PMID- 32606026
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240329
IS  - 2379-5077 (Print)
IS  - 2379-5077 (Electronic)
IS  - 2379-5077 (Linking)
VI  - 5
IP  - 3
DP  - 2020 Jun 30
TI  - Metabolomics and Machine Learning Approaches Combined in Pursuit for More 
      Accurate Paracoccidioidomycosis Diagnoses.
LID - 10.1128/mSystems.00258-20 [doi]
LID - e00258-20
AB  - Brazil and many other Latin American countries are areas of endemicity for 
      different neglected diseases, and the fungal infection paracoccidioidomycosis 
      (PCM) is one of them. Among the clinical manifestations, pneumopathy associated 
      with skin and mucosal lesions is the most frequent. PCM definitive diagnosis 
      depends on yeast microscopic visualization and immunological tests, but both 
      present ambiguous results and difficulty in differentiating PCM from other fungal 
      infections. This research has employed metabolomics analysis through 
      high-resolution mass spectrometry to identify PCM biomarkers in serum samples in 
      order to improve diagnosis for this debilitating disease. To upgrade the 
      biomarker selection, machine learning approaches, using Random Forest 
      classifiers, were combined with metabolomics data analysis. The proposed 
      combination of these two analytical methods resulted in the identification of a 
      set of 19 PCM biomarkers that show accuracy of 97.1%, specificity of 100%, and 
      sensitivity of 94.1%. The obtained results are promising and present great 
      potential to improve PCM definitive diagnosis and adequate pharmacological 
      treatment, reducing the incidence of PCM sequelae and resulting in a better 
      quality of life.IMPORTANCE Paracoccidioidomycosis (PCM) is a fungal infection 
      typically found in Latin American countries, especially in Brazil. The 
      identification of this disease is based on techniques that may fail sometimes. 
      Intending to improve PCM detection in patient samples, this study used the 
      combination of two of the newest technologies, artificial intelligence and 
      metabolomics. This combination allowed PCM detection, independently of disease 
      form, through identification of a set of molecules present in patients' blood. 
      The great difference in this research was the ability to detect disease with 
      better confidence than the routine methods employed today. Another important 
      point is that among the molecules, it was possible to identify some indicators of 
      contamination and other infection that might worsen patients' condition. Thus, 
      the present work shows a great potential to improve PCM diagnosis and even 
      disease management, considering the possibility to identify concomitant harmful 
      factors.
CI  - Copyright (c) 2020 Lima et al.
FAU - Lima, Estela de Oliveira
AU  - Lima EO
AUID- ORCID: 0000-0003-0479-0364
AD  - Department of Internal Medicine, Botucatu Medical School, Sao Paulo State 
      University, Botucatu, SP, Brazil.
AD  - Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of 
      Campinas, Campinas, SP, Brazil.
FAU - Navarro, Luiz Claudio
AU  - Navarro LC
AUID- ORCID: 0000-0002-8041-8743
AD  - RECOD Laboratory, Institute of Computing, University of Campinas, Campinas, SP, 
      Brazil.
FAU - Morishita, Karen Noda
AU  - Morishita KN
AD  - Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of 
      Campinas, Campinas, SP, Brazil.
FAU - Kamikawa, Camila Mika
AU  - Kamikawa CM
AD  - Laboratory of Mycosis Immunodiagnosis-Immunology Section, Adolfo Lutz Institute, 
      Sao Paulo, SP, Brazil.
FAU - Rodrigues, Rafael Gustavo Martins
AU  - Rodrigues RGM
AD  - Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of 
      Campinas, Campinas, SP, Brazil.
FAU - Dabaja, Mohamed Ziad
AU  - Dabaja MZ
AD  - Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of 
      Campinas, Campinas, SP, Brazil.
FAU - de Oliveira, Diogo Noin
AU  - de Oliveira DN
AD  - Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of 
      Campinas, Campinas, SP, Brazil.
FAU - Delafiori, Jeany
AU  - Delafiori J
AD  - Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of 
      Campinas, Campinas, SP, Brazil.
FAU - Dias-Audibert, Flavia Luisa
AU  - Dias-Audibert FL
AD  - Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of 
      Campinas, Campinas, SP, Brazil.
FAU - Ribeiro, Marta da Silva
AU  - Ribeiro MDS
AD  - Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of 
      Campinas, Campinas, SP, Brazil.
FAU - Vicentini, Adriana Pardini
AU  - Vicentini AP
AD  - Laboratory of Mycosis Immunodiagnosis-Immunology Section, Adolfo Lutz Institute, 
      Sao Paulo, SP, Brazil.
FAU - Rocha, Anderson
AU  - Rocha A
AUID- ORCID: 0000-0002-4236-8212
AD  - RECOD Laboratory, Institute of Computing, University of Campinas, Campinas, SP, 
      Brazil anderson.rocha@ic.unicamp.br rrc@unicamp.br.
FAU - Catharino, Rodrigo Ramos
AU  - Catharino RR
AD  - Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of 
      Campinas, Campinas, SP, Brazil anderson.rocha@ic.unicamp.br rrc@unicamp.br.
LA  - eng
PT  - Journal Article
DEP - 20200630
PL  - United States
TA  - mSystems
JT  - mSystems
JID - 101680636
PMC - PMC7329323
OTO - NOTNLM
OT  - artificial intelligence
OT  - diagnosis
OT  - metabolomics
OT  - paracoccidioidomycosis
EDAT- 2020/07/02 06:00
MHDA- 2020/07/02 06:01
PMCR- 2020/06/30
CRDT- 2020/07/02 06:00
PHST- 2020/07/02 06:00 [entrez]
PHST- 2020/07/02 06:00 [pubmed]
PHST- 2020/07/02 06:01 [medline]
PHST- 2020/06/30 00:00 [pmc-release]
AID - 5/3/e00258-20 [pii]
AID - mSystems00258-20 [pii]
AID - 10.1128/mSystems.00258-20 [doi]
PST - epublish
SO  - mSystems. 2020 Jun 30;5(3):e00258-20. doi: 10.1128/mSystems.00258-20.