Early detection of risk of autism spectrum disorder based on recurrence quantification analysis of electroencephalographic signals
| dc.contributor.advisor | Nieuwoudt, Martin | en_ZA |
| dc.contributor.advisor | De Vries, Petrus J. | en_ZA |
| dc.contributor.advisor | Aldrich, C. | en_ZA |
| dc.contributor.author | Heunis, Tosca-Marie | en_ZA |
| dc.contributor.other | Stellenbosch University. Faculty of Engineering. Dept. of Mechanical and Mechatronic Engineering. | en_ZA |
| dc.date.accessioned | 2016-03-09T14:42:49Z | |
| dc.date.available | 2016-03-09T14:42:49Z | |
| dc.date.issued | 2016-03 | |
| dc.description | Thesis (PhD)--Stellenbosch University, 2016. | en_ZA |
| dc.description.abstract | ENGLISH ABSTRACT: Background: Autism spectrum disorder (ASD) is a neurodevelopmental disorder (NDD) with a prevalence of 1–2%. In low resource environments, in particular, early identification and diagnosis is a significant challenge. There is a great demand for ‘language-free, culturally fair’ low-cost screening tools for ASD risk that do not require highly-trained professionals. There has been growing interest in electroencephalography (EEG) as an investigational tool for biomarker development in ASD and NDDs. One of the key challenges lies in the identification of appropriate multivariate, next-generation analytical methodologies that can characterise the complex, nonlinear dynamics of neural networks in the brain. Objectives: The primary objective was to develop a biomarker to differentiate ASD from typically developing (TD) individuals. The secondary objectives included evaluating the ability of the biomarker to discriminate between ASD and non-ASD within Tuberous Sclerosis Complex (TSC), a genetic disorder, and to distinguish non-syndromal and syndromal ASD. Method: Recurrence quantification analysis (RQA) of rsEEG was explored as a potential biomarker for ASD. The final methodology comprised the analysis of continuous five second segments of rsEEG with independent component analysis ocular artefact correction, multivariate time series embedding, principal component analysis dimensionality reduction, RQA feature extraction, and classification of statistically significant features using linear discriminant analysis (LDA), multilayer perceptron (MLP) neural network and support vector machine (SVM) classifiers. A clinical scenario of diagnosing an unseen subject was simulated using a leave-one-subject-out classification approach. Results: In a sample of 7 ASD and 5 TD subjects, aged 8 – 17 years, with analysis of 12 best segments, the proof-of-principle study showed 83.3% accuracy, 85.7% sensitivity and 80.0% specificity with a LDA classifier. A replication study (study 1) was performed in an age-matched sample of 7 ASD and 7 TD subjects, aged 2 – 6 years, comprising a total of 666 segments. Classification with a nonlinear SVM classifier showed 92.9% accuracy, 100.0% sensitivity and 85.7% specificity. The biomarker was explored further in an age and intellectual ability matched sample of 5 TSC+ASD and 5 TSC-ASD subjects, aged 0 – 12 years, comprising 1 202 segments (study 2). The nonlinear MLP classifier achieved 90.0% accuracy, 80.0% sensitivity and 100.0% specificity. The ability of the biomarker to distinguish non-syndromal and syndromal ASD was evaluated in an age and intellectual ability matched sample of 6 ASD and 6 TSC+ASD subjects, aged 2 – 6 years, with analysis of 832 segments (study 3). Using the MLP and SVM classifiers, 100% accuracy, sensitivity and specificity was achieved. Conclusions: RQA of rsEEG was an accurate classifier of ASD under a range of clinical conditions, suggesting potential of this approach for global screening in ASD. Validation of this biomarker in a large and well-matched sample is required. Age, gender, intellectual ability, socio-economic status, comorbidity, medication use, eyes-open versus eyes-closed condition, the number and location of electrodes, and test-retest reliability are all important factors to consider in the evaluation and development of biomarkers for ASD and related neurodevelopmental disabilities. | en_ZA |
