01763nas a2200325   4500000000100000008004100001260002500042653003300067653001100100653001900111653002800130653002300158100001900181700001300200700001500213700001700228700002200245700002400267700002500291700001500316700002000331700001300351700001400364245015700378856026000535300001200795490000600807520061000813022001401423       2025                            d  c11/2025bElsevier BV10asmartphone-based diagnostics10aChagas10aChagas disease10aArtificial Intelligence10aValidation studies1 aGEBRAN CH KJ1 aLEYVA JL1 aDEMOLDER A1 aKRESNAKOVA V1 aOmaña-Ávila ÓD1 aMILANO-MARTÍNEZ JM1 aGÓMEZ-FERNÁNDEZ JM1 aRAFAJDUS A1 aForero-Peña DA1 aHERMAN R1 aMendoza I00aSmartphone-based AI-enhanced ECG Detection of Left Ventricular Systolic Dysfunction in Chagas Disease: External Validation in a Resource-limited Setting  uhttps://pdf.sciencedirectassets.com/789132/1-s2.0-S3050661125X00034/1-s2.0-S3050661125000383/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEJr%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FwEaCXVzLWVhc3QtMSJGMEQCIAeEp7y8xiBTdiqhzl140WcMoOUXYnfdfeCgOFMR1QP8AiAnP88gucqj%2BC  a176-1800 v13 a<p><strong>Highlights</strong></p>

<ul>
	<li>The artificial intelligence-enhanced electrocardiographic (AI-enhanced ECG) model achieved high sensitivity and negative predictive values for detecting left ventricular systolic dysfunction in Chagas disease patients using photographed paper-based ECGs.</li>
	<li>Model performance remained robust across ECGs of varying quality and in populations outside the training dataset.</li>
	<li>The smartphone-compatible AI-enhanced ECG offers a scalable, low-cost solution for the early detection of cardiac dysfunction in low-resource settings.</li>
</ul>
  a3050-6611