Predicting Parkinson's disease trajectory using clinical and neuroimaging baseline measures
Predictive biomarkers of Parkinson's Disease progression are needed to expedite neuroprotective treatment development and facilitate prognoses for patients. This work uses measures derived from resting-state functional magnetic resonance imaging, including regional homogeneity (ReHo) and fracti...
Gespeichert in:
| Veröffentlicht in: | Parkinsonism & related disorders 2021-04, Vol.85, p.44-51 |
|---|---|
| Hauptverfasser: | , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 51 |
|---|---|
| container_issue | |
| container_start_page | 44 |
| container_title | Parkinsonism & related disorders |
| container_volume | 85 |
| creator | Nguyen, Kevin P. Raval, Vyom Treacher, Alex Mellema, Cooper Yu, Fang Frank Pinho, Marco C. Subramaniam, Rathan M. Dewey, Richard B. Montillo, Albert A. |
| description | Predictive biomarkers of Parkinson's Disease progression are needed to expedite neuroprotective treatment development and facilitate prognoses for patients. This work uses measures derived from resting-state functional magnetic resonance imaging, including regional homogeneity (ReHo) and fractional amplitude of low frequency fluctuations (fALFF), to predict an individual's current and future severity over up to 4 years and to elucidate the most prognostic brain regions.
ReHo and fALFF are measured for 82 Parkinson's Disease subjects and used to train machine learning predictors of baseline clinical and future severity at 1 year, 2 years, and 4 years follow-up as measured by the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Predictive performance is measured with nested cross-validation, validated on an external dataset, and again validated through leave-one-site-out cross-validation. Important predictive features are identified.
The models explain up to 30.4% of the variance in current MDS-UPDRS scores, 55.8% of the variance in year 1 scores, and 47.1% of the variance in year 2 scores (p |
| doi_str_mv | 10.1016/j.parkreldis.2021.02.026 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8127393</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S1353802021000754</els_id><sourcerecordid>2502809323</sourcerecordid><originalsourceid>FETCH-LOGICAL-c479t-9bed5df3272c2db9935ee9fdd5ab1ecbfedbd136d944187d5dd0b2a9ce511a6f3</originalsourceid><addsrcrecordid>eNqFkUlLBDEQhYMo7n9B-qaXHrNML7kIKm4g6EFPHkI6qR4z9iRj0i34761mXE9CQQLvq1eVPEIyRieMsvJ4Plnq-BKhsy5NOOVsQjlWuUa2WV2JvGC8XMe7KEReU063yE5Kc0ppVVCxSbaEqAQteblNnu4jWGd652fZPXo6n4I_TBkag06Q9VHPwfQhvmdDGiHTOe-M7jLtbeZhiMEt9GxUGuRRhGyBnUOEtEc2Wt0l2P88d8nj5cXD-XV-e3d1c356m5tpJftcNmAL2wpeccNtI6UoAGRrbaEbBqZpwTaWidLK6RRfh6ylDdfSQMGYLluxS05WvsuhWYA14HHrTi0jbhbfVdBO_VW8e1az8KZqxishBRocfRrE8DpA6tXCJQNdpz2EISleUF5TKfiI1ivUxJBShPZ7DKNqzEbN1U82asxGUY5VYuvB7zW_G7_CQOBsBQB-1puDqJJx4A0GFDEDZYP7f8oH15yqLA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2502809323</pqid></control><display><type>article</type><title>Predicting Parkinson's disease trajectory using clinical and neuroimaging baseline measures</title><source>MEDLINE</source><source>Elsevier ScienceDirect Journals</source><creator>Nguyen, Kevin P. ; Raval, Vyom ; Treacher, Alex ; Mellema, Cooper ; Yu, Fang Frank ; Pinho, Marco C. ; Subramaniam, Rathan M. ; Dewey, Richard B. ; Montillo, Albert A.</creator><creatorcontrib>Nguyen, Kevin P. ; Raval, Vyom ; Treacher, Alex ; Mellema, Cooper ; Yu, Fang Frank ; Pinho, Marco C. ; Subramaniam, Rathan M. ; Dewey, Richard B. ; Montillo, Albert A.</creatorcontrib><description>Predictive biomarkers of Parkinson's Disease progression are needed to expedite neuroprotective treatment development and facilitate prognoses for patients. This work uses measures derived from resting-state functional magnetic resonance imaging, including regional homogeneity (ReHo) and fractional amplitude of low frequency fluctuations (fALFF), to predict an individual's current and future severity over up to 4 years and to elucidate the most prognostic brain regions.
