda
- TCS Research and Innovation, Tata Consultancy Services, Unit 129/130, SEEPZ, Andheri East, Mumbai, 400096 India
| | | | - Aniruddha Sinha
- TCS Research and Innovation, Tata Consultancy Services, Kolkata, 700160 India
| |
Collapse
|
13
|
Gabrielli AS, Gale T, Hogan M, Anderst W. Bilateral Symmetry, Sex Differences, and Primary Shape Factors in Ankle and Hindfoot Bone Morphology. FOOT & ANKLE ORTHOPAEDICS 2020; 5:2473011420908796. [PMID: 35097367 PMCID: PMC8697112 DOI: 10.1177/2473011420908796] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022] Open
Abstract
Background: Ankle injuries and joint degeneration may be related to ankle bone morphology. Little data exist to characterize healthy hindfoot bone morphology. The purpose of this study was to characterize side-to-side symmetry and sex differences in ankle and hindfoot bone morphology, and to identify the primary shape factors that differentiate ankle and hindfoot bone morphology among individuals. Methods: Computed tomography was used to create 3D surface models of the distal tibia, talus, and calcaneus for 40 ankle and hindfoot bones from 20 healthy individuals. Morphologic differences between left and right bones of the same individual and between males and females were determined. Statistical shape modeling was performed to identify primary shape variations among individuals. Results: Side-to-side differences in bone morphology averaged 0.79 mm or less. The average distal tibia in males was larger overall than in females. No significant sex difference was noted in the tali. The average female calcaneus was longer and thinner than the average male calcaneus. Variability in ankle and hindfoot bone morphology is primarily associated with articulating surface shape, overall length and width, and tendon/ligament attachment points. Conclusion: In general, the contralateral ankle can serve as an accurate guide for operative restoration of native ankle morphology; however, specific regions demonstrate higher asymmetry. Clinical Relevance: Knowledge of regions of high and low bilateral symmetry can improve hindfoot and ankle reconstruction. Design of ankle prostheses can be improved by accounting for differences in bone morphology associated with sex and shape differences among individuals.
Collapse
Affiliation(s)
- Alexandra S. Gabrielli
- Department of Orthopaedic Surgery, University of Pittsburgh Medical Center, Pittsburgh, PA, USA
| | - Tom Gale
- Biodynamics Lab, University of Pittsburgh, Pittsburgh, PA, USA
| | - MaCalus Hogan
- Department of Orthopaedic Surgery, University of Pittsburgh Medical Center, Pittsburgh, PA, USA
- The Foot and Ankle Injury Group, University of Pittsburgh Medical Center, Pittsburgh, PA, USA
| | - William Anderst
- Biodynamics Lab, University of Pittsburgh, Pittsburgh, PA, USA
| |
Collapse
|
14
|
Dworak TC, Wagner SC, Nappo KE, Balazs GC, Grimm PD, Colantonio DF, Tintle SM. The Use of Distal Ulnar Hounsfield Units to Predict Future Fragility Fracture Risk. J Hand Surg Am 2018; 43:1010-1015. [PMID: 29891269 DOI: 10.1016/j.jhsa.2018.04.017] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/14/2017] [Revised: 02/28/2018] [Accepted: 04/11/2018] [Indexed: 02/02/2023]
Abstract
PURPOSE Distal ulnar Hounsfield unit (HU) measurements obtained from computed tomography (CT) scans of the wrist can be used to accurately screen for low bone mineral density. It is unknown whether HU measurements can also predict the risk of future fragility fractures. Therefore, the purpose of this study was to determine if the HU values of the distal ulna correlate to fragility fracture risk. METHODS An electronic database of radiographs at a single institution was searched for all wrist CT scans, obtained for any reason, between January 1, 2002, and December 31, 2008, to allow a minimum of 5-year follow-up. Manual measurement of HU on sequential coronal CT slices of the distal ulnar head was taken, and mean values were recorded. Previously determined cutoff values for the diagnosis of low bone mineral density were implemented to stratify patients as at risk or not at risk for future fragility fracture. Medical records were then manually reviewed for the occurrence of any future fragility fracture (hip, spine, proximal humerus, or rib). RESULTS There were 161 CTs in 157 patients and 34 fragility fractures in 21 patients, with a prevalence of 13.4%. The mean HU in the fragility fracture group was significantly lower (134.2 vs 197.1 HU). The percentage of low HU patients with fragility fractures was significantly higher (22.7% vs 3.8%). The odds ratio for fragility fracture in the low HU group was 7.4 (95% confidence interval, 2.1-26.2). Using previously determined cutoff values, the sensitivity and specificity of distal ulna HU values for identifying patients who would sustain at least 1 future fragility fracture were 85.7% and 55.2%, respectively. CONCLUSIONS Patients with low distal ulnar HU were significantly more likely to sustain a subsequent fragility fracture. A determination of distal ulnar HUs represents a quick, simple tool to identify patients potentially at risk for fragility fractures. TYPE OF STUDY/LEVEL OF EVIDENCE Prognostic IV.
