4b4d1efacfd69c16ef34eec76b793a95 pmc_11764607.pdf a6e5c0e2f70db70f4c6112edbfef10703e0a4d9c pmc_11764607.pdf 6b156ef18ae07a42ae708f13a0b197374a0cd00238c52c5e858adf573fa15053 pmc_11764607.pdf Title: Evaluation of an Artificial Intelligence-Based Tool and a Universal Low-Cost Robotized Microscope for the Automated Diagnosis of Malaria Subject: The gold standard diagnosis for malaria is the microscopic visualization of blood smears to identify Plasmodium parasites, although it is an expert-dependent technique and could trigger diagnostic errors. Artificial intelligence (AI) tools based on digital image analysis were postulated as a suitable supportive alternative for automated malaria diagnosis. A diagnostic evaluation of the iMAGING AI-based system was conducted in the reference laboratory of the International Health Unit Drassanes-Vall d’Hebron in Barcelona, Spain. iMAGING is an automated device for the diagnosis of malaria by using artificial intelligence image analysis tools and a robotized microscope. A total of 54 Giemsa-stained thick blood smear samples from travelers and migrants coming from endemic areas were employed and analyzed to determine the presence/absence of Plasmodium parasites. AI diagnostic results were compared with expert light microscopy gold standard method results. The AI system shows 81.25% sensitivity and 92.11% specificity when compared with the conventional light microscopy gold standard method. Overall, 48/54 (88.89%) samples were correctly identified [13/16 (81.25%) as positives and 35/38 (92.11%) as negatives]. The mean time of the AI system to determine a positive malaria diagnosis was 3 min and 48 s, with an average of 7.38 FoV analyzed per sample. Statistical analyses showed the Kappa Index = 0.721, demonstrating a satisfactory correlation between the gold standard diagnostic method and iMAGING results. The AI system demonstrated reliable results for malaria diagnosis in a reference laboratory in Barcelona. Validation in malaria-endemic regions will be the next step to evaluate its potential in resource-poor settings. Keywords: artificial intelligence; malaria; automated diagnosis; tropical medicine; Plasmodium; point-of-care; infectious diseases Author: Carles Rubio Maturana, Allisson Dantas de Oliveira, Francesc Zarzuela, Alejandro Mediavilla, Patricia Martínez-Vallejo, Aroa Silgado, Lidia Goterris, Marc Muixí, Alberto Abelló, Anna Veiga, Daniel López-Codina, Elena Sulleiro, Elisa Sayrol and Joan Joseph-Munné Creator: LaTeX with hyperref Producer: pdfTeX-1.40.25 CreationDate: Mon Jan 6 10:35:06 2025 CET ModDate: Mon Jan 6 10:42:49 2025 CET Custom Metadata: no Metadata Stream: no Tagged: no UserProperties: no Suspects: no Form: none JavaScript: no Pages: 11 Encrypted: no Page size: 595.276 x 841.89 pts (A4) Page rot: 0 File size: 1117815 bytes Optimized: no PDF version: 1.7 name type encoding emb sub uni object ID ------------------------------------ ----------------- ---------------- --- --- --- --------- XWOCXD+VnURWPalladioL-Bold Type 1 Custom yes yes yes 10 0 MLQFKQ+URWPalladioL-Roma Type 1 Custom yes yes yes 16 0 NAHOOK+URWPalladioL-Bold Type 1 Custom yes yes yes 22 0 CMTVTV+URWPalladioL-Ital Type 1 Custom yes yes yes 27 0 LWJOET+VnURWPalladioL Type 1 Custom yes yes yes 32 0 OVNEXW+EURM10 Type 1 Builtin yes yes yes 58 0 KWKPAT+CMSY10 Type 1 Builtin yes yes yes 66 0 PUQVDK+PalatinoLinotype-Roman CID TrueType Identity-H yes yes yes 78 0 URFZVA+PalatinoLinotype-Bold CID TrueType Identity-H yes yes yes 86 0 KSBMLU+PalatinoLinotype-Italic TrueType WinAnsi yes yes yes 94 0 FSSNTE+PalatinoLinotype-Bold TrueType WinAnsi yes yes yes 98 0 AVDEBO+PalatinoLinotype-Roman TrueType WinAnsi yes yes yes 102 0 ZKIUPY+URWPalladioL-BoldItal Type 1 Custom yes yes yes 111 0 URFZVA+PalatinoLinotype-Bold