ReHo and fALFF are measured for 82 Parkinson's Disease subjects and used to train machine learning predictors of baseline clinical and future severity at 1 year, 2 years, and 4 years follow-up as measured by the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Predictive performance is measured with nested cross-validation, validated on an external dataset, and again validated through leave-one-site-out cross-validation. Important predictive features are identified.
The models explain up to 30.4% of the variance in current MDS-UPDRS scores, 55.8% of the variance in year 1 scores, and 47.1% of the variance in year 2 scores (p < 0.0001). For distinguishing high and low-severity individuals at each timepoint (MDS-UPDRS score above or below the median, respectively), the models achieve positive predictive values up to 79% and negative predictive values up to 80%. Higher ReHo and fALFF in several regions, including components of the default motor network, predicted lower severity across current and future timepoints.
These results identify an accurate prognostic neuroimaging biomarker which may be used to better inform enrollment in trials of neuroprotective treatments and enable physicians to counsel their patients.
•Biomarkers of Parkinson's Disease severity and future trajectory are needed.•Regional brain activity and homogeneity were measured from resting functional MRI.•Machine learning models were trained to predict disease severity from this data.•Both current and future severity were predicted reproducibly across datasets.•Several brain regions, such as the default mode network, were important predictors.</description><identifier>ISSN: 1353-8020</identifier><identifier>ISSN: 1873-5126</identifier><identifier>EISSN: 1873-5126</identifier><identifier>DOI: 10.1016/j.parkreldis.2021.02.026</identifier><identifier>PMID: 33730626</identifier><language>eng</language><publisher>England: Elsevier Ltd</publisher><subject>Aged ; Biomarkers ; Cerebellum - diagnostic imaging ; Cerebellum - physiopathology ; Cerebral Cortex - diagnostic imaging ; Cerebral Cortex - physiopathology ; Default Mode Network - diagnostic imaging ; Default Mode Network - physiopathology ; Disease Progression ; Female ; Follow-Up Studies ; Functional MRI ; Functional Neuroimaging - standards ; Humans ; Machine Learning ; Magnetic Resonance Imaging - standards ; Male ; Middle Aged ; Nerve Net - diagnostic imaging ; Nerve Net - physiopathology ; Neuroimaging ; Parkinson Disease - diagnosis ; Parkinson Disease - physiopathology ; Parkinson's disease ; Prognosis ; Reproducibility of Results ; Severity of Illness Index</subject><ispartof>Parkinsonism & related disorders, 2021-04, Vol.85, p.44-51</ispartof><rights>2021 Elsevier Ltd</rights><rights>Copyright © 2021 Elsevier Ltd. All rights reserved.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c479t-9bed5df3272c2db9935ee9fdd5ab1ecbfedbd136d944187d5dd0b2a9ce511a6f3</citedby><cites>FETCH-LOGICAL-c479t-9bed5df3272c2db9935ee9fdd5ab1ecbfedbd136d944187d5dd0b2a9ce511a6f3</cites><orcidid>0000-0001-8401-8889</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S1353802021000754$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>230,314,776,780,881,3537,27901,27902,65306</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33730626$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Nguyen, Kevin P.</creatorcontrib><creatorcontrib>Raval, Vyom</creatorcontrib><creatorcontrib>Treacher, Alex</creatorcontrib><creatorcontrib>Mellema, Cooper</creatorcontrib><creatorcontrib>Yu, Fang Frank</creatorcontrib><creatorcontrib>Pinho, Marco C.</creatorcontrib><creatorcontrib>Subramaniam, Rathan M.</creatorcontrib><creatorcontrib>Dewey, Richard B.</creatorcontrib><creatorcontrib>Montillo, Albert A.</creatorcontrib><title>Predicting Parkinson's disease trajectory using clinical and neuroimaging baseline measures</title><title>Parkinsonism & related disorders</title><addtitle>Parkinsonism Relat Disord</addtitle><description>Predictive biomarkers of Parkinson's Disease progression are needed to expedite neuroprotective treatment development and facilitate prognoses for patients. This work uses measures derived from resting-state functional magnetic resonance imaging, including regional homogeneity (ReHo) and fractional amplitude of low frequency fluctuations (fALFF), to predict an individual's current and future severity over up to 4 years and to elucidate the most prognostic brain regions.
