Search: WFRF:(Lengqvist Johan) >
Towards an Earlier ...
Towards an Earlier Detection of Progressive Multiple Sclerosis using Metabolomics and Machine Learning
-
- Herman, Stephanie (author)
- Uppsala universitet,Klinisk kemi
-
- Kultima, Kim, Docent (thesis advisor)
- Uppsala universitet,Klinisk kemi
-
- Spjuth, Ola, Professor, 1977- (thesis advisor)
- Uppsala universitet,Institutionen för farmaceutisk biovetenskap,Science for Life Laboratory, SciLifeLab
-
show more...
-
- Burman, Joachim, Docent, 1974- (thesis advisor)
- Uppsala universitet,Landtblom: Neurovetenskap
-
- Lengqvist, Johan (thesis advisor)
- Pelago Bioscience AB
-
- Svensson, Camilla, Professor (thesis advisor)
- Institutionen för fysiologi och farmakologi, Karolinska Institutet
-
- Kastenmüller, Gabi, Docent, 1977- (opponent)
- Institute of Bioinformatics and Systems Biology at the Helmholtz Zentrum München
-
show less...
-
(creator_code:org_t)
- ISBN 9789151309811
- Uppsala : Acta Universitatis Upsaliensis, 2020
- English 56 s.
-
Series: Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Medicine, 1651-6206 ; 1674
- Related links:
-
https://uu.diva-port... (primary) (Raw object)
-
show more...
-
https://uu.diva-port... (Preview)
-
https://urn.kb.se/re...
-
show less...
Abstract
Subject headings
Close
- Decision-making guided by advanced analytics is becoming increasingly common in many fields. Implementing computationally driven healthcare solutions does, however, pose ethical dilemmas as it involves human health. Therefore, augmenting clinical expertise with advanced analytical insights to support decision-making in healthcare is probably a more feasible strategy.Multiple sclerosis is a debilitating neurological disease with two subtypes; relapsing-remitting multiple sclerosis (RRMS) and the typically late-stage progressive subtype (PMS). Progressive multiple sclerosis is a neurodegenerative phenotype, with a vague functional definition, that currently is diagnosed retrospectively. The challenge of diagnosing PMS earlier is a great example where data-driven insights might prove useful.This thesis addresses the need for an earlier detection of patients developing the progressive and neurodegenerative subtype of multiple sclerosis, using primarily metabolomics and machine learning approaches. In Paper I, the biochemical differences in cerebrospinal fluid (CSF) from RRMS and PMS patients were characterised, leading to the conclusion that it is possible to distinguish PMS patients based on biochemical alterations. In addition, pathway analysis revealed several metabolic pathways that were affected in the transition to PMS, including tryptophan metabolism and pyrimidine metabolism. In Paper II and III, the possibility of generating a concise PMS signature based on solely low-molecular measurements (III) or in combination with radiological and protein measures (II) was explored. In both cases, it was concluded that it is plausible to generate a condensed set of highly informative markers that can distinguish PMS patients from RRMS patients. In Paper III, the classifier was complemented with conformal prediction that enabled an estimate of confidence in single patient predictions and a personalised evaluation of current disease state. Finally, in Paper IV, the extracted low-molecular marker candidates were characterised in isolation, revealing that several metabolites were distinctively altered in the CSF of PMS patients, including increased levels of 4-acetamidobutanoate, 4-hydroxybenzoate and thymine.Overall, the results from this work indicate that it is possible to detect PMS at an earlier stage and that advanced analytical algorithms can support healthcare.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Bioinformatik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Bioinformatics (hsv//eng)
- MEDICIN OCH HÄLSOVETENSKAP -- Klinisk medicin -- Neurologi (hsv//swe)
- MEDICAL AND HEALTH SCIENCES -- Clinical Medicine -- Neurology (hsv//eng)
Keyword
- bioinformatics
- biomarkers
- progressive multiple sclerosis
- metabolomics
- machine learning
- advanced analytics
- mass spectrometry
Publication and Content Type
- vet (subject category)
- dok (subject category)
Find in a library
To the university's database
- By the author/editor
-
Herman, Stephani ...
-
Kultima, Kim, Do ...
-
Spjuth, Ola, Pro ...
-
Burman, Joachim, ...
-
Lengqvist, Johan
-
Svensson, Camill ...
-
show more...
-
Kastenmüller, Ga ...
-
show less...
- About the subject
-
- NATURAL SCIENCES
-
NATURAL SCIENCES
-
and Computer and Inf ...
-
and Bioinformatics
-
- MEDICAL AND HEALTH SCIENCES
-
MEDICAL AND HEAL ...
-
and Clinical Medicin ...
-
and Neurology
- Parts in the series
-
Digital Comprehe ...
- By the university
-
Uppsala University