Table 2.

Research overview: diagnosis.

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
Gordon et al., 2009	Eleanor and Lou Gehrig MDA/ALS Research Center	Real-life	34	ALS, UMN, PLS	Clinical	FS	None described	Linear regression	-
Srivastava et al., 2012	Boston Children Hospital	Real-life	46	SMA phenotypes	Clinical, genetic	FS	CV	SVM	AUC (0.928)
Welsh et al., 2013	Michigan MND Clinic	Real-life	63	ALS, healthy	Imaging	FS	LOOV	SVM	AUC:0.7, Acc:71%, Spec:74%, Sens:68.8%
Sarica et al., 2016	Catanzaro Magna Graecia University	Real-life	48	ALS, healthy	Clinical, imaging	SP, FS	CV	RF	Acc:80%
Schuster et al., 2016b	Trinity College Dublin	Real-life	147	ALS, healthy	Imaging	SP, FS	CV	Logistic regression	Acc:78.4%, raji Sens:90.5%, rajiSpec:62.5%
Bede et al., 2017	Trinity College Dublin	Real-life	150	ALS, healthy	Imaging	SP, FS	HOV	Discriminant function	Acc:90%, Sens:90%, Spec:90%
Ferraro et al., 2017	MND Clinics in Northern Italy	Real-life	265	ALS, UMN, ALS mimics	Imaging	SP	HOV	RF	Acc:87%, Spec:75%, Sens:92%
Fratello et al., 2017	UK PD Brain Bank	Real-life	120	ALS, PD, healthy	Imaging	SP, FS	CV	RF	Acc:80%
D'hulst et al., 2018	University Hospital rajiLeuven and Turino ALS Center	Real-life	370	ALS, healthy	Imaging	SP	LOOV	SVM	Acc:80%, Sens:85%, Spec:12.5%
Li et al., 2018	Australia	Clinical trial	81	ALS, KD, ALS mimics	Clinical	FS	None described	Linear regression	Acc:77.5%, Sens:68%, Spec:87%
Querin et al., 2018	Pitiè Salpêtrière Hospital	Real-life	105	ALS, healthy	Imaging	SP	CV	RF	AUC:0.96, Acc:86.5%, Sens:88%, Spec:85%

CV, Cross Validation; LOOV, Leave One Out Validation; HOV, Hold Out Validation; AUC, Area under the ROC Curve; Acc, Accuracy; Sens, Sensitivity; Spec, Specificity; PD, Parkinson's Disease; FS, Feature Selection; SP, Signal Processing.