ReHo and fALFF are measured for 82 Parkinson's Disease subjects and used to train machine learning predictors of baseline clinical and future severity at 1 year, 2 years, and 4 years follow-up as measured by the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Predictive performance is measured with nested cross-validation, validated on an external dataset, and again validated through leave-one-site-out cross-validation. Important predictive features are identified.
The models explain up to 30.4% of the variance in current MDS-UPDRS scores, 55.8% of the variance in year 1 scores, and 47.1% of the variance in year 2 scores (p < 0.0001). For distinguishing high and low-severity individuals at each timepoint (MDS-UPDRS score above or below the median, respectively), the models achieve positive predictive values up to 79% and negative predictive values up to 80%. Higher ReHo and fALFF in several regions, including components of the default motor network, predicted lower severity across current and future timepoints.
These results identify an accurate prognostic neuroimaging biomarker which may be used to better inform enrollment in trials of neuroprotective treatments and enable physicians to counsel their patients.
•Biomarkers of Parkinson's Disease severity and future trajectory are needed.•Regional brain activity and homogeneity were measured from resting functional MRI.•Machine learning models were trained to predict disease severity from this data.•Both current and future severity were predicted reproducibly across datasets.•Several brain regions, such as the default mode network, were important predictors.</description><subject>Aged</subject><subject>Biomarkers</subject><subject>Cerebellum - diagnostic imaging</subject><subject>Cerebellum - physiopathology</subject><subject>Cerebral Cortex - diagnostic imaging</subject><subject>Cerebral Cortex - physiopathology</subject><subject>Default Mode Network - diagnostic imaging</subject><subject>Default Mode Network - physiopathology</subject><subject>Disease Progression</subject><subject>Female</subject><subject>Follow-Up Studies</subject><subject>Functional MRI</subject><subject>Functional Neuroimaging - standards</subject><subject>Humans</subject><subject>Machine Learning</subject><subject>Magnetic Resonance Imaging - standards</subject><subject>Male</subject><subject>Middle Aged</subject><subject>Nerve Net - diagnostic imaging</subject><subject>Nerve Net - physiopathology</subject><subject>Neuroimaging</subject><subject>Parkinson Disease - diagnosis</subject><subject>Parkinson Disease - physiopathology</subject><subject>Parkinson's disease</subject><subject>Prognosis</subject><subject>Reproducibility of Results</subject><subject>Severity of Illness Index</subject><issn>1353-8020</issn><issn>1873-5126</issn><issn>1873-5126</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNqFkUlLBDEQhYMo7n9B-qaXHrNML7kIKm4g6EFPHkI6qR4z9iRj0i34761mXE9CQQLvq1eVPEIyRieMsvJ4Plnq-BKhsy5NOOVsQjlWuUa2WV2JvGC8XMe7KEReU063yE5Kc0ppVVCxSbaEqAQteblNnu4jWGd652fZPXo6n4I_TBkag06Q9VHPwfQhvmdDGiHTOe-M7jLtbeZhiMEt9GxUGuRRhGyBnUOEtEc2Wt0l2P88d8nj5cXD-XV-e3d1c356m5tpJftcNmAL2wpeccNtI6UoAGRrbaEbBqZpwTaWidLK6RRfh6ylDdfSQMGYLluxS05WvsuhWYA14HHrTi0jbhbfVdBO_VW8e1az8KZqxishBRocfRrE8DpA6tXCJQNdpz2EISleUF5TKfiI1ivUxJBShPZ7DKNqzEbN1U82asxGUY5VYuvB7zW_G7_CQOBsBQB-1puDqJJx4A0GFDEDZYP7f8oH15yqLA</recordid><startdate>20210401</startdate><enddate>20210401</enddate><creator>Nguyen, Kevin P.</creator><creator>Raval, Vyom</creator><creator>Treacher, Alex</creator><creator>Mellema, Cooper</creator><creator>Yu, Fang Frank</creator><creator>Pinho, Marco C.