FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3103444995> ?p ?o ?g. }

• W3103444995 abstract "Abstract Objectives Machine learning (ML) has been demonstrated to improve the prediction of functional outcome in patients with acute ischemic stroke. However, its value in a specific clinical use case has not been investigated. Aim of this study was to assess the clinical utility of ML models with respect to predicting functional impairment and severe disability or death considering its potential value as a decision-support tool in an acute stroke workflow. Materials and Methods Patients (n=1317) from a retrospective, non-randomized observational registry treated with Mechanical Thrombectomy (MT) were included. The final dataset of patients who underwent successful recanalization (TICI ≥ 2b) (n=932) was split in order to develop ML-based prediction models using data of (n=745, 80%) patients. Subsequently, the models were tested on the remaining patient data (n=187, 20%). For comparison, baseline algorithms using majority class prediction, SPAN-100 score, PRE score, and Stroke-TPI score were implemented. The ML methods included eight different algorithms (e.g. Support Vector Machines and Random forests), stacked ensemble method and tabular neural networks. Prediction of modified Rankin Scale (mRS) 3–6 (primary analysis) and mRS 5–6 (secondary analysis) at 3 months was performed using 25 baseline variables available at patient admission. ML models were assessed with respect to their ability for discrimination, calibration and clinical utility (decision curve analysis). Results Analyzed patients (n=932) showed a median age of 74.7 (IQR 62.7–82.4) years with (n=461, 49.5%) being female. ML methods performed better than clinical scores with stacked ensemble method providing the best overall performance including an F1-score of 0.75 ± 0.01, an ROC-AUC of 0.81 ± 0.00, AP score of 0.81 ± 0.01, MCC of 0.48 ± 0.02, and ECE of 0.06 ± 0.01 for prediction of mRS 3–6, and an F1-score of 0.57 ± 0.02, an ROC-AUC of 0.79 ± 0.01, AP score of 0.54 ± 0.02, MCC of 0.39 ± 0.03, and ECE of 0.19 ± 0.01 for prediction of mRS 5–6. Decision curve analyses suggested highest mean net benefit of 0.09 ± 0.02 at a-priori defined threshold (0.8) for the stacked ensemble method in primary analysis (mRS 3–6). Across all methods, higher mean net benefits were achieved for optimized probability thresholds but with considerably reduced certainty (threshold probabilities 0.24–0.47). For the secondary analysis (mRS 5–6), none of the ML models achieved a positive net benefit for the a-priori threshold probability 0.8. Conclusions The clinical utility of ML prediction models in a decision-support scenario aimed at yielding a high certainty for prediction of functional dependency (mRS 3–6) is marginal and not evident for the prediction of severe disability or death (mRS 5–6). Hence, using those models for patient exclusion cannot be recommended and future research should evaluate utility gains after incorporating more advanced imaging parameters." @default.
• W3103444995 created "2020-11-23" @default.
• W3103444995 creator A5000397338 @default.
• W3103444995 creator A5002472123 @default.
• W3103444995 creator A5007955209 @default.
• W3103444995 creator A5019980438 @default.
• W3103444995 creator A5020320620 @default.
• W3103444995 creator A5028955075 @default.
• W3103444995 creator A5034007830 @default.
• W3103444995 creator A5038570572 @default.
• W3103444995 creator A5059989473 @default.
• W3103444995 creator A5063137318 @default.
• W3103444995 creator A5073445438 @default.
• W3103444995 creator A5090448109 @default.
• W3103444995 date "2020-11-18" @default.
• W3103444995 modified "2023-10-01" @default.
• W3103444995 title "Beyond Accuracy: Investigating the Potential Clinical Utility of Predicting Functional Dependency and Severe Disability or Death in Successfully Reperfused Patients using Machine Learning" @default.
• W3103444995 cites W1582774210 @default.
• W3103444995 cites W1625634356 @default.
• W3103444995 cites W1984628358 @default.
• W3103444995 cites W2006381742 @default.
• W3103444995 cites W2045030989 @default.
• W3103444995 cites W2081301924 @default.
• W3103444995 cites W2087411027 @default.
• W3103444995 cites W2277258071 @default.
• W3103444995 cites W2436702034 @default.
