1
|
Yang X, Yang S, Bao Y, Wang Q, Peng Z, Lu S. Novel machine-learning prediction tools for overall survival of patients with chondrosarcoma: Based on recursive partitioning analysis. Cancer Med 2024; 13:e70058. [PMID: 39123313 PMCID: PMC11315679 DOI: 10.1002/cam4.70058] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2024] [Revised: 07/04/2024] [Accepted: 07/20/2024] [Indexed: 08/12/2024] Open
Abstract
BACKGROUND Chondrosarcoma (CHS), a bone malignancy, poses a significant challenge due to its heterogeneous nature and resistance to conventional treatments. There is a clear need for advanced prognostic instruments that can integrate multiple prognostic factors to deliver personalized survival predictions for individual patients. This study aimed to develop a novel prediction tool based on recursive partitioning analysis (RPA) to improve the estimation of overall survival for patients with CHS. METHODS Data from the Surveillance, Epidemiology, and End Results (SEER) database were analyzed, including demographic, clinical, and treatment details of patients diagnosed between 2000 and 2018. Using C5.0 algorithm, decision trees were created to predict survival probabilities at 12, 24, 60, and 120 months. The performance of the models was assessed through confusion scatter plot, accuracy rate, receiver operator characteristic (ROC) curve, and area under ROC curve (AUC). RESULTS The study identified tumor histology, surgery, age, visceral (brain/liver/lung) metastasis, chemotherapy, tumor grade, and sex as critical predictors. Decision trees revealed distinct patterns for survival prediction at each time point. The models showed high accuracy (82.40%-89.09% in training group, and 82.16%-88.74% in test group) and discriminatory power (AUC: 0.806-0.894 in training group, and 0.808-0.882 in test group) in both training and testing datasets. An interactive web-based shiny APP (URL: https://yangxg1209.shinyapps.io/chondrosarcoma_survival_prediction/) was developed, simplifying the survival prediction process for clinicians. CONCLUSIONS This study successfully employed RPA to develop a user-friendly tool for personalized survival predictions in CHS. The decision tree models demonstrated robust predictive capabilities, with the interactive application facilitating clinical decision-making. Future prospective studies are recommended to validate these findings and further refine the predictive model.
Collapse
Affiliation(s)
- Xiong‐Gang Yang
- Department of Orthopedics, The First People's Hospital of Yunnan ProvinceThe Affiliated Hospital of Kunming University of Science and TechnologyKunmingYunnanChina
- The Key Laboratory of Digital Orthopedics of Yunnan ProvinceKunmingYunnanChina
| | - Shan‐Shan Yang
- Department of ProsthodonticsAffiliated Stomatological Hospital of Zunyi Medical University, Zunyi Medical UniversityZunyiChina
| | - Yi Bao
- Department of Orthopedics, The First People's Hospital of Yunnan ProvinceThe Affiliated Hospital of Kunming University of Science and TechnologyKunmingYunnanChina
- The Key Laboratory of Digital Orthopedics of Yunnan ProvinceKunmingYunnanChina
| | - Qi‐Yang Wang
- Department of Orthopedics, The First People's Hospital of Yunnan ProvinceThe Affiliated Hospital of Kunming University of Science and TechnologyKunmingYunnanChina
- The Key Laboratory of Digital Orthopedics of Yunnan ProvinceKunmingYunnanChina
| | - Zhi Peng
- Department of Orthopedics, The First People's Hospital of Yunnan ProvinceThe Affiliated Hospital of Kunming University of Science and TechnologyKunmingYunnanChina
- The Key Laboratory of Digital Orthopedics of Yunnan ProvinceKunmingYunnanChina
| | - Sheng Lu
- Department of Orthopedics, The First People's Hospital of Yunnan ProvinceThe Affiliated Hospital of Kunming University of Science and TechnologyKunmingYunnanChina
- The Key Laboratory of Digital Orthopedics of Yunnan ProvinceKunmingYunnanChina
| |
Collapse
|
2
|
Wang W, Zhen J. Prognostic Factors and Surgical Impact of Non-metastatic Conventional Chondrosarcoma of the Extremities. Orthop Surg 2023; 15:3288-3299. [PMID: 37875420 PMCID: PMC10694025 DOI: 10.1111/os.13916] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/05/2023] [Revised: 09/08/2023] [Accepted: 09/13/2023] [Indexed: 10/26/2023] Open
Abstract
