bc6506438c605035511ae08a3745bafb sensors_a2022v22n13p4790.pdf 817853a74eff5e0710fc1297de3902c6d02f3079 sensors_a2022v22n13p4790.pdf 59126282d6b4fb7e507f1eee73da3633d3e2c2b1897e722a9d78f36da946e20a sensors_a2022v22n13p4790.pdf Title: A Machine Learning Approach for Predicting Non-Suicidal Self-Injury in Young Adults Subject: Artificial intelligence techniques were explored to assess the ability to anticipate self-harming behaviour in the mental health context using a database collected by an app previously designed to record the emotional states and activities of a group of subjects exhibiting self-harm. Specifically, the Leave-One-Subject-Out technique was used to train classification trees with a maximum of five splits. The results show an accuracy of 84.78%, a sensitivity of 64.64% and a specificity of 85.53%. In addition, positive and negative predictive values were also obtained, with results of 14.48% and 98.47%, respectively. These results are in line with those reported in previous work using a multilevel mixed-effect regression analysis. The combination of apps and AI techniques is a powerful way to improve the tools to accompany and support the care and treatment of patients with this type of behaviour. These studies also guide the improvement of apps on the user side, simplifying and collecting more meaningful data, and on the therapist side, progressing in pathology treatments. Traditional therapy involves observing and reconstructing what had happened before episodes once they have occurred. This new generation of tools will make it possible to monitor the pathology more closely and to act preventively. Keywords: NSSI; EMA; app; machine learning Author: Pere Marti-Puig, Chiara Capra, Daniel Vega, Laia Llunas and Jordi Solé-Casals Creator: LaTeX with hyperref Producer: pdfTeX-1.40.21 CreationDate: Fri Jun 24 14:08:17 2022 CEST ModDate: Fri Jun 24 14:10:34 2022 CEST Tagged: no UserProperties: no Suspects: no Form: none JavaScript: no Pages: 14 Encrypted: no Page size: 595.276 x 841.89 pts (A4) Page rot: 0 File size: 1757905 bytes Optimized: no PDF version: 1.7 name type encoding emb sub uni object ID ------------------------------------ ----------------- ---------------- --- --- --- --------- UEPUGP+URWPalladioL-Bold Type 1 Custom yes yes no 10 0 AZDDQB+URWPalladioL-Roma Type 1 Custom yes yes no 15 0 RSGJZP+URWPalladioL-Ital Type 1 Custom yes yes no 19 0 RVSEMT+TimesNewRomanPS-BoldItalicMT Type 1C WinAnsi yes yes no 37 0 PDTLUH+CMSY10 Type 1 Builtin yes yes no 62 0 RLYTRW+CMMI10 Type 1 Builtin yes yes no 83 0 YTYGMW+CMEX10 Type 1 Builtin yes yes no 100 0 RFLZJB+CMR10 Type 1 Builtin yes yes no 104 0 QQXUPP+PazoMath Type 1 Builtin yes yes no 108 0 Jhove (Rel. 1.22.1, 2019-04-17) Date: 2023-06-17 02:32:16 CEST RepresentationInformation: sensors_a2022v22n13p4790.pdf ReportingModule: PDF-hul, Rel. 1.12.1 (2019-04-17) LastModified: 2022-06-29 10:47:59 CEST Size: 1757905 Format: PDF Version: 1.7 Status: Well-Formed and valid SignatureMatches: PDF-hul MIMEtype: application/pdf PDFMetadata: Objects: 238 FreeObjects: 1 IncrementalUpdates: 0 DocumentCatalog: PageLayout: SinglePage PageMode: UseNone Outlines: Item: Title: Introduction Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@12f41634 Item: Title: Materials and Methods Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@13c27452 Children: Item: Title: Participants Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@262b2c86 Item: Title: Sinjur App Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@371a67ec Item: Title: EMA Data Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@5ed828d Item: Title: Model and Training Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@50d0686 