Table 5.
Research overview: Prognosis with ML models (2/2).
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|
| Schuster et al., 2017 | Trinity College Dublin |
Real-life | 69 | Outcome | Clinical, imaging | SP, FS | CV | Logistic regression | Spec:83.34%, Sens:75%, Acc:79.19% | Classification |
| Seibold et al., 2017 | PRO-ACT | Clinical trial | 2534-3306 | Progression, outcome | Clinical, biological | MVR, VIA | None | RF | Treatment effect on rajioutcome and progression |
Regression |
| Bandini et al., 2018 | - | Clinical trial | 64 | Progression | Clinical | SP, FS | CV | k-NN, SVM (best) | Spec:86.1%, Sens:88.8%, Acc:87% | Classification |
| Pfohl et al., 2018 | Emery ALS Clinic | Real-life | 801 | Outcome | Clinical | MVI, FS, VIA |
CV | GLM, raji RF (best) | RMSE:547 raji+/-46 days, rajiR2:52%, rajiAUC:0.85 | Regression, Classification |
| Westeneng et al., 2018 | 14 European ALS centers | Real-life | 11475 | Outcome | Clinical | FS, MVI | CV | MRP | Acc:78%, MC:1.01, AUC:0.86 | Classification |
CV, Cross Validation; AUC, Area under the ROC Curve; Acc, Accuracy; Sens, Sensitivity; Spec, Specificity; MC, Model Calibration; GLM, Generalized Linear Model; k-NN, k-Nearest Neighbors; MRP, Multivariate Royston-Parmar; FS, Feature Selection; MVI, Missing Value Imputation; VIA, Variable Importance Analysis; MVR, Missing Value Removal;SP, Signal Processing.