OBJECTIVE Chondrosarcoma is a common bone malignancy, and the main treatment method is surgery. Different surgeries lead to different survival outcomes. The aim of this study was to construct a new clinical predictive tool to accurately predict the overall survival (OS) and cause specific survival (CSS) of patients with chondrosarcoma receiving different treatments. METHODS A total of 620 patients with chondrosarcoma registered between January 1, 2000 and December 31, 2016 were recruited as study targets. The missing values are filled by multiple imputation. Two continuous variables, age and tumor size, were divided into binary variables based on Kaplan-Meier curve. Univariate and multivariate analyses were used to explore predictors and establish nomograms. Propensity score matching (PSM) analysis was used to reduce the impact of potential confounders to determine whether different surgical modalities had any survival benefits in subgroups. RESULTS In a multivariate cox regression, age, grade, tumor size, radiotherapy, chemotherapy, and surgical methods were identified as independent prognostic factors for chondrosarcoma. To construct 1-, 3-, and 5-year nomogram maps of OS and CSS with prognostic factors and verify the c index internally (OS, 0.807; CSS, 0.847) above American Joint Committee on Cancer (AJCC) (OS, 0.685; CSS, 0.732). CONCLUSION This study found that the 5 year overall survival rate of patients with non-metastatic chondrosarcoma of the extremities was about 80%. Age, high malignancy, large tumor, prior chemoradiotherapy, and poor surgical selection were independent risk factors. Therefore, the nomogram established in this study will help to optimize clinicians' personalized decision making for patients.
Collapse
Affiliation(s)
- Wenhui Wang
- College of Medical ImagingShanxi Medical UniversityTaiyuanChina
- Department of Imagingthe Second Hospital of Shanxi Medical UniversityTaiyuanChina
| | - Junping Zhen
- Department of Imagingthe Second Hospital of Shanxi Medical UniversityTaiyuanChina
| |
Collapse
|
3
|
Jiang L, Gong Y, Jiang J, Zhao D. Construction of novel predictive tools for post-surgical cancer-specific survival probability in patients with primary chondrosarcoma and external validation in Chinese cohorts: a large population-based retrospective study. J Cancer Res Clin Oncol 2023; 149:13027-13042. [PMID: 37466790 DOI: 10.1007/s00432-023-05186-z] [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: 05/22/2023] [Accepted: 07/13/2023] [Indexed: 07/20/2023]
Abstract
BACKGROUND Surgery is the predominant treatment modality for chondrosarcoma. This study aims to construct a novel clinic predictive tool that accurately predicts the 3-, 5-, and 8-year probability of cancer-specific survival (CSS) for primary chondrosarcoma patients who have undergone surgical treatment. METHODS The Surveillance, Epidemiology, and End Results (SEER) database was used to identify 982 primary chondrosarcoma patients after surgery, who were randomly divided into two sets: training set (60%) and internal validation set (40%). Cox proportional regression analyses were used to screen post-surgical independent prognostic variables in primary chondrosarcoma patients. These identified variables were used to construct a nomogram to predict the probability of post-surgical CSS of primary chondrosarcoma patients. The k-fold cross-validation method (k = 10), Harrell's concordance index (C-index), receiver operating characteristic curve (ROC) and area under curve (AUC) were used to assess the predictive accuracy of the nomogram. Calibration curve and decision curve analysis (DCA) were used to validate the clinical application of the nomogram. RESULTS Age, tumor size, disease stage and histological type were finally identified post-surgical independent prognostic variables. Based the above variables, a nomogram was constructed to predict the 3-, 5- and 8-year probability of post-surgical CSS in primary chondrosarcoma patients. The results of the C-index showed excellent predictive performance of the nomogram (training set: 0.837, 95% CI: 0.766-0.908; internal validation set: 0.835, 95% CI: 0.733-0.937; external validation set: 0.869, 95% CI: 0.740-0.998). The AUCs of ROC were all greater than 0.830 which again indicated that the nomogram had excellent predictive performance. The results of calibration curve and DCA indicated that the clinical applicability of this nomogram was outstanding. Finally, the risk classification system and online access version of the nomogram was developed. CONCLUSION We constructed the first nomogram to accurately predict the 3-, 5- and 8-year probability of post-surgical CSS in primary chondrosarcoma patients. This nomogram would assist surgeons to provide individualized post-surgical survival predictions and clinical strategies for primary chondrosarcoma patients.