Item: Title: Leave-One-Subject-Out Cross Validation Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@7a3d45bd Item: Title: Preliminary Work Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@1e7c7811 Item: Title: Machine Learning Model Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@77ec78b9 Item: Title: Results and Discussion Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@1a3869f4 Children: Item: Title: Visualization Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@a38d7a3 Item: Title: Performance Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@77f99a05 Item: Title: Discussion Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@63440df3 Item: Title: Conclusions Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@3aeaafa6 Item: Title: References Destination: edu.harvard.hul.ois.jhove.module.pdf.PdfSimpleObject@76a3e297 Info: Title: A Machine Learning Approach for Predicting Non-Suicidal Self-Injury in Young Adults Author: Pere Marti-Puig, Chiara Capra, Daniel Vega, Laia Llunas and Jordi Solé-Casals Subject: Artificial intelligence techniques were explored to assess the ability to anticipate self-harming behaviour in the mental health context using a database collected by an app previously designed to record the emotional states and activities of a group of subjects exhibiting self-harm. Specifically, the Leave-One-Subject-Out technique was used to train classification trees with a maximum of five splits. The results show an accuracy of 84.78%, a sensitivity of 64.64% and a specificity of 85.53%. In addition, positive and negative predictive values were also obtained, with results of 14.48% and 98.47%, respectively. These results are in line with those reported in previous work using a multilevel mixed-effect regression analysis. The combination of apps and AI techniques is a powerful way to improve the tools to accompany and support the care and treatment of patients with this type of behaviour. These studies also guide the improvement of apps on the user side, simplifying and collecting more meaningful data, and on the therapist side, progressing in pathology treatments. Traditional therapy involves observing and reconstructing what had happened before episodes once they have occurred. This new generation of tools will make it possible to monitor the pathology more closely and to act preventively. Keywords: NSSI; EMA; app; machine learning Creator: LaTeX with hyperref Producer: pdfTeX-1.40.21 CreationDate: Fri Jun 24 14:08:17 CEST 2022 ModDate: Fri Jun 24 14:10:34 CEST 2022 ID: 0x0c25931d6622fee1b4f59f535b68bb00, 0x0c25931d6622fee1b4f59f535b68bb00 Filters: FilterPipeline: FlateDecode Images: Image: NisoImageMetadata: FormatName: image/png ImageWidth: 1360 ImageHeight: 1226 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 1478 ImageHeight: 956 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 1564 ImageHeight: 506 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 1558 ImageHeight: 1156 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 1610 ImageHeight: 1164 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Fonts: Type1: Font: BaseFont: RSGJZP+URWPalladioL-Ital FontSubset: true FirstChar: 45 LastChar: 231 FontDescriptor: FontName: RSGJZP+URWPalladioL-Ital Flags: Symbolic FontBBox: -170, -305, 1010, 941 FontFile: true EncodingDictionary: Differences: true Font: BaseFont: RLYTRW+CMMI10 FontSubset: true FirstChar: 60 LastChar: 60 FontDescriptor: FontName: RLYTRW+CMMI10 Flags: Symbolic FontBBox: -32, -250, 1048, 750 FontFile: true Font: BaseFont: YTYGMW+CMEX10 FontSubset: true FirstChar: 20 LastChar: 21 FontDescriptor: FontName: YTYGMW+CMEX10 Flags: Symbolic FontBBox: -24, -2960, 1454, 