AI-enabled assessment of gait patterns via smartphone
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10362/160965 |
Resumo: | Musculoskeletal and neurological diseases greatly impact the quality of life of those afflicted. Symptoms typically worsen over time and thus early detection is critical. Gait alterations are a common early warning sign but tests to detect gait alterations require expensive clinical equipment and experienced physical-health workers. Thus, there has recently been great interest in finding lower cost alternatives to data collection and gait alteration detection. We believe that the ubiquity of smartphones and their ability to record motion data reflect an opportunity for democratizing data collection equipment. We found that a particularly smartphone-friendly clinical approach is the dual-task method. Dual-task simultaneously places a patient under both a cognitive and a motor load. The additional cognitive task causes affected individuals to exhibit decreased gait quality allowing for detection of the underlying disease. In this dissertation, we develop dualgAIt, a system for the recording and analysis of a patient’s gait using low-cost smartphones. Data acquisition is achieved through an Android application that leverages only common sensors such as the accelerometer, the microphone and the gyroscope. This data is recorded in a database and processed by a desktop module, which displays visualisations of spatial and temporal gait features in a dashboard for a clinician. Additionally, we train supervised classifiers on these features to provide further decision support through an initial guess presented in the dashboard. We implemented and evaluated gait features from prior work and propose trial distance, a novel feature based on dynamic time warping which has shown good clinical potential as it is correlated with the cognitive dual-task cost. We validate the system through two sets of experiments consisting of single- and dual-task trials, evaluating both the classifiers and the predictive capacity of the features, and show that the system is able to provide effective clinical decision support. Our work shows that it is possible to reduce the cost clinical diagnosis and improve decision support through the use of data-driven technology, while also providing insights into the most relevant gait features. |
id |
RCAP_fe017c3fe8977c0e3e2bfbb4b4fd9e3c |
---|---|
oai_identifier_str |
oai:run.unl.pt:10362/160965 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
AI-enabled assessment of gait patterns via smartphonedecision support systemsgaitdual-tasksmartphonesensorsmachine learningDomínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e InformáticaMusculoskeletal and neurological diseases greatly impact the quality of life of those afflicted. Symptoms typically worsen over time and thus early detection is critical. Gait alterations are a common early warning sign but tests to detect gait alterations require expensive clinical equipment and experienced physical-health workers. Thus, there has recently been great interest in finding lower cost alternatives to data collection and gait alteration detection. We believe that the ubiquity of smartphones and their ability to record motion data reflect an opportunity for democratizing data collection equipment. We found that a particularly smartphone-friendly clinical approach is the dual-task method. Dual-task simultaneously places a patient under both a cognitive and a motor load. The additional cognitive task causes affected individuals to exhibit decreased gait quality allowing for detection of the underlying disease. In this dissertation, we develop dualgAIt, a system for the recording and analysis of a patient’s gait using low-cost smartphones. Data acquisition is achieved through an Android application that leverages only common sensors such as the accelerometer, the microphone and the gyroscope. This data is recorded in a database and processed by a desktop module, which displays visualisations of spatial and temporal gait features in a dashboard for a clinician. Additionally, we train supervised classifiers on these features to provide further decision support through an initial guess presented in the dashboard. We implemented and evaluated gait features from prior work and propose trial distance, a novel feature based on dynamic time warping which has shown good clinical potential as it is correlated with the cognitive dual-task cost. We validate the system through two sets of experiments consisting of single- and dual-task trials, evaluating both the classifiers and the predictive capacity of the features, and show that the system is able to provide effective clinical decision support. Our work shows that it is possible to reduce the cost clinical diagnosis and improve decision support through the use of data-driven technology, while also providing insights into the most relevant gait features.Doenças musculoesqueléticas e neurológicas têm um impacto substancial na vida dos pacientes. Dado que os sintomas tipicamente pioram com o tempo, a detecção prematura é crucial. Alterações na marcha são um primeiro sinal de alerta, no entanto, testes para as de- tetar requerem equipamento dispendioso e profissionais experientes. Consequentemente, soluções acessíveis para recolher dados e detectar alterações à marcha têm sido um objecto de estudo. O uso generalizado de smartphones e a sua capacidade para capturar dados de movimento apresenta uma oportunidade para democratizar equipamentos de recolha de dados. Consideramos que uma técnica clínica adaptável para uso em smartphones