CID TrueType Identity-H yes yes yes 123 0 PUQVDK+PalatinoLinotype-Roman CID TrueType Identity-H yes yes yes 131 0 KSBMLU+PalatinoLinotype-Italic TrueType WinAnsi yes yes yes 139 0 FSSNTE+PalatinoLinotype-Bold TrueType WinAnsi yes yes yes 143 0 AVDEBO+PalatinoLinotype-Roman TrueType WinAnsi yes yes yes 147 0 Jhove (Rel. 1.28.0, 2023-05-18) Date: 2025-02-13 02:52:06 CET RepresentationInformation: pmc_11764607.pdf ReportingModule: PDF-hul, Rel. 1.12.4 (2023-03-16) LastModified: 2025-02-11 02:32:13 CET Size: 1117815 Format: PDF Version: 1.7 Status: Well-Formed and valid SignatureMatches: PDF-hul MIMEtype: application/pdf PDFMetadata: Objects: 267 FreeObjects: 1 IncrementalUpdates: 0 DocumentCatalog: PageLayout: SinglePage PageMode: UseNone Outlines: Item: Title: Introduction Destination: section.1 Item: Title: Materials and Methods Destination: section.2 Children: Item: Title: Study Design Destination: subsection.2.1 Item: Title: Sample Size Destination: subsection.2.2 Item: Title: Microscope Automation Destination: subsection.2.3 Item: Title: Image Analysis and Diagnostic Algorithm Destination: subsection.2.4 Item: Title: Statistical Analysis Destination: subsection.2.5 Item: Title: Results Destination: section.3 Children: Item: Title: Diagnostic Accuracy of the iMAGING System Compared with Light Optical Microscopy Destination: subsection.3.1 Item: Title: Parasite Density and Plasmodium Species Destination: subsection.3.2 Item: Title: iMAGING System Scanning Performance Destination: subsection.3.3 Item: Title: Discussion Destination: section.4 Item: Title: Conclusions Destination: section.5 Item: Title: Appendix A Destination: appendix.A. Item: Title: References Destination: appendix.B. Info: Title: Evaluation of an Artificial Intelligence-Based Tool and a Universal Low-Cost Robotized Microscope for the Automated Diagnosis of Malaria Author: Carles Rubio Maturana, Allisson Dantas de Oliveira, Francesc Zarzuela, Alejandro Mediavilla, Patricia Martínez-Vallejo, Aroa Silgado, Lidia Goterris, Marc Muixí, Alberto Abelló, Anna Veiga, Daniel López-Codina, Elena Sulleiro, Elisa Sayrol and Joan Joseph-Munné Subject: The gold standard diagnosis for malaria is the microscopic visualization of blood smears to identify Plasmodium parasites, although it is an expert-dependent technique and could trigger diagnostic errors. Artificial intelligence (AI) tools based on digital image analysis were postulated as a suitable supportive alternative for automated malaria diagnosis. A diagnostic evaluation of the iMAGING AI-based system was conducted in the reference laboratory of the International Health Unit Drassanes-Vall d’Hebron in Barcelona, Spain. iMAGING is an automated device for the diagnosis of malaria by using artificial intelligence image analysis tools and a robotized microscope. A total of 54 Giemsa-stained thick blood smear samples from travelers and migrants coming from endemic areas were employed and analyzed to determine the presence/absence of Plasmodium parasites. AI diagnostic results were compared with expert light microscopy gold standard method results. The AI system shows 81.25% sensitivity and 92.11% specificity when compared with the conventional light microscopy gold standard method. Overall, 48/54 (88.89%) samples were correctly identified [13/16 (81.25%) as positives and 35/38 (92.11%) as negatives]. The mean time of the AI system to determine a positive malaria diagnosis was 3 min and 48 s, with an average of 7.38 FoV analyzed per sample. Statistical analyses showed the Kappa Index = 0.721, demonstrating a satisfactory correlation between the gold standard diagnostic method and iMAGING results. The AI system demonstrated reliable results for malaria diagnosis in a reference laboratory in Barcelona. Validation in