</creator><creator>Subramaniam, Rathan M.</creator><creator>Dewey, Richard B.</creator><creator>Montillo, Albert A.</creator><general>Elsevier Ltd</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0001-8401-8889</orcidid></search><sort><creationdate>20210401</creationdate><title>Predicting Parkinson's disease trajectory using clinical and neuroimaging baseline measures</title><author>Nguyen, Kevin P. ; Raval, Vyom ; Treacher, Alex ; Mellema, Cooper ; Yu, Fang Frank ; Pinho, Marco C. ; Subramaniam, Rathan M. ; Dewey, Richard B. ; Montillo, Albert A.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c479t-9bed5df3272c2db9935ee9fdd5ab1ecbfedbd136d944187d5dd0b2a9ce511a6f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Aged</topic><topic>Biomarkers</topic><topic>Cerebellum - diagnostic imaging</topic><topic>Cerebellum - physiopathology</topic><topic>Cerebral Cortex - diagnostic imaging</topic><topic>Cerebral Cortex - physiopathology</topic><topic>Default Mode Network - diagnostic imaging</topic><topic>Default Mode Network - physiopathology</topic><topic>Disease Progression</topic><topic>Female</topic><topic>Follow-Up Studies</topic><topic>Functional MRI</topic><topic>Functional Neuroimaging - standards</topic><topic>Humans</topic><topic>Machine Learning</topic><topic>Magnetic Resonance Imaging - standards</topic><topic>Male</topic><topic>Middle Aged</topic><topic>Nerve Net - diagnostic imaging</topic><topic>Nerve Net - physiopathology</topic><topic>Neuroimaging</topic><topic>Parkinson Disease - diagnosis</topic><topic>Parkinson Disease - physiopathology</topic><topic>Parkinson's disease</topic><topic>Prognosis</topic><topic>Reproducibility of Results</topic><topic>Severity of Illness Index</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Nguyen, Kevin P.</creatorcontrib><creatorcontrib>Raval, Vyom</creatorcontrib><creatorcontrib>Treacher, Alex</creatorcontrib><creatorcontrib>Mellema, Cooper</creatorcontrib><creatorcontrib>Yu, Fang Frank</creatorcontrib><creatorcontrib>Pinho, Marco C.</creatorcontrib><creatorcontrib>Subramaniam, Rathan M.</creatorcontrib><creatorcontrib>Dewey, Richard B.</creatorcontrib><creatorcontrib>Montillo, Albert A.</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Parkinsonism & related disorders</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Nguyen, Kevin P.</au><au>Raval, Vyom</au><au>Treacher, Alex</au><au>Mellema, Cooper</au><au>Yu, Fang Frank</au><au>Pinho, Marco C.</au><au>Subramaniam, Rathan M.</au><au>Dewey, Richard B.</au><au>Montillo, Albert A.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Predicting Parkinson's disease trajectory using clinical and neuroimaging baseline measures</atitle><jtitle>Parkinsonism & related disorders</jtitle><addtitle>Parkinsonism Relat Disord</addtitle><date>2021-04-01</date><risdate>2021</risdate><volume>85</volume><spage>44</spage><epage>51</epage><pages>44-51</pages><issn>1353-8020</issn><issn>1873-5126</issn><eissn>1873-5126</eissn><abstract>Predictive biomarkers of Parkinson's Disease progression are needed to expedite neuroprotective treatment development and facilitate prognoses for patients. This work uses measures derived from resting-state functional magnetic resonance imaging, including regional homogeneity (ReHo) and fractional amplitude of low frequency fluctuations (fALFF), to predict an individual's current and future severity over up to 4 years and to elucidate the most prognostic brain regions.