Collapse
Affiliation(s)
- Liming Jiang
- Department of Orthopedics, The China-Japan Union Hospital of Jilin University, No. 126 Xiantai Street, Changchun, 130033, Jilin, People's Republic of China
| | - Yan Gong
- Department of Orthopedics, The China-Japan Union Hospital of Jilin University, No. 126 Xiantai Street, Changchun, 130033, Jilin, People's Republic of China
| | - Jiajia Jiang
- Department of Orthopedics, The China-Japan Union Hospital of Jilin University, No. 126 Xiantai Street, Changchun, 130033, Jilin, People's Republic of China
| | - Dongxu Zhao
- Department of Orthopedics, The China-Japan Union Hospital of Jilin University, No. 126 Xiantai Street, Changchun, 130033, Jilin, People's Republic of China.
| |
Collapse
|
4
|
Lawrenz JM, Johnson SR, Hajdu KS, Chi A, Bendfeldt GA, Kang H, Halpern JL, Holt GE, Schwartz HS. Is the Number of National Database Research Studies in Musculoskeletal Sarcoma Increasing, and Are These Studies Reliable? Clin Orthop Relat Res 2023; 481:491-508. [PMID: 35767810 PMCID: PMC9928832 DOI: 10.1097/corr.0000000000002282] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/07/2022] [Accepted: 05/27/2022] [Indexed: 01/31/2023]
Abstract
BACKGROUND Large national databases have become a common source of information on patterns of cancer care in the United States, particularly for low-incidence diseases such as sarcoma. Although aggregating information from many hospitals can achieve statistical power, this may come at a cost when complex variables must be abstracted from the medical record. There is a current lack of understanding of the frequency of use of the Surveillance, Epidemiology, and End Results (SEER) database and the National Cancer Database (NCDB) over the last two decades in musculoskeletal sarcoma research and whether their use tends to produce papers with conflicting findings. QUESTIONS/PURPOSES (1) Is the number of published studies using the SEER and NCDB databases in musculoskeletal sarcoma research increasing over time? (2) What are the author, journal, and content characteristics of these studies? (3) Do studies using the SEER and the NCDB databases for similar diagnoses and study questions report concordant or discordant key findings? (4) Are the administrative data reported by our institution to the SEER and the NCDB databases concordant with the data in our longitudinally maintained, physician-run orthopaedic oncology dataset? METHODS To answer our first three questions, PubMed was searched from 2001 through 2020 for all studies using the SEER or the NCDB databases to evaluate sarcoma. Studies were excluded from the review if they did not use these databases or studied anatomic locations other than the extremities, nonretroperitoneal pelvis, trunk, chest wall, or spine. To answer our first question, the number of SEER and NCDB studies were counted by year. The publication rate over the 20-year span was assessed with simple linear regression modeling. The difference in the mean number of studies between 5-year intervals (2001-2005, 2006-2010, 2011-2015, 2016-2020) was also assessed with Student t-tests. To answer our second question, we recorded and summarized descriptive data regarding author, journal, and content for these studies. To answer our third question, we grouped all studies by diagnosis, and then identified studies that shared the same diagnosis and a similar major study question with at least one other study. We then categorized study questions (and their associated studies) as having concordant findings, discordant findings, or mixed findings. Proportions of studies with concordant, discordant, or mixed findings were compared. To answer our fourth question, a coding audit was performed assessing the concordance of nationally reported administrative data from our institution with data from our longitudinally maintained, physician-run orthopaedic oncology dataset in a series of patients during the past 3 years. Our orthopaedic oncology dataset is maintained on a weekly basis by the senior author who manually records data directly from the medical record and sarcoma tumor board consensus notes; this dataset served as the gold standard for data comparison. We compared date of birth, surgery date, margin status, tumor size, clinical stage, and adjuvant treatment. RESULTS The number of musculoskeletal sarcoma studies using the SEER and the NCDB databases has steadily increased over time in a linear regression model (β = 2.51; p < 0.001). The mean number of studies per year more than tripled during 2016-2020 compared with 2011-2015 (39 versus 13 studies; mean difference 26 ± 11; p = 0.03). Of the 299 studies in total, 56% (168 of 299) have been published since 2018. Nineteen institutions published more than five studies, and the most studies from one institution was 13. Orthopaedic surgeons authored 35% (104 of 299) of studies, and medical oncology journals published 44% (130 of 299). Of the 94 studies (31% of total [94 of 299]) that shared a major study question with at least one other study, 35% (33 of 94) reported discordant key findings, 29% (27 of 94) reported mixed key findings, and 44% (41 of 94) reported concordant key findings. Both concordant and discordant groups included papers on prognostic factors, demographic factors, and treatment strategies. When we compared nationally reported administrative data from our institution with our orthopaedic oncology dataset, we found clinically important discrepancies in adjuvant treatment (19% [15 of 77]), tumor size (21% [16 of 77]), surgery date (23% [18 of 77]), surgical margins (38% [29 of 77]), and clinical stage (77% [59 of 77]). CONCLUSION Appropriate use of databases in musculoskeletal cancer research is essential to promote clear interpretation of findings, as almost two-thirds of studies we evaluated that asked similar study questions produced discordant or mixed key findings. Readers should be mindful of the differences in what each database seeks to convey because asking the same questions of different databases may result in different answers depending on what information each database captures. Likewise, differences in how studies determine which patients to include or exclude, how they handle missing data, and what they choose to emphasize may result in different messages getting drawn from large-database studies. Still, given the rarity and heterogeneity of sarcomas, these databases remain particularly useful in musculoskeletal cancer research for nationwide incidence estimations, risk factor/prognostic factor assessment, patient demographic and hospital-level variable assessment, patterns of care over time, and hypothesis generation for future prospective studies. LEVEL OF EVIDENCE Level III, therapeutic study.