• W3103444995 cites W2556696393 @default.
• W3103444995 cites W2561699212 @default.
• W3103444995 cites W2602181220 @default.
• W3103444995 cites W2768518950 @default.
• W3103444995 cites W2781354428 @default.
• W3103444995 cites W2894529428 @default.
• W3103444995 cites W2898554342 @default.
• W3103444995 cites W2901965063 @default.
• W3103444995 cites W2902080736 @default.
• W3103444995 cites W2903229176 @default.
• W3103444995 cites W2917157314 @default.
• W3103444995 cites W2917585458 @default.
• W3103444995 cites W2918716168 @default.
• W3103444995 cites W2921379447 @default.
• W3103444995 cites W2963296304 @default.
• W3103444995 cites W2967578066 @default.
• W3103444995 cites W2967587752 @default.
• W3103444995 cites W3006436762 @default.
• W3103444995 cites W3007594181 @default.
• W3103444995 cites W3010947265 @default.
• W3103444995 cites W3019119825 @default.
• W3103444995 cites W3022890390 @default.
• W3103444995 cites W3035510802 @default.
• W3103444995 cites W3042936115 @default.
• W3103444995 cites W3046808987 @default.
• W3103444995 cites W3080723895 @default.
• W3103444995 cites W3085552469 @default.
• W3103444995 cites W3087406383 @default.
• W3103444995 cites W3090176150 @default.
• W3103444995 cites W3093856169 @default.
• W3103444995 cites W3102476541 @default.
• W3103444995 doi "https://doi.org/10.1101/2020.11.17.20232280" @default.
• W3103444995 hasPublicationYear "2020" @default.
• W3103444995 type Work @default.
• W3103444995 sameAs 3103444995 @default.
• W3103444995 citedByCount "0" @default.
• W3103444995 crossrefType "posted-content" @default.
• W3103444995 hasAuthorship W3103444995A5000397338 @default.
• W3103444995 hasAuthorship W3103444995A5002472123 @default.
• W3103444995 hasAuthorship W3103444995A5007955209 @default.
• W3103444995 hasAuthorship W3103444995A5019980438 @default.
• W3103444995 hasAuthorship W3103444995A5020320620 @default.
• W3103444995 hasAuthorship W3103444995A5028955075 @default.
• W3103444995 hasAuthorship W3103444995A5034007830 @default.
• W3103444995 hasAuthorship W3103444995A5038570572 @default.
• W3103444995 hasAuthorship W3103444995A5059989473 @default.
• W3103444995 hasAuthorship W3103444995A5063137318 @default.
• W3103444995 hasAuthorship W3103444995A5073445438 @default.
• W3103444995 hasAuthorship W3103444995A5090448109 @default.
• W3103444995 hasBestOaLocation W31034449951 @default.
• W3103444995 hasConcept C119857082 @default.
• W3103444995 hasConcept C126322002 @default.
• W3103444995 hasConcept C127413603 @default.
• W3103444995 hasConcept C154945302 @default.
• W3103444995 hasConcept C1862650 @default.
• W3103444995 hasConcept C23131810 @default.
• W3103444995 hasConcept C2780645631 @default.
• W3103444995 hasConcept C2780931571 @default.
• W3103444995 hasConcept C3020199598 @default.
• W3103444995 hasConcept C41008148 @default.
• W3103444995 hasConcept C541997718 @default.
• W3103444995 hasConcept C71924100 @default.
• W3103444995 hasConcept C78519656 @default.
• W3103444995 hasConcept C99508421 @default.
• W3103444995 hasConceptScore W3103444995C119857082 @default.
• W3103444995 hasConceptScore W3103444995C126322002 @default.
• W3103444995 hasConceptScore W3103444995C127413603 @default.
• W3103444995 hasConceptScore W3103444995C154945302 @default.
• W3103444995 hasConceptScore W3103444995C1862650 @default.
• W3103444995 hasConceptScore W3103444995C23131810 @default.
• W3103444995 hasConceptScore W3103444995C2780645631 @default.
• W3103444995 hasConceptScore W3103444995C2780931571 @default.
• W3103444995 hasConceptScore W3103444995C3020199598 @default.
• W3103444995 hasConceptScore W3103444995C41008148 @default.

• next