Biomarker selection and a prospective metabolite-based machine learning diagnostic for lyme disease

Kehoe, Eric; Fitzgerald, Bryna L.; Graham, Barbara; Islam, M. Nurul; Sharma, K.; Wormser, Gary P.; Belisle, John T.; Kirby, Michael

doi:10.1038/s41598-022-05451-0

Cited by 11 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…applied the ResNet50 for detecting erythema migrans and other baffling skin conditions using a cross‐sectional dataset of images, obtaining 95% accuracy in recognizing erythema migrans. Kehoe et al 29 . constructed a discriminant model for Lyme illness based on metabolomics data, which is employed in general and can be readily adapted to other LCMS or metabolomics data sets.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Lyme rashes disease classification using deep feature fusion technique

Ali,

Anwar,

Nauman

et al. 2023

Skin Research and Technology

View full text Add to dashboard Cite

Automatic classification of Lyme disease rashes on the skin helps clinicians and dermatologists’ probe and investigate Lyme skin rashes effectively. This paper proposes a new in‐depth features fusion system to classify Lyme disease rashes. The proposed method consists of two main steps. First, three different deep learning models, Densenet201, InceptionV3, and Exception, were trained independently to extract the deep features from the erythema migrans (EM) images. Second, a deep feature fusion mechanism (meta classifier) is developed to integrate the deep features before the final classification output layer. The meta classifier is a basic deep convolutional neural network trained on original images and features extracted from base level three deep learning models. In the feature fusion mechanism, the last three layers of base models are dropped out and connected to the meta classifier. The proposed deep feature fusion method significantly improved the classification process, where the classification accuracy was 98.97%, which is particularly impressive than the other state‐of‐the‐art models.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Kehoe et al. 29 constructed a discriminant model for Lyme illness based on metabolomics data, which is employed in general and can be readily adapted to other LCMS or metabolomics data sets.…”

Section: Related Workmentioning

confidence: 99%

Lyme rashes disease classification using deep feature fusion technique

Ali,

Anwar,

Nauman

et al. 2023

Skin Research and Technology

View full text Add to dashboard Cite

show abstract

“…Another very important issue in metabolomics data-based biomarker discovery is the presence of missing values that can occur due to technical reason or biological origin [ 75 , 76 ]. The batch effect also influences the selection of biomarkers and can affect the prediction of the classifier model, as addressed by Kehoe et al [ 77 ]. Indeed, the authors showed that when training and test data are collected within the same batch of analysis, the classification models are more accurate, but they failed to achieve the same level of accuracy with data generated in a different session of analysis.…”

Section: Factors Influencing Biomarker Selection Through Machine Lear...mentioning

confidence: 99%

Precision Medicine Approaches with Metabolomics and Artificial Intelligence

Barberis

Khoso

Sica

et al. 2022

IJMS

View full text Add to dashboard Cite

Recent technological innovations in the field of mass spectrometry have supported the use of metabolomics analysis for precision medicine. This growth has been allowed also by the application of algorithms to data analysis, including multivariate and machine learning methods, which are fundamental to managing large number of variables and samples. In the present review, we reported and discussed the application of artificial intelligence (AI) strategies for metabolomics data analysis. Particularly, we focused on widely used non-linear machine learning classifiers, such as ANN, random forest, and support vector machine (SVM) algorithms. A discussion of recent studies and research focused on disease classification, biomarker identification and early diagnosis is presented. Challenges in the implementation of metabolomics–AI systems, limitations thereof and recent tools were also discussed.

show abstract

“…PCR assays have been developed to detect B. burgdorferi DNA [105]. Directly seeing spirochetal components can be an accurate method to identify active infections, such as antigens for OspC [105] and peptidoglycan [106]. OspC is present on spirochetes originating from the tick to the mammalian host [103].…”

Section: Immune Disorder and Diagnostic Implicationmentioning

confidence: 99%

Recent Advances in the Immunologic Method Applied to Tick-Borne Diseases in Brazil

De-Simone

Chino

2022

Pathogens

View full text Add to dashboard Cite

Zoonotic-origin infectious diseases are one of the major concerns of human and veterinary health systems. Ticks, as vectors of several zoonotic diseases, are ranked second only to mosquitoes as vectors. Many ticks’ transmitted infections are still endemic in the Americas, Europe, and Africa and represent approximately 17% of their infectious diseases population. Although our scientific capacity to identify and diagnose diseases is increasing, it remains a challenge in the case of tick-borne conditions. For example, in 2017, 160 cases of the Brazilian Spotted Fever (BSF, a tick-borne illness) were confirmed, alarming the notifiable diseases information system. Conversely, Brazilian borreliosis and ehrlichiosis do not require notification. Still, an increasing number of cases in humans and dogs have been reported in southeast and northeastern Brazil. Immunological methods applied to human and dog tick-borne diseases (TBD) show low sensitivity and specificity, cross-reactions, and false IgM positivity. Thus, the diagnosis and management of TBD are hampered by the personal tools and indirect markers used. Therefore, specific and rapid methods urgently need to be developed to diagnose the various types of tick-borne bacterial diseases. This review presents a brief historical perspective on the evolution of serological assays and recent advances in diagnostic tests for TBD (ehrlichiosis, BSF, and borreliosis) in humans and dogs, mainly applied in Brazil. Additionally, this review covers the emerging technologies available in diagnosing TBD, including biosensors, and discusses their potential for future use as gold standards in diagnosing these diseases.

show abstract

Biomarker selection and a prospective metabolite-based machine learning diagnostic for lyme disease

Cited by 11 publications

References 41 publications

Lyme rashes disease classification using deep feature fusion technique

Lyme rashes disease classification using deep feature fusion technique

Precision Medicine Approaches with Metabolomics and Artificial Intelligence

Recent Advances in the Immunologic Method Applied to Tick-Borne Diseases in Brazil

Contact Info

Product

Resources

About