Collapse
Affiliation(s)
- Joshua M. Lawrenz
- Department of Orthopaedic Surgery, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Samuel R. Johnson
- Department of Orthopaedic Surgery, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Katherine S. Hajdu
- Department of Orthopaedic Surgery, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Andrew Chi
- Department of Orthopaedic Surgery, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Gabriel A. Bendfeldt
- Department of Orthopaedic Surgery, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Hakmook Kang
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Jennifer L. Halpern
- Department of Orthopaedic Surgery, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Ginger E. Holt
- Department of Orthopaedic Surgery, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Herbert S. Schwartz
- Department of Orthopaedic Surgery, Vanderbilt University Medical Center, Nashville, TN, USA
| |
Collapse
|
5
|
Association Between Insurance Status and Chondrosarcoma Stage at Diagnosis in the United States: Implications for Detection and Outcomes. J Am Acad Orthop Surg 2023; 31:e189-e197. [PMID: 36730695 DOI: 10.5435/jaaos-d-22-00379] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/14/2022] [Accepted: 08/20/2022] [Indexed: 02/04/2023] Open
Abstract
INTRODUCTION Chondrosarcoma is a common primary bone tumor, and survival is highly influenced by stage at diagnosis. Early detection is paramount to improve outcomes. The aim of this study is to analyze the association between insurance status and stage of chondrosarcoma at the time of diagnosis. METHODS A comparative cross-sectional study was conducted using the Surveillance, Epidemiology and End Results database. Patients with a diagnosis of chondrosarcoma between 2007 and 2016 were included. Exposure variable was insurance status and the outcome chondrosarcoma staging at the time of diagnosis. Control variables included tumor grade, age, sex, race, ethnicity, marital status, place of residence, and primary site. Both unadjusted and adjusted (multiple logistic regression) odds ratios (ORs) and 95% confidence intervals (CIs) were computed to estimate the association between insurance status and stage. RESULTS An effective sample of 2,187 patients was included for analysis. In total, 1824 (83%) patients had health insurance (nonspecified), 277 (13%) had Medicaid, and the remaining 86 (4%) had no insurance. Regarding stage at diagnosis, 1,213 (55%) had localized disease, whereas 974 (45%) had a later stage at presentation. Before adjustment, the odds of being diagnosed at an advanced (regional/distant) stage were 55% higher in patients without insurance (unadjusted OR 1.55; 95% CI 1.003 to 2.39). After adjusting for potential confounders, the odds increased (adjusted OR 1.94; 95% CI 1.12 to 3.32). Variables with a significant association with a later stage at diagnosis included older age ( P < 0.001), male sex ( P < 0.001), pelvic location ( P < 0.001), and high grade ( P < 0.001). CONCLUSION Being uninsured in the United States increased the odds of a late-stage diagnosis of chondrosarcoma by 94% when compared with insured patients. Lack of medical insurance presumably leads to diminished access to necessary diagnostic testing, which results in a more advanced stage at diagnosis and ultimately a worse prognosis. Efforts are required to remediate healthcare access disparities. LEVEL OF EVIDENCE Level III.