ReHo and fALFF are measured for 82 Parkinson's Disease subjects and used to train machine learning predictors of baseline clinical and future severity at 1 year, 2 years, and 4 years follow-up as measured by the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Predictive performance is measured with nested cross-validation, validated on an external dataset, and again validated through leave-one-site-out cross-validation. Important predictive features are identified.
The models explain up to 30.4% of the variance in current MDS-UPDRS scores, 55.8% of the variance in year 1 scores, and 47.1% of the variance in year 2 scores (p < 0.0001). For distinguishing high and low-severity individuals at each timepoint (MDS-UPDRS score above or below the median, respectively), the models achieve positive predictive values up to 79% and negative predictive values up to 80%. Higher ReHo and fALFF in several regions, including components of the default motor network, predicted lower severity across current and future timepoints.
These results identify an accurate prognostic neuroimaging biomarker which may be used to better inform enrollment in trials of neuroprotective treatments and enable physicians to counsel their patients.
•Biomarkers of Parkinson's Disease severity and future trajectory are needed.•Regional brain activity and homogeneity were measured from resting functional MRI.•Machine learning models were trained to predict disease severity from this data.•Both current and future severity were predicted reproducibly across datasets.•Several brain regions, such as the default mode network, were important predictors.</abstract><cop>England</cop><pub>Elsevier Ltd</pub><pmid>33730626</pmid><doi>10.1016/j.parkreldis.2021.02.026</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0001-8401-8889</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1353-8020 |
| ispartof | Parkinsonism & related disorders, 2021-04, Vol.85, p.44-51 |
| issn | 1353-8020 1873-5126 1873-5126 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8127393 |
| source | MEDLINE; Elsevier ScienceDirect Journals |
| subjects | Aged Biomarkers Cerebellum - diagnostic imaging Cerebellum - physiopathology Cerebral Cortex - diagnostic imaging Cerebral Cortex - physiopathology Default Mode Network - diagnostic imaging Default Mode Network - physiopathology Disease Progression Female Follow-Up Studies Functional MRI Functional Neuroimaging - standards Humans Machine Learning Magnetic Resonance Imaging - standards Male Middle Aged Nerve Net - diagnostic imaging Nerve Net - physiopathology Neuroimaging Parkinson Disease - diagnosis Parkinson Disease - physiopathology Parkinson's disease Prognosis Reproducibility of Results Severity of Illness Index |
| title | Predicting Parkinson's disease trajectory using clinical and neuroimaging baseline measures |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T04%3A29%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Predicting%20Parkinson's%20disease%20trajectory%20using%20clinical%20and%20neuroimaging%20baseline%20measures&rft.jtitle=Parkinsonism%20&%20related%20disorders&rft.au=Nguyen,%20Kevin%20P.&rft.date=2021-04-01&rft.volume=85&rft.spage=44&rft.epage=51&rft.pages=44-51&rft.issn=1353-8020&rft.eissn=1873-5126&rft_id=info:doi/10.1016/j.parkreldis.2021.02.026&rft_dat=%3Cproquest_pubme%3E2502809323%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2502809323&rft_id=info:pmid/33730626&rft_els_id=S1353802021000754&rfr_iscdi=true |