| dc.description.abstract | AFRIKAANSE OPSOMMING: Agtergrond: Die outisme spektrum (ASD) is ‘n neurologiese ontwikkelingsafwyking (NDD) met ‘n voorkoms van 1–2%. Die vroeë identifikasie en diagnose van ASD is ‘n beduidende uitdaging veral in omgewings met hulpbron-tekort. Daar is ‘n groot behoefte aan lae-koste siftingsinstrumente vir ASD-risiko wat nie deur taal en kultuur gekortwiek word en hoogs opgeleide professionele persone benodig nie. Daar is toenemende belangstelling om elektro-enkefalografie (EEG) as ‘n ondersoekinstrument te gebruik vir biomerker-ontwikkeling in ASD en NDD. Een van die hoofuitdagings is die identifikasie van geskikte multiveranderlike, nuwe-generasie analitiese metodologieë wat die komplekse, nie-liniêre dinamika van die brein se senuweenetwerk kan karakteriseer. Doelwitte: Die primêre doelwit was om ‘n biomerker te ontwikkel om ASD en normaal-ontwikkelende (TD) individue van mekaar te onderskei. Die sekondêre doelwitte was die evaluering van die biomerker se vermoë om ASD en nie-ASD binne tubereuse sklerose kompleks (TSC) – ‘n genetiese toestand – te identifiseer, en om te onderskei tussen nie-sindroomverwante ASD en sindroomverwante ASD. Metode: Herhalingskwantifiseringsanalise (RQA) van rustende toestand EEG (rsEEG) is ondersoek as ‘n potensiële biomerker vir ASD. Die finale metodologie behels die analise van aaneenlopende vyf-sekonde rsEEG-segmente met onafhanklike komponent-analise, oogartefak-regstelling, multiveranderlike tydreeks-vaslegging, hoofkomponent-analise dimensionele vermindering, RQA kenmerk-ekstraksie, en klassifikasie van statisties betekenisvolle kenmerke deur liniêre diskriminantanalise (LDA), multivlak perseptron (MLP) neurale netwerk en ondersteuningsvektormasjien (SVM) klassifiseerders. ‘n Kliniese scenario van die diagnose van ‘n ongesiene deelnemer is gesimuleer deur die los-een-deelnemer-uit klassifikasiebenadering. Resultate: In ‘n steekproef van 7 ASD en 5 TD deelnemers, 8 – 17 jaar oud, met analise van die 12 beste segmente, het die bewys-van-beginsel studie 83.3% akkuraatheid, 85.7% sensitiwiteit en 80.0% spesifisiteit met ‘n LDA-klassifiseerder getoon. ‘n Repliseringstudie (studie 1) is gedoen in ‘n ouderdom-gekontroleerde steekproef van 7 ASD en 7 TD deelnemers, 2 – 6 jaar oud, met ‘n totaal van 666 segmente. Klassifikasie met ‘n nie-liniêre SVM-klassifiseerder het 92.9% akkuraatheid, 100.0% sensitiwiteit en 85.7% spesifisiteit getoon. Die biomerker is verder ondersoek in ‘n ouderdom- en intellektuele vermoëns-gekontroleerde groep van 5 TSC+ASD en 5 TSC-ASD deelnemers, 0 – 12 jaar oud, met 1 202 segmente (studie 2). Die nie-liniêre MLP-klassifiseerder het 90.0% akkuraatheid, 80.0% sensitiwiteit en 100.0% spesifisiteit behaal. Die vermoë van die biomerker om te onderskei tussen nie-sindroomverwante ASD en sindroomverwante ASD is geëvalueer in ‘n ouderdom- en intellektuele vermoëns-gekontroleerde steekproef van 6 ASD en 6 TSC+ASD deelnemers, 2 – 6 jaar oud, met die analise van 832 segmente (studie 3). Deur gebruik te maak van die MLP en SVM klassifiseerders is 100% akkuraatheid, sensitiwiteit en spesfisiteit behaal. Gevolgtrekkings: RQA van rsEEG was ‘n akkurate klassifiseerder van ASD onder ‘n reeks kliniese toestande, wat die potensiaal van hierdie benadering vir globale ASD sifting aandui. Validasie van hierdie biomerker in ‘n groot en gekontroleerde steekproef moet vasgestel word. Ouderdom, geslag, intellektuele vermoë, sosio-ekonomiese status, komorbiditeit, medikasiegebruik, oop-oë teenoor toe-oë toestand, die hoeveelheid en posisie van elektrodes en toets-hertoets betroubaarheid is alles belangrike faktore in die evaluering en ontwikkeling van biomerkers vir ASD en verwante neurologiese ontwikkelingsafwykings. | af_ZA |
| dc.description.sponsorship | QB201607 | |
| dc.format.extent | 223 pages : illustrations | en_ZA |
| dc.identifier.uri | http://hdl.handle.net/10019.1/98635 | |
| dc.language.iso | en_ZA | en_ZA |
| dc.publisher | Stellenbosch : Stellenbosch University | en_ZA |
| dc.rights.holder | Stellenbosch University | en_ZA |
| dc.subject | Autism spectrum disorders | en_ZA |
| dc.subject | Electroencephalography (EEG) | en_ZA |
| dc.subject | Brain--Imaging | en_ZA |
| dc.subject | UCTD | en_ZA |
| dc.title | Early detection of risk of autism spectrum disorder based on recurrence quantification analysis of electroencephalographic signals | en_ZA |
| dc.type | Thesis | en_ZA |