Collapse
|
6
|
Xie T, Sun Y, Han X, Zhang J. The clinicopathological characteristics and prognosis of young patients with chondrosarcoma of bone. Front Surg 2022; 9:926008. [PMID: 36132200 PMCID: PMC9484535 DOI: 10.3389/fsurg.2022.926008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2022] [Accepted: 08/16/2022] [Indexed: 11/26/2022] Open
Abstract
Purpose Clinicopathologic characteristics and treatment outcomes for young patients (less than 40 years) with chondrosarcoma of bone are rarely documented. The purpose of this study is to determine the clinicopathological characteristics and identify the survival predictors for this rare population. Patients and Methods We used the Surveillance, Epidemiology, and End Results (SEER) database to identify young patients with chondrosarcoma of bone between 1973 and 2016. Univariate and multivariate Cox regression analyses were conducted to determine the independent risk factors. Kaplan-Meier method was used to intuitively show the survival difference stratified by different treatments. Results A total of 1312 eligible young patients with chondrosarcoma of bone were analyzed this study. The mean age at diagnosis was 28.5 ± 0.2 years old (ranging from 1 to 40 years). 51.1% of cases were located in the extremity. More than two-thirds of patients (71.4%) were high grade. The majority of the patients (92.0%) received surgery, only 11.8% of patients received radiotherapy, and only 10.4% of patients received chemotherapy. The 5-year overall survival (OS) and cancer-specific survival (CSS) rates of this cohort were 88.5% and 89.1%, respectively. According to the results of multivariate analysis, nine variables were significantly correlated with OS and CSS, including gender, year of diagnosis, tumor site, tumor grade, tumor subtype, distant metastasis, tumor size, surgery, and chemotherapy. Conclusion Young patients with chondrosarcoma of bone experienced better prognosis. Surgery was significantly correlated with increased survival, while chemotherapy was significantly correlated with decreased survival. Radiotherapy was not a meaningful survival predictor of young patients with chondrosarcoma of bone. Prospective clinical trials are needed in the future to determine the effect of radiotherapy and chemotherapy on prognosis of those patients.
Collapse
Affiliation(s)
- Tao Xie
- Department of Orthopedic Surgery, Affiliated Hangzhou First People’s Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Yuanyuan Sun
- Department of Neurology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Xiao Han
- Department of Orthopedic Surgery, Affiliated Hangzhou First People’s Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Jian Zhang
- Department of Orthopedic Surgery, Affiliated Hangzhou First People’s Hospital, Zhejiang University School of Medicine, Hangzhou, China
- Correspondence: Jian Zhang
| |
Collapse
|
7
|
Cranmer LD, Chau B, Mantilla JG, Loggers ET, Pollack SM, Kim TS, Kim EY, Kane GM, Thompson MJ, Harwood JL, Wagner MJ. Is Chemotherapy Associated with Improved Overall Survival in Patients with Dedifferentiated Chondrosarcoma? A SEER Database Analysis. Clin Orthop Relat Res 2022; 480:748-758. [PMID: 34648466 PMCID: PMC8923599 DOI: 10.1097/corr.0000000000002011] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/17/2020] [Accepted: 09/21/2021] [Indexed: 01/31/2023]
Abstract
BACKGROUND Dedifferentiated chondrosarcoma is a chondrosarcoma subtype associated with high rates of recurrence and a poor prognosis. Others have proposed treatment of dedifferentiated chondrosarcoma using osteosarcoma protocols, including perioperative chemotherapy. However, the rarity of this condition poses difficulties in undertaking single- institution studies of sufficient sample size. QUESTION/PURPOSE Is perioperative chemotherapy associated with improved overall survival in patients with dedifferentiated chondrosarcoma? METHODS We queried the Surveillance, Epidemiology, and End Results (SEER) 1973 to 2016 database for patients with a diagnosis of dedifferentiated chondrosarcoma (n = 308). As dedifferentiated chondrosarcoma was only classified as a distinct entity in SEER starting in 2000, only patients treated in 2000 and later were included. We excluded from our analyses those patients with distant disease at diagnosis, a primary site of disease other than bone or joints, and those who did not receive cancer-directed surgery. These criteria yielded 185 dedifferentiated chondrosarcoma patients for inclusion. We used Kaplan-Meier analyses and Cox proportional hazards models to assess the association of clinical, demographic, and treatment characteristics on overall survival (OS). RESULTS After controlling for confounding variables, including age, sex, tumor size, stage, grade, location, and radiation treatment status, and after adjusting for missing data, no overall survival benefit was associated with receipt of chemotherapy in patients with dedifferentiated chondrosarcoma (hazard ratio 0.75 [95% confidence interval 0.49 to 1.12]; p = 0.16). CONCLUSION Chemotherapy treatment of dedifferentiated chondrosarcoma was not associated with improved OS. These results must be viewed cautiously, given the limited granularity of information on chemotherapy treatment, the concerns regarding chemotherapy misclassification in SEER data, and the small sample of patients with dedifferentiated chondrosarcoma, all of which limit the power to detect a difference. Our findings are nevertheless consistent with those of prior reports in which no benefit of chemotherapy could be detected. Lack of clear benefit from perioperative chemotherapy in dedifferentiated chondrosarcoma argues that it should be used only after careful consideration, and ideally in the context of a clinical trial. LEVEL OF EVIDENCE Level III, therapeutic study.
