Background:The prediction of survival is valuable to optimize treatment of metastatic long-bone disease. The Skeletal Oncology Research Group (SORG) machine-learning (ML) algorithm has been previously developed and internally validated. The purpose of this study was to determine if the SORG ML algorithm accurately predicts 90-day and 1-year survival in an external metastatic long-bone disease patient cohort.Methods: A retrospective review of 264 patients who underwent surgery for long-bone metastases between 2003 and 2019 was performed. Variables used in the stochastic gradient boosting SORG algorithm were age, sex, primary tumor type, visceral/brain metastases, systemic therapy, and 10 preoperative laboratory values. Model performance was calculated by discrimination, calibration, and overall performance.Results: The SORG ML algorithms retained good discriminative ability (area under the cure [AUC]: 0.83; 95% confidence interval [CI]: 0.76-0.88 for 90-day mortality and AUC: 0.84; 95% CI: 0.79-0.88 for 1-year mortality), calibration, overall performance, and decision curve analysis.
Conclusion:The previously developed ML algorithms demonstrated good performance in the current study, thereby providing external validation. The models were incorporated into an accessible application (https://sorg-apps.shinyapps.io/ extremitymetssurvival/) that may be freely utilized by clinicians in helping predict survival for individual patients and assist in informative decision-making discussion before operative management of long bone metastatic lesions.
Background
Patients often turn to web-based resources following the diagnosis of osteosarcoma. To be fully understood by average American adults, the American Medical Association (AMA) and National Institutes of Health (NIH) recommend web-based health information to be written at a 6th grade level or lower. Previous analyses of osteosarcoma resources have not measured whether text is written such that readers can process key information (understandability) or identify available actions to take (actionability). The Patient Education Materials Assessment Tool (PEMAT) is a validated measurement of understandability and actionability.
Objective
The purpose of this study was to evaluate web-based osteosarcoma resources using measures of readability, understandability, and actionability.
Methods
Using the search term “osteosarcoma,” two independent Google searches were performed on March 7, 2020 (by AGS), and March 11, 2020 (by TRG). The top 50 results were collected. Websites were included if they were directed at providing patient education on osteosarcoma. Readability was quantified using validated algorithms: Flesh-Kincaid Grade Ease (FKGE), Flesch-Kincaid Grade-Level (FKGL). A higher FKGE score indicates that the material is easier to read. All other readability scores represent the US school grade level. Two independent PEMAT assessments were performed with independent scores assigned for both understandability and actionability. A PEMAT score of 70% or below is considered poorly understandable or poorly actionable. Statistical significance was defined as P≤.05.
Results
Two searches yielded 53 unique websites, of which 37 (70%) met the inclusion criteria. The mean FKGE and FKGL scores were 40.8 (SD 13.6) and 12.0 (SD 2.4), respectively. No website scored within the acceptable NIH or AHA recommended reading level. Only 4 (11%) and 1 (3%) website met the acceptable understandability and actionability threshold. Both understandability and actionability were positively correlated with FKGE (ρ=0.55, P<.001; ρ=0.60, P<.001), but were otherwise not significantly associated with other readability scores. There were no associations between readability (P=.15), understandability (P=.20), or actionability (P=.31) scores and Google rank.
Conclusions
Overall, web-based osteosarcoma patient educational materials scored poorly with respect to readability, understandability, and actionability. None of the web-based resources scored at the recommended reading level. Only 4 achieved the appropriate score to be considered understandable by the general public. Authors of patient resources should incorporate PEMAT and readability criteria to improve web-based resources to support patient understanding.
data do not provide evidence that undergoing such treatments increases women's risk of experiencing PPD relative to women who conceived naturally and intentionally. Instead, having an unintended birth increases risk of experiencing more postpartum depressive symptoms.
BACKGROUND
Patients often turn to online resources following the diagnosis of osteosarcoma. To be fully understood by the average American adult, the American Medical Association (AMA) and National Institutes of Health (NIH) recommend online health information to be written at a 6th grade level or lower. Previous analyses of osteosarcoma resources have not measured whether text is written such that readers can process key information (understandability) or identify available actions to take (actionability). The Patient Education Materials Assessment Tool (PEMAT) is a validated measurement of understandability and actionability.
OBJECTIVE
The purpose of this study was to evaluate osteosarcoma online resources utilizing measures of readability, understandability, and actionability.
METHODS
Using the search term “osteosarcoma”, two independent searches (Google.com) were performed and the top 50 results were collected. Websites were included if directed at providing patient education on osteosarcoma. Readability was quantified using validated algorithms: Flesh-Kincaid Grade Ease (FKGE), Flesch-Kincaid Grade-Level (FKGL). A higher FKGE score represents the material is easier to read. All other readability scores represent the US school grade level. Two independent PEMAT assessments were performed with independent scores assigned for both understandability and actionability. A PEMAT score of 70% or below is considered poorly understandable and/or poorly actionable. Statistical significance was defined as p≤0.05.
RESULTS
Of 53 unique websites, 37 websites (69.8%) met inclusion criteria. The mean FKGE was 40.8±13.6. The mean FKGL grade level was 12.0±2.4. No (0%) websites scored within the acceptable NIH/AHA recommended reading level. Overall, only 10.8% (n=4) and 2.7% (n=1) met the acceptable understandability and actionability threshold.
CONCLUSIONS
Overall, osteosarcoma online patient educational materials scored poorly with respect to readability, understandability, and actionability. None of the online resources scored at the recommended reading level. Only four met the appropriate score to considered understandable by the general public. Future efforts should be made to improve online resources in order to support patient understanding.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.