malaria-endemic regions will be the next step to evaluate its potential in resource-poor settings. Keywords: artificial intelligence; malaria; automated diagnosis; tropical medicine; Plasmodium; point-of-care; infectious diseases Creator: LaTeX with hyperref Producer: pdfTeX-1.40.25 CreationDate: Mon Jan 06 10:35:06 CET 2025 ModDate: Mon Jan 06 10:42:49 CET 2025 ID: 0xdfce9e13207257d49b1a76920da33a9a, 0xdfce9e13207257d49b1a76920da33a9a Filters: FilterPipeline: FlateDecode Fonts: Type1: Font: BaseFont: LWJOET+VnURWPalladioL FontSubset: true FirstChar: 177 LastChar: 226 FontDescriptor: FontName: LWJOET+VnURWPalladioL Flags: Symbolic FontBBox: -166, -283, 1021, 943 FontFile: true EncodingDictionary: Differences: true ToUnicode: true Font: BaseFont: MLQFKQ+URWPalladioL-Roma FontSubset: true FirstChar: 2 LastChar: 241 FontDescriptor: FontName: MLQFKQ+URWPalladioL-Roma Flags: Symbolic FontBBox: -166, -283, 1021, 943 FontFile: true EncodingDictionary: Differences: true ToUnicode: true Font: BaseFont: KWKPAT+CMSY10 FontSubset: true FirstChar: 0 LastChar: 21 FontDescriptor: FontName: KWKPAT+CMSY10 Flags: Symbolic FontBBox: -29, -960, 1116, 775 FontFile: true ToUnicode: true Font: BaseFont: NAHOOK+URWPalladioL-Bold FontSubset: true FirstChar: 2 LastChar: 122 FontDescriptor: FontName: NAHOOK+URWPalladioL-Bold Flags: Symbolic FontBBox: -152, -301, 1000, 935 FontFile: true EncodingDictionary: Differences: true ToUnicode: true Font: BaseFont: XWOCXD+VnURWPalladioL-Bold FontSubset: true FirstChar: 178 LastChar: 226 FontDescriptor: FontName: XWOCXD+VnURWPalladioL-Bold Flags: Symbolic FontBBox: -152, -301, 1000, 935 FontFile: true EncodingDictionary: Differences: true ToUnicode: true Font: BaseFont: OVNEXW+EURM10 FontSubset: true FirstChar: 22 LastChar: 22 FontDescriptor: FontName: OVNEXW+EURM10 Flags: Symbolic FontBBox: -32, -243, 1060, 720 FontFile: true ToUnicode: true Font: BaseFont: CMTVTV+URWPalladioL-Ital FontSubset: true FirstChar: 40 LastChar: 174 FontDescriptor: FontName: CMTVTV+URWPalladioL-Ital Flags: Symbolic FontBBox: -170, -305, 1010, 941 FontFile: true EncodingDictionary: Differences: true ToUnicode: true Font: BaseFont: ZKIUPY+URWPalladioL-BoldItal FontSubset: true FirstChar: 65 LastChar: 112 FontDescriptor: FontName: ZKIUPY+URWPalladioL-BoldItal Flags: Symbolic FontBBox: -170, -300, 1073, 935 FontFile: true EncodingDictionary: Differences: true ToUnicode: true Pages: Page: Sequence: 1 Annotations: Annotation: Subtype: Link Rect: 34, 177, 152, 186 Annotation: Subtype: Link Rect: 34, 165, 82, 174 Annotation: Subtype: Link Rect: 36, 75, 152, 84 Annotation: Subtype: Link Rect: 34, 63, 89, 72 Annotation: Subtype: Link Rect: 34, 774, 185, 810 Annotation: Subtype: Link Rect: 515, 774, 560, 810 Annotation: Subtype: Link Rect: 154, 643, 165, 657 Annotation: Subtype: Link Rect: 301, 643, 312, 657 Annotation: Subtype: Link Rect: 328, 629, 339, 643 Annotation: Subtype: Link Rect: 483, 629, 494, 643 Annotation: Subtype: Link Rect: 139, 615, 150, 629 Annotation: Subtype: Link Rect: 415, 27, 560, 37 Annotation: Subtype: Link Rect: 34, 379, 87, 398 Page: Sequence: 2 Annotations: Annotation: Subtype: Link Rect: 238, 672, 245, 681 ActionDest: 162 Annotation: Subtype: Link Rect: 422, 547, 429, 556 ActionDest: 162 Annotation: Subtype: Link Rect: 276, 505, 283, 514 ActionDest: 162 Annotation: Subtype: Link Rect: 512, 491, 519, 500 ActionDest: 162 Annotation: Subtype: Link Rect: 522, 491, 529, 500 ActionDest: 162 Annotation: Subtype: Link Rect: 360, 393, 367, 402 ActionDest: 162 Annotation: Subtype: Link Rect: 368, 393, 375, 402 ActionDest: 162 Annotation: Subtype: Link Rect: 503, 237, 510, 246 ActionDest: 162 Page: Sequence: 3 Annotations: Annotation: Subtype: Link Rect: 316, 700, 328, 709 ActionDest: 162 Annotation: Subtype: Link Rect: 