Collapse
Affiliation(s)
- Lee D. Cranmer
- Division of Medical Oncology, University of Washington, Seattle, WA, USA
- Clinical Research Division, Fred Hutchinson Cancer Research Center, Seattle, WA, USA
| | - Bonny Chau
- Division of Medical Oncology, University of Washington, Seattle, WA, USA
| | - Jose G. Mantilla
- Department of Laboratory Medicine and Pathology, University of Washington, Seattle, WA, USA
| | - Elizabeth T. Loggers
- Division of Medical Oncology, University of Washington, Seattle, WA, USA
- Clinical Research Division, Fred Hutchinson Cancer Research Center, Seattle, WA, USA
| | - Seth M. Pollack
- Division of Medical Oncology, University of Washington, Seattle, WA, USA
- Clinical Research Division, Fred Hutchinson Cancer Research Center, Seattle, WA, USA
| | - Teresa S. Kim
- Department of Surgery, University of Washington, Seattle, WA, USA
| | - Edward Y. Kim
- Department of Radiation Oncology, University of Washington, Seattle, WA, USA
| | - Gabrielle M. Kane
- Department of Radiation Oncology, University of Washington, Seattle, WA, USA
| | - Matthew J. Thompson
- Department of Orthopedics and Sports Medicine, University of Washington, Seattle, WA, USA
| | - Jared L. Harwood
- Department of Orthopedics and Sports Medicine, University of Washington, Seattle, WA, USA
| | - Michael J. Wagner
- Division of Medical Oncology, University of Washington, Seattle, WA, USA
- Clinical Research Division, Fred Hutchinson Cancer Research Center, Seattle, WA, USA
| |
Collapse
|
8
|
Groot OQ, Bindels BJJ, Ogink PT, Kapoor ND, Twining PK, Collins AK, Bongers MER, Lans A, Oosterhoff JHF, Karhade AV, Verlaan JJ, Schwab JH. Availability and reporting quality of external validations of machine-learning prediction models with orthopedic surgical outcomes: a systematic review. Acta Orthop 2021; 92:385-393. [PMID: 33870837 PMCID: PMC8436968 DOI: 10.1080/17453674.2021.1910448] [Citation(s) in RCA: 44] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/31/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Olivier Q Groot
- Orthopedic Oncology Service, Massachusetts General Hospital, Harvard Medical School, Boston, USA;;
- Department of Orthopedic Surgery, University Medical Center Utrecht, Utrecht University, The Netherlands
| | - Bas J J Bindels
- Department of Orthopedic Surgery, University Medical Center Utrecht, Utrecht University, The Netherlands
| | - Paul T Ogink
- Department of Orthopedic Surgery, University Medical Center Utrecht, Utrecht University, The Netherlands
| | - Neal D Kapoor
- Orthopedic Oncology Service, Massachusetts General Hospital, Harvard Medical School, Boston, USA;;
| | - Peter K Twining
- Orthopedic Oncology Service, Massachusetts General Hospital, Harvard Medical School, Boston, USA;;
| | - Austin K Collins
- Orthopedic Oncology Service, Massachusetts General Hospital, Harvard Medical School, Boston, USA;;
| | - Michiel E R Bongers
- Orthopedic Oncology Service, Massachusetts General Hospital, Harvard Medical School, Boston, USA;;
| | - Amanda Lans
- Orthopedic Oncology Service, Massachusetts General Hospital, Harvard Medical School, Boston, USA;;
- Department of Orthopedic Surgery, University Medical Center Utrecht, Utrecht University, The Netherlands
| | - Jacobien H F Oosterhoff
- Orthopedic Oncology Service, Massachusetts General Hospital, Harvard Medical School, Boston, USA;;
| | - Aditya V Karhade
- Orthopedic Oncology Service, Massachusetts General Hospital, Harvard Medical School, Boston, USA;;
| | - Jorrit-Jan Verlaan
- Department of Orthopedic Surgery, University Medical Center Utrecht, Utrecht University, The Netherlands
| | - Joseph H Schwab
- Orthopedic Oncology Service, Massachusetts General Hospital, Harvard Medical School, Boston, USA;;
| |
Collapse
|
9
|
Haygood TM, Amini B. Chondroid Tumors of Bone. Semin Ultrasound CT MR 2021; 42:123-133. [PMID: 33814100 DOI: 10.1053/j.sult.2020.08.017] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
Recent scholarship on enchondroma, chondrosarcoma, and chondroblastoma is presented. The focus of this article is on the imaging appearance of these tumors and the means by which they can be distinguished from one another by both clinical and imaging criteria.
