Table 4.
Research overview: Prognosis with ML models (1/2).
| Key | Dataset(s) origin | Dataset(s) type | Dataset(s) length | Scope | Biomarker(s) type | Pre-processing (if any) | Validation (if any) | Model(s) tested | Performance | Framework |
|---|---|---|---|---|---|---|---|---|---|---|
| Gomeni and Fava, 2013 | PRO-ACT | Clinical trial | 338 | Progression | Clinical | FS | HOV | non-linear Weibull | AUC:0.96 | Classification |
| Hothorn and Jung, 2014 | PRO-ACT | Clinical trial | 1822 | Progression | Clinical, biological | MVI, VIA | HOV | RF | RMSE:0.52 (ALSFRS rate), PC:40% | Regression |
| Ko et al., 2014 | PRO-ACT | Clinical trial | 1822 | Progression | Clinical, biological | FS | HOV | RF | Spec:66%, Sens:65%, Acc:66% | Classification |
| Beaulieu-Jones and Greene, 2016 | PRO-ACT | Clinical trial | 3398 | Outcome | Clinical, biological | MVI | CV | NN, RF, SVM, k-NN, raji DT, NN with RF raji(best) |
AUC:0.692 | Classification |
| Taylor A. A. et al., 2016 | PRO-ACT, Emery ALS Clinic | Clinical trial, real-life | 4372 | Progression | Clinical | FS, MVR, VIA |
HOV | GLM, RF (best) |
R2:58.2%, MC:0.942, ME:-0.627 (ALSFRS score) | Regression |
| van der Burgh et al., 2017 | University Medical Center Utrecht | Real-life | 135 | Outcome | Clinical, imaging | SP | HOV | NN | Acc:84.4% | Classification |
| Huang et al., 2017 | PRO-ACT | Clinical trial | 6565 | Outcome | Clinical, biological | FS, MVR, raji VIA | CV | GP, Lasso, RF (best) |
C-ind:0.717 | Regression |
| Jahandideh et al., 2017 | PRO-ACT, NEALS | Clinical trial, population |
4406 | Progression | Clinical, biological | FS, MVI, VIA |
CV | RF, XGBoost, GBM (best) | RMSE:0.635 (FVC), R2:66.9% | Regression |
| Ong et al., 2017 | PRO-ACT | Clinical trial | 1568-6355 | Progression, outcome |
Clinical, biological | MVR, VIA | CV | Boosting | For P: AUC:0.82, rajiAcc:56.5%, rajiSpec:74%, rajiSens:39%, rajiFor O: AUC:0.83, rajiAcc:76.7%, rajiSpec:76.1%, rajiSens:77.3% |
Classification |
CV, Cross Validation; HOV, Hold Out Validation; AUC, Area under the ROC Curve; Acc, Accuracy; Sens, Sensitivity; Spec, Specificity; MC, Model Calibration; ME, Mean Error; PC, Pearson's Correlation; DT, Decision Tree; GLM, Generalized Linear Model; k-NN, k-Nearest Neighbors; FS, Feature Selection; MVI, Missing Value Imputation; VIA, Variable Importance Analysis; MVR, Missing Value Removal; P, Progression; O, Outcome; C-ind, Concordance; GP, Gaussian Process; GBM, Gradient Boosting Model; SP, Signal Processing; FVC, Forced Vital Capacity.