| DB ID | MyCo_5264 |
| Title | Metabolomics and Machine Learning Approaches Combined in Pursuit for More Accurate Paracoccidioidomycosis Diagnoses |
| Year | 2020 |
| PMID | 32606026 |
| Fungal Diseases involved | Paracoccidioidomycosis |
| Associated Medical Condition | None |
| Genus | Paracoccidioides |
| Species | brasiliensis |
| Organism | Paracoccidioides brasiliensis |
| Ethical Statement | This work was approved under number 1.850.251 by the Research Ethics Com- mittee of the University of Campinas. |
| Site of Infection | None |
| Opportunistic invasive | None |
| Sample type | Body fluid |
| Sample source | Serum |
| Host Group | Human |
| Host Common name | Human |
| Host Scientific name | Homo sapiens |
| Biomarker Name | GlcCer (d36:1α [2OH]) |
| Biomarker Full Name | GlcCer (d36:1α [2OH]) |
| Biomarker Type | Diagnostic |
| Biomolecule | Metabolite |
| Geographical Location | Brazil |
| Cohort | In total, 343 individuals were included in this study, regardless of age and gender, in two main groups: the test group, consisting of PCM patients (n=85),andthecontrolgroup(n=258). |
| Cohort No. | 85 Patients and 258 control |
| Age Group | None |
| P Value | None |
| Sensitivity | 0.941 |
| Specificity | 1 |
| Positive Predictive Value | None |
| MIC | None |
| Fold Change | None |
| Pathway | None |
| Disease Introduction Mechanism | None |
| Technique | Bioinformatics analysis |
| Analysis Method | Metabolomics-Machine Learning Approaches |
| ELISA kits | None |
| Assay Data | None |
| Validation Techniques used | Metabolomics-Machine Learning Approaches |
| Up Regulation Down Regulation | Positive |
| Sequence Data | ID: LMSP05010059 |
| External Link | None |