Collapse
Affiliation(s)
- Tamara Miner Haygood
- Department of Musculoskeletal Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX.
| | - Behrang Amini
- Department of Musculoskeletal Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX
| |
Collapse
|
10
|
Yin M, Yan Y, Tong Z, Xu C, Qiao J, Zhou X, Ye J, Mo W. Development and Validation of a Novel Scoring System for Severity of Plantar Fasciitis. Orthop Surg 2020; 12:1882-1889. [PMID: 33112035 PMCID: PMC7767669 DOI: 10.1111/os.12827] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/20/2020] [Revised: 09/07/2020] [Accepted: 09/16/2020] [Indexed: 12/04/2022] Open
Abstract
OBJECTIVES Plantar fasciitis (PF) is the most common cause of heel pain. Though PF is self-limited, it can develop into chronic pain and thus treatment is needed. Early and accurate prognostic assessment of patients with PF is critically important for selecting the optimal treatment pathway. Nevertheless, there is no scoring system to determine the severity of PF and no prognostic model in choosing between conservative or surgical treatment. The study aimed to develop a novel scoring system to evaluate the severity of plantar fasciitis and predict the prognosis of conservative treatment. METHODS Data of consecutive patients treated from 2014 to 2018 were retrospectively collected. One hundred and eighty patients were eligible for the study. The demographics and clinical characteristics served as independent variables. The least follow-up time was 6 months. A minimal reduction of 60% in the visual analog scale (VAS) score from baseline was considered as minimal clinically important difference (MCID). Those factors significantly associated with achieving MCID in univariate analyses were further analyzed by multivariate logistic regression. A novel scoring system was developed using the best available literature and expert-opinion consensus. Inter-observer reliability and intra-observer reproducibility were evaluated. The appropriate cut-off points for the novel score system were obtained using receiver operating characteristic (ROC) curves. RESULTS The system score = VAS (0-3 point = 1; 3.1-7 point = 3; 7.1-10 point = 5) + duration of symptoms (<6 months = 1; ≥1 6 months = 2) + ability to walk without pain (>1 h = 1; ≤1 h = 4) + heel spur in X-ray (No = 0; Yes = 2) + high intensity zone (HIZ) in MRI (No = 0; Yes = 2). The total score was divided in four categories of severity: mild (2-4 points), moderate (5-8 points), severe (9-12 points), and critical (13-15 points). Inter-observer agreement with a value of 0.84 was considered as perfect reliability. Intra-observer reproducibility with a value of 0.92 was considered as perfect reproducibility. The optimum cut-off value was 10 points. The sensitivity of predictive factors was 86.37%, 84.21%, 91.22%, 84.12%, and 89.32%, respectively; the specificity was 64.21%, 53.27%, 67.76%, 62.37%, and 79.58%, respectively; the area under curve was 0.75, 0.71, 0.72, 0.87, and 0.77, respectively. The Hosmer-Lemeshow test showed a good fitting of the score system with an overall accuracy of 90.6%. CONCLUSIONS Based on prognostic factors, the present study establishes a novel scoring system which is highly comprehensible, reliable, and reproducible. This score system can be used to identify the severity of plantar fasciitis and predict the prognosis of conservative treatment accurately. The application of this scoring system in clinical settings can significantly improve the decision-making process.