480, 464, 487, 473 ActionDest: 162 Annotation: Subtype: Link Rect: 293, 257, 300, 266 ActionDest: 162 Page: Sequence: 4 Annotations: Annotation: Subtype: Link Rect: 236, 703, 243, 712 ActionDest: 162 Annotation: Subtype: Link Rect: 459, 700, 466, 712 ActionDest: 71 Page: Sequence: 5 Annotations: Annotation: Subtype: Link Rect: 271, 686, 278, 698 ActionDest: 108 Annotation: Subtype: Link Rect: 489, 452, 504, 464 ActionDest: 156 Annotation: Subtype: Link Rect: 444, 285, 451, 297 ActionDest: 116 Annotation: Subtype: Link Rect: 413, 147, 420, 159 ActionDest: 116 Page: Sequence: 6 Annotations: Annotation: Subtype: Link Rect: 260, 357, 267, 366 ActionDest: 162 Annotation: Subtype: Link Rect: 268, 357, 280, 366 ActionDest: 162 Annotation: Subtype: Link Rect: 280, 357, 292, 366 ActionDest: 162 Annotation: Subtype: Link Rect: 269, 329, 276, 338 ActionDest: 162 Annotation: Subtype: Link Rect: 277, 329, 289, 338 ActionDest: 162 Annotation: Subtype: Link Rect: 289, 329, 301, 338 ActionDest: 162 Annotation: Subtype: Link Rect: 433, 274, 445, 282 ActionDest: 162 Annotation: Subtype: Link Rect: 380, 246, 392, 255 ActionDest: 162 Annotation: Subtype: Link Rect: 273, 118, 280, 130 ActionDest: 71 Page: Sequence: 7 Annotations: Annotation: Subtype: Link Rect: 512, 744, 519, 754 ActionDest: 162 Annotation: Subtype: Link Rect: 480, 661, 492, 670 ActionDest: 162 Annotation: Subtype: Link Rect: 495, 661, 507, 670 ActionDest: 165 Annotation: Subtype: Link Rect: 445, 605, 457, 614 ActionDest: 165 Annotation: Subtype: Link Rect: 202, 438, 214, 447 ActionDest: 165 Annotation: Subtype: Link Rect: 215, 438, 227, 447 ActionDest: 165 Annotation: Subtype: Link Rect: 365, 285, 372, 294 ActionDest: 162 Annotation: Subtype: Link Rect: 261, 257, 273, 266 ActionDest: 165 Annotation: Subtype: Link Rect: 274, 257, 286, 266 ActionDest: 165 Page: Sequence: 8 Page: Sequence: 9 Page: Sequence: 10 Annotations: Annotation: Subtype: Link Rect: 308, 477, 345, 488 Annotation: Subtype: Link Rect: 239, 440, 277, 450 Annotation: Subtype: Link Rect: 283, 440, 319, 450 Annotation: Subtype: Link Rect: 478, 401, 515, 412 Annotation: Subtype: Link Rect: 521, 401, 557, 412 Annotation: Subtype: Link Rect: 59, 363, 96, 373 Annotation: Subtype: Link Rect: 102, 363, 138, 373 Annotation: Subtype: Link Rect: 299, 325, 336, 335 Annotation: Subtype: Link Rect: 290, 286, 327, 297 Annotation: Subtype: Link Rect: 334, 286, 370, 297 Annotation: Subtype: Link Rect: 280, 247, 318, 258 Annotation: Subtype: Link Rect: 324, 247, 360, 258 Annotation: Subtype: Link Rect: 59, 210, 96, 220 Annotation: Subtype: Link Rect: 102, 210, 138, 220 Annotation: Subtype: Link Rect: 238, 145, 275, 156 Annotation: Subtype: Link Rect: 281, 145, 318, 156 Annotation: Subtype: Link Rect: 478, 107, 515, 118 Annotation: Subtype: Link Rect: 521, 107, 557, 118 Annotation: Subtype: Link Rect: 59, 82, 96, 93 Annotation: Subtype: Link Rect: 102, 82, 138, 93 Page: Sequence: 11 Annotations: Annotation: Subtype: Link Rect: 117, 744, 155, 754 Annotation: Subtype: Link Rect: 161, 744, 197, 754 Annotation: Subtype: Link Rect: 231, 706, 268, 716 Annotation: Subtype: Link Rect: 274, 706, 310, 716 Annotation: Subtype: Link Rect: 283, 679, 320, 690 Annotation: Subtype: Link Rect: 327, 679, 363, 690 Annotation: Subtype: Link Rect: 445, 654, 482, 665 Annotation: Subtype: Link Rect: 324, 628, 362, 639 Annotation: Subtype: Link Rect: 81, 604, 119, 614 Annotation: Subtype: Link Rect: 125, 604, 161, 614 Annotation: Subtype: Link Rect: 395, 577, 432, 588 Annotation: Subtype: Link Rect: 439, 577, 475, 588 Checksum: d98d3637 Type: CRC32 Checksum: 4b4d1efacfd69c16ef34eec76b793a95 Type: MD5 Checksum: a6e5c0e2f70db70f4c6112edbfef10703e0a4d9c Type: SHA-1 Checksum: 6b156ef18ae07a42ae708f13a0b197374a0cd00238c52c5e858adf573fa15053 Type: SHA-256