Collapse
Affiliation(s)
- Theodora C Dworak
- Department of Orthopaedics, Walter Reed National Military Medical Center, Bethesda, MD; Department of Surgery, Uniformed Services University of the Health Sciences, Bethesda, MD
| | - Scott C Wagner
- Department of Orthopaedics, Walter Reed National Military Medical Center, Bethesda, MD; Department of Surgery, Uniformed Services University of the Health Sciences, Bethesda, MD; Department of Orthopaedics, Rothman Institute at Thomas Jefferson University, Philadelphia, PA.
| | - Kyle E Nappo
- Department of Orthopaedics, Walter Reed National Military Medical Center, Bethesda, MD; Department of Surgery, Uniformed Services University of the Health Sciences, Bethesda, MD
| | - George C Balazs
- Department of Orthopaedics, Walter Reed National Military Medical Center, Bethesda, MD; Department of Surgery, Uniformed Services University of the Health Sciences, Bethesda, MD
| | - Patrick D Grimm
- Department of Orthopaedics, Walter Reed National Military Medical Center, Bethesda, MD; Department of Surgery, Uniformed Services University of the Health Sciences, Bethesda, MD
| | - Donald F Colantonio
- Department of Surgery, Uniformed Services University of the Health Sciences, Bethesda, MD
| | - Scott M Tintle
- Department of Orthopaedics, Walter Reed National Military Medical Center, Bethesda, MD; Department of Surgery, Uniformed Services University of the Health Sciences, Bethesda, MD; Department of Orthopaedic Surgery, University of Pennsylvania Health System, Philadelphia, PA
| |
Collapse
|
15
|
Rejali M, Mansourian M, Babaei Z, Eshrati B. Prediction of Low Birth Weight Delivery by Maternal Status and Its Validation: Decision Curve Analysis. Int J Prev Med 2017; 8:53. [PMID: 28928911 PMCID: PMC5553248 DOI: 10.4103/ijpvm.ijpvm_146_16] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2016] [Accepted: 01/07/2017] [Indexed: 11/30/2022] Open
Abstract
Background: In this study, we evaluated assessed elements connected with low birth weight (LBW) and used decision curve analysis (DCA) to define a scale to anticipate the probability of having a LBW newborn child. Methods: This hospital-based case–control study was led in Arak Hospital in Iran. The study included 470 mothers with LBW neonate and 470 mothers with natural neonates. Information were gathered by meeting moms utilizing preplanned organized questionnaire and from hospital records. The estimated probabilities of detecting LBW were calculated using the logistic regression and DCA to quantify the clinical consequences and its validation. Results: Factors significantly associated with LBW were premature membrane rupture (odds ratio [OR] = 3.18 [1.882–5.384]), former LBW infants (OR = 2.99 [1.510–5.932]), premature pain (OR = 2.70 [1.659–4.415]), hypertension in pregnancy (OR = 2.39 [1.429–4.019]), last trimester of pregnancy bleeding (OR = 2.58 [1.018–6.583]), mother age >30 (OR = 2.17 [1.350–3.498]). However, with DCA, the prediction model made on these 15 variables has a net benefit (NB) of 0.3110 is best predictive with the highest NB. NB has simple clinical interpretation and utilizing the model is what might as well be called a procedure that distinguished what might as well be called 31.1 LBW per 100 cases with no superfluous recognize. Conclusions: It is conceivable to foresee LBW utilizing a prediction model show in light of noteworthy hazard components connected with LBW. The majority of the hazard elements for LBW are preventable, and moms can be alluded amid early pregnancy to a middle which is furnished with facilities for administration of high hazard pregnancy and LBW infant.