Collapse
Affiliation(s)
- Meng‐chen Yin
- Department of Orthopaedics, Longhua HospitalShanghai University of Traditional Chinese MedicineShanghaiChina
| | - Yin‐jie Yan
- Department of Orthopaedics, Longhua HospitalShanghai University of Traditional Chinese MedicineShanghaiChina
| | - Zheng‐yi Tong
- Department of Orthopaedics, Longhua HospitalShanghai University of Traditional Chinese MedicineShanghaiChina
| | - Chong‐qin Xu
- Department of Orthopaedics, Longhua HospitalShanghai University of Traditional Chinese MedicineShanghaiChina
| | - Jiao‐jiao Qiao
- Department of Orthopaedics, Longhua HospitalShanghai University of Traditional Chinese MedicineShanghaiChina
| | - Xiao‐ning Zhou
- Department of Orthopaedics, Longhua HospitalShanghai University of Traditional Chinese MedicineShanghaiChina
| | - Jie Ye
- Department of Orthopaedics, Longhua HospitalShanghai University of Traditional Chinese MedicineShanghaiChina
| | - Wen Mo
- Department of Orthopaedics, Longhua HospitalShanghai University of Traditional Chinese MedicineShanghaiChina
| |
Collapse
|
11
|
Tong Y, Huang Z, Hu C, Chi C, Lv M, Li P, Zhao C, Song Y. Independent risk factors evaluation for overall survival and cancer-specific survival in thyroid cancer patients with bone metastasis: A study for construction and validation of the predictive nomogram. Medicine (Baltimore) 2020; 99:e21802. [PMID: 32899008 PMCID: PMC7478775 DOI: 10.1097/md.0000000000021802] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/13/2022] Open
Abstract
Bone is a frequent site for the occurrence of metastasis of thyroid cancer (TC). TC with bone metastasis (TCBM) is associated with skeletal-related events (SREs), with poor prognosis and low overall survival (OS). Therefore, it is necessary to develop a predictive nomogram for prognostic evaluation. This study aimed to construct an effective nomogram for predicting the OS and cancer-specific survival (CSS) of TC patients with BM. Those TC patients with newly diagnosed BM were retrospectively examined over a period of 6 years from 2010 to 2016 using data from the Surveillance, Epidemiology and End Results (SEER) database. Demographics and clinicopathological data were collected for further analysis. Patients were randomly allocated into training and validation cohorts with a ratio of ∼7:3. OS and CSS were retrieved as research endpoints. Univariate and multivariate Cox regression analyses were performed for identifying independent predictors. Overall, 242 patients were enrolled in this study. Age, histologic grade, histological subtype, tumor size, radiotherapy, liver metastatic status, and lung metastatic status were determined as the independent prognostic factors for predicting the OS and CSS in TCBM patients. Based on the results, visual nomograms were separately developed and validated for predicting 1-, 2-, and 3-year OS and CSS in TCBM patients on the ground of above results. The calibration, receiver operating characteristic (ROC) curve and decision curve analysis (DCA) also demonstrated the reliability and accuracy of the clinical prediction model. Our predictive model is expected to be a personalized and easily applicable tool for evaluating the prognosis of TCBM patients, and may contribute toward making an accurate judgment in clinical practice.
Collapse
Affiliation(s)
- Yuexin Tong
- Department of Minimally Invasive Spine Surgery, Affiliated Hospital of Chengde Medical University, Chengde, Hebei Province
| | - Zhangheng Huang
- Department of Minimally Invasive Spine Surgery, Affiliated Hospital of Chengde Medical University, Chengde, Hebei Province
| | - Chuan Hu
- Department of Minimally Invasive Spine Surgery, Affiliated Hospital of Chengde Medical University, Chengde, Hebei Province
- Department of Orthopedic Surgery, The Affiliated Hospital of Qingdao University, Qingdao, Shandong Province
| | - Changxing Chi
- Department of Radiotherapy, The Third Affiliated Hospital of Kunming Medical University, Kunming, Yunnan Province
| | - Meng Lv
- Department of Ophthalmology, Affiliated Hospital of Chengde Medical University, Chengde, Hebei Province, China
| | - Pengfei Li
- Department of Minimally Invasive Spine Surgery, Affiliated Hospital of Chengde Medical University, Chengde, Hebei Province
| | - Chengliang Zhao
- Department of Minimally Invasive Spine Surgery, Affiliated Hospital of Chengde Medical University, Chengde, Hebei Province
| | - Youxin Song
- Department of Minimally Invasive Spine Surgery, Affiliated Hospital of Chengde Medical University, Chengde, Hebei Province
| |
Collapse
|