772 FontFile: true Font: BaseFont: RFLZJB+CMR10 FontSubset: true FirstChar: 43 LastChar: 61 FontDescriptor: FontName: RFLZJB+CMR10 Flags: Symbolic FontBBox: -40, -250, 1009, 750 FontFile: true Font: BaseFont: UEPUGP+URWPalladioL-Bold FontSubset: true FirstChar: 3 LastChar: 233 FontDescriptor: FontName: UEPUGP+URWPalladioL-Bold Flags: Symbolic FontBBox: -152, -301, 1000, 935 FontFile: true EncodingDictionary: Differences: true Font: BaseFont: QQXUPP+PazoMath FontSubset: true FirstChar: 229 LastChar: 229 FontDescriptor: FontName: QQXUPP+PazoMath Flags: Symbolic FontBBox: -40, -283, 878, 946 FontFile: true Font: BaseFont: PDTLUH+CMSY10 FontSubset: true FirstChar: 21 LastChar: 21 FontDescriptor: FontName: PDTLUH+CMSY10 Flags: Symbolic FontBBox: -29, -960, 1116, 775 FontFile: true Font: BaseFont: AZDDQB+URWPalladioL-Roma FontSubset: true FirstChar: 2 LastChar: 250 FontDescriptor: FontName: AZDDQB+URWPalladioL-Roma Flags: Symbolic FontBBox: -166, -283, 1021, 943 FontFile: true EncodingDictionary: Differences: true Pages: Page: Sequence: 1 Annotations: Annotation: Subtype: Link Rect: 34, 311, 146, 320 Annotation: Subtype: Link Rect: 34, 164, 96, 186 Annotation: Subtype: Link Rect: 126, 90, 154, 99 Annotation: Subtype: Link Rect: 34, 78, 147, 87 Annotation: Subtype: Link Rect: 34, 756, 153, 792 Annotation: Subtype: Link Rect: 515, 756, 560, 792 Annotation: Subtype: Link Rect: 119, 660, 130, 674 Annotation: Subtype: Link Rect: 279, 660, 290, 674 Annotation: Subtype: Link Rect: 472, 660, 483, 674 Annotation: Subtype: Link Rect: 447, 247, 454, 256 ActionDest: 121 Annotation: Subtype: Link Rect: 455, 247, 462, 256 ActionDest: 121 Annotation: Subtype: Link Rect: 442, 221, 449, 230 ActionDest: 121 Annotation: Subtype: Link Rect: 320, 196, 327, 205 ActionDest: 121 Annotation: Subtype: Link Rect: 328, 196, 335, 205 ActionDest: 121 Annotation: Subtype: Link Rect: 358, 184, 365, 193 ActionDest: 121 Annotation: Subtype: Link Rect: 168, 159, 175, 168 ActionDest: 121 Annotation: Subtype: Link Rect: 191, 133, 198, 143 ActionDest: 121 Annotation: Subtype: Link Rect: 199, 133, 206, 143 ActionDest: 121 Annotation: Subtype: Link Rect: 370, 121, 381, 130 ActionDest: 121 Annotation: Subtype: Link Rect: 200, 83, 212, 92 ActionDest: 121 Annotation: Subtype: Link Rect: 113, 17, 241, 28 Annotation: Subtype: Link Rect: 410, 17, 560, 28 Annotation: Subtype: Link Rect: 34, 384, 87, 403 Page: Sequence: 2 Annotations: Annotation: Subtype: Link Rect: 210, 723, 222, 732 ActionDest: 121 Annotation: Subtype: Link Rect: 289, 673, 301, 682 ActionDest: 121 Annotation: Subtype: Link Rect: 496, 660, 507, 669 ActionDest: 121 Annotation: Subtype: Link Rect: 253, 635, 265, 644 ActionDest: 121 Annotation: Subtype: Link Rect: 268, 635, 280, 644 ActionDest: 121 Annotation: Subtype: Link Rect: 470, 623, 482, 631 ActionDest: 121 Annotation: Subtype: Link Rect: 483, 622, 495, 631 ActionDest: 121 Annotation: Subtype: Link Rect: 465, 484, 477, 493 ActionDest: 121 Annotation: Subtype: Link Rect: 499, 447, 511, 456 ActionDest: 121 Annotation: Subtype: Link Rect: 323, 346, 335, 355 ActionDest: 121 Annotation: Subtype: Link Rect: 532, 321, 544, 330 ActionDest: 121 Annotation: Subtype: Link Rect: 274, 296, 286, 305 ActionDest: 124 Annotation: Subtype: Link Rect: 251, 271, 263, 280 ActionDest: 124 Annotation: Subtype: Link Rect: 543, 258, 555, 267 ActionDest: 124 Annotation: Subtype: Link Rect: 369, 221, 381, 230 ActionDest: 124 Annotation: Subtype: Link Rect: 197, 133, 209, 142 ActionDest: 124 Annotation: Subtype: Link Rect: 224, 95, 236, 104 ActionDest: 124 Page: Sequence: 3 Annotations: Annotation: Subtype: Link Rect: 382, 735, 394, 744 ActionDest: 124 Annotation: Subtype: Link Rect: 228, 635, 240, 