Table 2. Quality assessment according to the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) criteria.

Study	Patient selection				Index test (machine learning)			Reference standard			Flow and timing					Patient selection	Index test	Reference standard
	Consecutive	Case- control	Inappropriate exclusion		Blinded to reference standard	Prespecified- threshold		Correctly classified target condition	Blinded to index test		Adequate interval: index to reference standard	All patients with reference standard	Same reference standard	All patients analyzed
*Referred to the studies included subjects with normal sinus rhythm and congestive heart failure/left ventricular systolic dysfunction patients from pubic database respectively. **Referred to the studies did not describe whether thresholds have been specified for machine learning data sets. ***Referred to the studies enrolled left ventricular systolic dysfunction patients with other diseases, such as diabetes mellitus, kidney disease, etc.
Pecchia, et al.[20]	Unclear	Yes*	No		Yes	Yes		Yes	Yes		Yes	Yes	Yes	Yes		Unclear	High	High
Chen, et al.[22]	Unclear	Yes*	No		Yes	Unclear**		Yes	Yes		Yes	Yes	Yes	Yes		Unclear	High	High
Acharya, et al.[21]	Unclear	Yes*	No		Yes	Unclear**		Yes	Yes		Yes	Yes	Yes	Yes		Unclear	High	High
Acharya, et al.[23]	Unclear	Yes*	No		Yes	Unclear**		Yes	Yes		Yes	Yes	Yes	Yes		Unclear	High	High
Attia, et al.[28]	Unclear	No	No		Yes	Yes		Yes	Yes		Yes	Yes	Yes	Yes		Low***	High	High
Hussain, et al.[24]	Unclear	Yes*	No		Yes	Unclear**		Yes	Yes		Yes	Yes	Yes	Yes		Unclear	High	High
Lih, et al.[25]	Unclear	Yes*	No		Yes	Unclear**		Yes	Yes		Yes	Yes	Yes	Yes		Unclear	High	High
Adedinsewo, et al.[29]	Yes	No	No		Yes	Unclear**		Yes	Yes		Yes	Yes	Yes	Yes		Low***	High	High
Yang, et al.[27]	Unclear	Yes*	No		Yes	Unclear**		Yes	Yes		Yes	Yes	Yes	Yes		Unclear	High	High
Attia, et al.[30]	Unclear	No	No		Yes	Unclear**		Yes	Yes		Yes	Yes	Yes	Yes		Low***	High	High
Jahmunah, et al.[26]	Unclear	Yes*	No		Yes	Unclear**		Yes	Yes		Yes	Yes	Yes	Yes		Unclear	High	High