é o método de tarefa dupla. Este método combina no mesmo ensaio uma tarefa motora primária e uma tarefa cognitiva secundária. Em indivíduos afetados, a tarefa secundária adicional afeta a qualidade da marcha permitindo detetar a doença. Nesta dissertação, desenvolvemos o dualgAIt, um sistema para recolher e analisar padrões de marcha, usando smartphones de preço acessível. A aquisição de dados é con- seguida através de uma aplicação Android que usa sensores comuns, como o microfone, o acelerómetro e o giroscópio. Estes dados são guardados numa base de dados e proces- sados por um software de desktop que extrai características temporo-espaciais da marcha. Estes dados são apresentados num dashboard para análise por um profissional de saúde. Usando classificadores de aprendizagem supervisionada, este dashboard oferece ainda uma sugestão de diagnóstico. Implementámos e avaliámos características da marcha da literatura e propomos uma nova característica baseada em dynamic time warping, que mos- tra potencial clínico por apresentar uma alta correlação com o custo cognitivo da tarefa dupla. Validámos o sistema através de duas experiências com ensaios de tarefa única e dupla, avaliando tanto os classificadores como a capacidade preditiva das características da marcha. Com esta dissertação, mostramos ser possível melhorar o apoio a decisões clínicas através de tecnologias orientadas a dados, ao mesmo tempo que oferecemos intuição sobre quais são as características da marcha mais relevantes.Ferreira, FernandoRUNSilvestre, Ricardo Miguel Fortunato2023-12-07T12:38:34Z2023-102023-10-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/160965enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:43:34Zoai:run.unl.pt:10362/160965Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:58:13.620007Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
AI-enabled assessment of gait patterns via smartphone |
title |
AI-enabled assessment of gait patterns via smartphone |
spellingShingle |
AI-enabled assessment of gait patterns via smartphone Silvestre, Ricardo Miguel Fortunato decision support systems gait dual-task smartphone sensors machine learning Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
title_short |
AI-enabled assessment of gait patterns via smartphone |
title_full |
AI-enabled assessment of gait patterns via smartphone |
title_fullStr |
AI-enabled assessment of gait patterns via smartphone |
title_full_unstemmed |
AI-enabled assessment of gait patterns via smartphone |
title_sort |
AI-enabled assessment of gait patterns via smartphone |
author |
Silvestre, Ricardo Miguel Fortunato |
author_facet |
Silvestre, Ricardo Miguel Fortunato |
author_role |
author |
dc.contributor.none.fl_str_mv |
Ferreira, Fernando RUN |
dc.contributor.author.fl_str_mv |
Silvestre, Ricardo Miguel Fortunato |
dc.subject.por.fl_str_mv |
decision support systems gait dual-task smartphone sensors machine learning Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
topic |
decision support systems gait dual-task smartphone sensors machine learning Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
description |
Musculoskeletal and neurological diseases greatly impact the quality of life of those afflicted. Symptoms typically worsen over time and thus early detection is critical. Gait alterations are a common early warning sign but tests to detect gait alterations require expensive clinical equipment and experienced physical-health workers. Thus, there has recently been great interest in finding lower cost alternatives to data collection and gait alteration detection. We believe that the ubiquity of smartphones and their ability to record motion data reflect an opportunity for democratizing data collection equipment. We found that a particularly smartphone-friendly clinical approach is the dual-task method. Dual-task simultaneously places a patient under both a cognitive and a motor load. The additional cognitive task causes affected individuals to exhibit decreased gait quality allowing for detection of the underlying disease. In this dissertation, we develop dualgAIt, a system for the recording and analysis of a patient’s gait using low-cost smartphones. Data acquisition is achieved through an Android application that leverages only common sensors such as the accelerometer, the microphone and the gyroscope. This data is recorded in a database and processed by a desktop module, which displays visualisations of spatial and temporal gait features in a dashboard for a clinician. Additionally, we train supervised classifiers on these features to provide further decision support through an initial guess presented in the dashboard. We implemented and evaluated gait features from prior work and propose trial distance, a novel feature based on dynamic time warping which has shown good clinical potential as it is correlated with the cognitive dual-task cost. We validate the system through two sets of experiments consisting of single- and dual-task trials, evaluating both the classifiers and the predictive capacity of the features, and show that the system is able to provide effective clinical decision support. Our work shows that it is possible to reduce the cost clinical diagnosis and improve decision support through the use of data-driven technology, while also providing insights into the most relevant gait features. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-12-07T12:38:34Z 2023-10 2023-10-01T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10362/160965 |
url |
http://hdl.handle.net/10362/160965 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799138163840516096 |