644 ActionDest: 124 Annotation: Subtype: Link Rect: 267, 610, 279, 619 ActionDest: 124 Annotation: Subtype: Link Rect: 345, 610, 357, 619 ActionDest: 124 Annotation: Subtype: Link Rect: 393, 585, 405, 594 ActionDest: 124 Annotation: Subtype: Link Rect: 419, 422, 431, 431 ActionDest: 124 Annotation: Subtype: Link Rect: 429, 256, 437, 268 ActionDest: 59 Annotation: Subtype: Link Rect: 249, 218, 256, 230 ActionDest: 87 Annotation: Subtype: Link Rect: 553, 206, 560, 218 ActionDest: 118 Annotation: Subtype: Link Rect: 398, 144, 410, 153 ActionDest: 121 Annotation: Subtype: Link Rect: 410, 144, 422, 153 ActionDest: 124 Page: Sequence: 4 Annotations: Annotation: Subtype: Link Rect: 310, 698, 322, 707 ActionDest: 121 Annotation: Subtype: Link Rect: 328, 647, 340, 656 ActionDest: 121 Annotation: Subtype: Link Rect: 374, 494, 381, 506 ActionDest: 66 Annotation: Subtype: Link Rect: 168, 481, 415, 493 Annotation: Subtype: Link Rect: 207, 469, 517, 481 Annotation: Subtype: Link Rect: 408, 170, 414, 182 ActionDest: 72 Annotation: Subtype: Link Rect: 552, 60, 559, 72 ActionDest: 72 Page: Sequence: 5 Annotations: Annotation: Subtype: Link Rect: 258, 231, 265, 243 ActionDest: 75 Annotation: Subtype: Link Rect: 285, 144, 292, 156 ActionDest: 75 Page: Sequence: 6 Annotations: Annotation: Subtype: Link Rect: 341, 378, 353, 387 ActionDest: 124 Annotation: Subtype: Link Rect: 221, 165, 233, 174 ActionDest: 124 Page: Sequence: 7 Annotations: Annotation: Subtype: Link Rect: 201, 685, 213, 694 ActionDest: 124 Annotation: Subtype: Link Rect: 340, 507, 347, 519 ActionDest: 72 Annotation: Subtype: Link Rect: 319, 321, 331, 330 ActionDest: 124 Annotation: Subtype: Link Rect: 331, 321, 343, 330 ActionDest: 124 Annotation: Subtype: Link Rect: 506, 321, 518, 330 ActionDest: 124 Annotation: Subtype: Link Rect: 196, 145, 208, 154 ActionDest: 124 Annotation: Subtype: Link Rect: 209, 145, 221, 154 ActionDest: 124 Annotation: Subtype: Link Rect: 412, 107, 424, 116 ActionDest: 124 Page: Sequence: 8 Annotations: Annotation: Subtype: Link Rect: 499, 582, 506, 594 ActionDest: 72 Annotation: Subtype: Link Rect: 506, 380, 513, 392 ActionDest: 87 Annotation: Subtype: Link Rect: 243, 153, 250, 165 ActionDest: 92 Annotation: Subtype: Link Rect: 345, 141, 352, 153 ActionDest: 75 Page: Sequence: 9 Annotations: Annotation: Subtype: Link Rect: 387, 683, 394, 695 ActionDest: 92 Annotation: Subtype: Link Rect: 261, 261, 267, 272 ActionDest: 87 Annotation: Subtype: Link Rect: 486, 187, 493, 200 ActionDest: 97 Annotation: Subtype: Link Rect: 515, 175, 522, 187 ActionDest: 75 Annotation: Subtype: Link Rect: 403, 137, 410, 149 ActionDest: 92 Page: Sequence: 10 Page: Sequence: 11 Annotations: Annotation: Subtype: Link Rect: 344, 619, 356, 628 ActionDest: 124 Annotation: Subtype: Link Rect: 444, 581, 455, 590 ActionDest: 121 Annotation: Subtype: Link Rect: 289, 515, 295, 527 ActionDest: 72 Annotation: Subtype: Link Rect: 373, 505, 385, 515 ActionDest: 121 Annotation: Subtype: Link Rect: 531, 365, 538, 376 ActionDest: 66 Annotation: Subtype: Link Rect: 482, 352, 489, 364 ActionDest: 66 Annotation: Subtype: Link Rect: 275, 254, 287, 263 ActionDest: 121 Annotation: Subtype: Link Rect: 331, 129, 343, 138 ActionDest: 124 Annotation: Subtype: Link Rect: 391, 116, 403, 125 ActionDest: 124 Page: Sequence: 12 Annotations: Annotation: Subtype: Link Rect: 448, 723, 460, 732 ActionDest: 124 Annotation: Subtype: Link Rect: 382, 673, 394, 682 ActionDest: 124 Annotation: Subtype: Link Rect: 503, 446, 515, 455 ActionDest: 124 Page: Sequence: 13 Page: Sequence: 14 Checksum: 8cf244e5 Type: CRC32 Checksum: bc6506438c605035511ae08a3745bafb Type: MD5 Checksum: 817853a74eff5e0710fc1297de3902c6d02f3079 Type: SHA-1