Collapse
Affiliation(s)
- Mehri Rejali
- Department of Epidemiology and Biostatistics, School of Health, Isfahan University of Medical Sciences, Isfahan, Iran
| | - Marjan Mansourian
- Department of Epidemiology and Biostatistics, School of Health, Isfahan University of Medical Sciences, Isfahan, Iran
| | - Zohre Babaei
- Student Research Center, School of Health, Isfahan University of Medical Sciences, Isfahan, Iran
| | - Babak Eshrati
- Department of Public Health, School of Health, Arak University of Medical Sciences, Arak, Iran
| |
Collapse
|
16
|
Abstract
Complex foot injuries occur infrequently, but are life-changing events. They often present with other injuries as the result of a high-energy trauma. After initial stabilization, early assessment should be regarding salvagability. All treatment strategies are intensive. The initial treatment includes prevention of progression ischemia/necrosis, prevention of infection, and considering salvage or amputation. Definitive treatment for salvage includes anatomic reconstruction with stable internal fixation and early soft tissue coverage followed by aggressive rehabilitation. Prognosis after complex injuries is hard to predict. The various stages of the treatment are reviewed and recommendations are made.
Collapse
Affiliation(s)
- Tim Schepers
- Trauma Unit, Academic Medical Center, University of Amsterdam, Meibergdreef 9, PO Box 22660, Amsterdam 1100 DD, The Netherlands.
| | - Stefan Rammelt
- University Center for Orthopaedics and Traumatology, University Hospital Carl-Gustav Carus, Fetscherstrasse 74, Dresden 01307, Germany
| |
Collapse
|
17
|
Abstract
INTRODUCTION The use of improvised explosive devices is a frequent method of insurgents to inflict harm on deployed military personnel. Consequently, lower extremity injuries make up the majority of combat related trauma. The wounding pattern of an explosion is not often encountered in a civilian population and can lead to substantial disability. It is therefore important to study the impact of these lower extremity injuries and their treatment (limb salvage versus amputation) on functional outcome and quality of life. PATIENTS AND METHODS All Dutch repatriated service members receiving treatment for wounds on the lower extremity sustained in the Afghan theater between august 2005 and August 2014, were invited to participate in this observational cohort study. We conducted a survey regarding their physical and mental health using the Short Form health survey 36, EuroQoL 6 dimensions and Lower Extremity Functional Scale questionnaires. Results were collated in a specifically designed electronic database combined with epidemiology and hospital statistics gathered from the archive of the Central Military Hospital. Statistical analyses were performed to identify differences between combat and non-combat related injuries and between limb salvage treatment and amputation. RESULTS In comparison with non-battle injury patients, battle casualties were significantly younger of age, sustained more severe injuries, needed more frequent operations and clinical rehabilitation. Their long-term outcome scores in areas concerning well-being, social and cognitive functioning, were significantly lower. Regarding treatment, amputees experienced higher physical well-being and less pain compared to those treated with limb salvage surgery. CONCLUSION Sustaining a combat injury to the lower extremity can lead to partial or permanent dysfunction. However, wounded service members, amputees included, are able to achieve high levels of activity and participation in society, proving a remarkable resilience. These long-term results demonstrate that amputation is not a failure for casualty and surgeon, and strengthen a life before limb (damage control surgery) mindset in the initial phase. For future research, we recommend the use of adequate coding and injury scoring systems to predict outcome and give insight in the attributes that are supportive for the resilience that is needed to cope with a serious battle injury.
Collapse
|
18
|
Melcer T, Walker J, Bhatnagar V, Richard E, Sechriest VF, Galarneau M. A Comparison of Four-Year Health Outcomes following Combat Amputation and Limb Salvage. PLoS One 2017; 12:e0170569. [PMID: 28122002 PMCID: PMC5266314 DOI: 10.1371/journal.pone.0170569] [Citation(s) in RCA: 22] [Impact Index Per Article: 3.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2016] [Accepted: 01/06/2017] [Indexed: 01/08/2023] Open
Abstract
Little research has described the long-term health outcomes of patients who had combat-related amputations or leg-threatening injuries. We conducted retrospective analysis of Department of Defense and Department of Veterans Affairs health data for lower extremity combat-injured patients with (1) unilateral amputation within 90 days postinjury (early amputation, n = 440), (2) unilateral amputation more than 90 days postinjury (late amputation, n = 78), or (3) leg-threatening injuries without amputation (limb salvage, n = 107). Patient medical records were analyzed for four years postinjury. After adjusting for group differences, early amputation was generally associated with a lower or similar prevalence for adverse physical and psychological diagnoses (e.g., pain, osteoarthritis, posttraumatic stress disorder) versus late amputation and/or limb salvage. By contrast, early amputation was associated with an increased likelihood of osteoporosis during the first year postinjury. The prevalence of posttraumatic stress disorder increased for all patient groups over four years postinjury, particularly in the second year. The different clinical outcomes among combat extremity injured patients treated with early amputation, late amputation, or limb salvage highlight their different healthcare requirements. These findings can inform and optimize the specific treatment pathways that address the physical and psychological healthcare needs of such patients over time.
Collapse
Affiliation(s)
- Ted Melcer
- Department of Medical Modeling, Simulation, and Mission Support, Naval Health Research Center, San Diego, California, United States of America
| | - Jay Walker
- Department of Medical Modeling, Simulation, and Mission Support, Naval Health Research Center, San Diego, California, United States of America
| | - Vibha Bhatnagar
- Department of Medical Modeling, Simulation, and Mission Support, Naval Health Research Center, San Diego, California, United States of America
- VA San Diego Healthcare System, San Diego, California, United States of America
- Department for Family Medicine and Public Health, University of California San Diego, San Diego, California, United States of America
| | - Erin Richard
- Department of Medical Modeling, Simulation, and Mission Support, Naval Health Research Center, San Diego, California, United States of America
- VA San Diego Healthcare System, San Diego, California, United States of America
- Department for Family Medicine and Public Health, University of California San Diego, San Diego, California, United States of America
| | | | - Michael Galarneau
- Department of Medical Modeling, Simulation, and Mission Support, Naval Health Research Center, San Diego, California, United States of America
| |
Collapse
|
19
|
Zhang X, Liu Y, Peng A, Wang H, Zhang Y. Clinical efficacy and prognosis factors of open calcaneal fracture: a retrospective study. Int J Clin Exp Med 2015; 8:3841-3847. [PMID: 26064282 PMCID: PMC4443116] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2014] [Accepted: 12/01/2014] [Indexed: 06/04/2023]
Abstract
BACKGROUND Treatment of open calcaneal fractures remains to be a challenge for orthopaedic surgeons. The aim of this study is to assess factors affecting the treatment results of open calcaneal fractures. METHODS A total of 98 patients who have 101 open calcaneal fractures were recruited in our hospital, they were all treated with a standard protocol based on the appearance of the traumatic wound. Data on mechanism of injury, location and size of wound, classification, fixation methods and subsequent soft-tissue complications were collected and evaluated. AOFAS Ankle-Hindfoot Survey and physical examinations were performed to access outcomes. RESULTS No statistical difference was found in complication and AOFAS score in open calcaneal fractures treated with different fixation, and no statistical difference was found in AOFAS between gustilo I and II type open calcaneal fractures (P > 0.05). There was significant difference between gustilo I and III type or gustilo II and III type fractures (P < 0.05). The more serious soft tissue injury of open calcaneal fracture lead to the worse outcome and higher incidence of complications obtained. CONCLUSION Open calcaneal fractures have a high propensity for soft-tissue complications no matter which fixation method was chose. There was no significant difference between patients who had been treated with different fixations in complication rates. Soft-tissue injury played an important role in outcomes of open calcaneal fractures. Deep infections and osteomyelitis were rare by means of emergency debridement and following repeated debridement.
Collapse
Affiliation(s)
- Xuebin Zhang
- Trauma & Emergency Center, The Third Hospital Hebei Medical University Shijiazhuang, China
| | - Yueju Liu
- Trauma & Emergency Center, The Third Hospital Hebei Medical University Shijiazhuang, China
| | - Aqin Peng
- Trauma & Emergency Center, The Third Hospital Hebei Medical University Shijiazhuang, China
| | - Haili Wang
- Trauma & Emergency Center, The Third Hospital Hebei Medical University Shijiazhuang, China
| | - Yingze Zhang
- Trauma & Emergency Center, The Third Hospital Hebei Medical University Shijiazhuang, China
| |
Collapse
|