A Novel Machine Learning Algorithm Predicts Dementia With Lewy Bodies Versus Parkinson's Disease Dementia Based on Clinical and Neuropsychological Scores
Our aim was to develop a machine learning algorithm based only on non-invasively clinic collectable predictors, for the accurate diagnosis of these disorders. This is an ongoing prospective cohort study (ClinicalTrials.gov identifier NCT number NCT04448340) of 78 PDD and 62 DLB subjects whose diagno...
Gespeichert in:
| Veröffentlicht in: | Journal of geriatric psychiatry and neurology Jg. 35; H. 3; S. 317 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
United States
01.05.2022
|
| Schlagworte: | |
| ISSN: | 0891-9887 |
| Online-Zugang: | Weitere Angaben |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Our aim was to develop a machine learning algorithm based only on non-invasively clinic collectable predictors, for the accurate diagnosis of these disorders.
This is an ongoing prospective cohort study (ClinicalTrials.gov identifier NCT number NCT04448340) of 78 PDD and 62 DLB subjects whose diagnostic follow-up is available for at least 3 years after the baseline assessment. We used predictors such as clinico-demographic characteristics, 6 neuropsychological tests (mini mental, PD Cognitive Rating Scale, Brief Visuospatial Memory test, Symbol digit written, Wechsler adult intelligence scale, trail making A and B). We investigated logistic regression, K-Nearest Neighbors (K-NNs) Support Vector Machine (SVM), Naïve Bayes classifier, and Ensemble Model for their ability to predict successfully PDD or DLB diagnosis.
The K-NN classification model had an accuracy 91.2% of overall cases based on 15 best clinical and cognitive scores achieving 96.42% sensitivity and 81% specificity on discriminating between DLB and PDD. The binomial logistic regression classification model achieved an accuracy of 87.5% based on 15 best features, showing 93.93% sensitivity and 87% specificity. The SVM classification model had an accuracy 84.6% of overall cases based on 15 best features achieving 90.62% sensitivity and 78.58% specificity. A model created on Naïve Bayes classification had 82.05% accuracy, 93.10% sensitivity and 74.41% specificity. Finally, an Ensemble model, synthesized by the individual ones, achieved 89.74% accuracy, 93.75% sensitivity and 85.73% specificity.
Machine learning method predicted with high accuracy, sensitivity and specificity PDD or DLB diagnosis based on non-invasively and easily in-the-clinic and neuropsychological tests. |
|---|---|
| AbstractList | Our aim was to develop a machine learning algorithm based only on non-invasively clinic collectable predictors, for the accurate diagnosis of these disorders.OBJECTIVEOur aim was to develop a machine learning algorithm based only on non-invasively clinic collectable predictors, for the accurate diagnosis of these disorders.This is an ongoing prospective cohort study (ClinicalTrials.gov identifier NCT number NCT04448340) of 78 PDD and 62 DLB subjects whose diagnostic follow-up is available for at least 3 years after the baseline assessment. We used predictors such as clinico-demographic characteristics, 6 neuropsychological tests (mini mental, PD Cognitive Rating Scale, Brief Visuospatial Memory test, Symbol digit written, Wechsler adult intelligence scale, trail making A and B). We investigated logistic regression, K-Nearest Neighbors (K-NNs) Support Vector Machine (SVM), Naïve Bayes classifier, and Ensemble Model for their ability to predict successfully PDD or DLB diagnosis.METHODSThis is an ongoing prospective cohort study (ClinicalTrials.gov identifier NCT number NCT04448340) of 78 PDD and 62 DLB subjects whose diagnostic follow-up is available for at least 3 years after the baseline assessment. We used predictors such as clinico-demographic characteristics, 6 neuropsychological tests (mini mental, PD Cognitive Rating Scale, Brief Visuospatial Memory test, Symbol digit written, Wechsler adult intelligence scale, trail making A and B). We investigated logistic regression, K-Nearest Neighbors (K-NNs) Support Vector Machine (SVM), Naïve Bayes classifier, and Ensemble Model for their ability to predict successfully PDD or DLB diagnosis.The K-NN classification model had an accuracy 91.2% of overall cases based on 15 best clinical and cognitive scores achieving 96.42% sensitivity and 81% specificity on discriminating between DLB and PDD. The binomial logistic regression classification model achieved an accuracy of 87.5% based on 15 best features, showing 93.93% sensitivity and 87% specificity. The SVM classification model had an accuracy 84.6% of overall cases based on 15 best features achieving 90.62% sensitivity and 78.58% specificity. A model created on Naïve Bayes classification had 82.05% accuracy, 93.10% sensitivity and 74.41% specificity. Finally, an Ensemble model, synthesized by the individual ones, achieved 89.74% accuracy, 93.75% sensitivity and 85.73% specificity.RESULTSThe K-NN classification model had an accuracy 91.2% of overall cases based on 15 best clinical and cognitive scores achieving 96.42% sensitivity and 81% specificity on discriminating between DLB and PDD. The binomial logistic regression classification model achieved an accuracy of 87.5% based on 15 best features, showing 93.93% sensitivity and 87% specificity. The SVM classification model had an accuracy 84.6% of overall cases based on 15 best features achieving 90.62% sensitivity and 78.58% specificity. A model created on Naïve Bayes classification had 82.05% accuracy, 93.10% sensitivity and 74.41% specificity. Finally, an Ensemble model, synthesized by the individual ones, achieved 89.74% accuracy, 93.75% sensitivity and 85.73% specificity.Machine learning method predicted with high accuracy, sensitivity and specificity PDD or DLB diagnosis based on non-invasively and easily in-the-clinic and neuropsychological tests.CONCLUSIONMachine learning method predicted with high accuracy, sensitivity and specificity PDD or DLB diagnosis based on non-invasively and easily in-the-clinic and neuropsychological tests. Our aim was to develop a machine learning algorithm based only on non-invasively clinic collectable predictors, for the accurate diagnosis of these disorders. This is an ongoing prospective cohort study (ClinicalTrials.gov identifier NCT number NCT04448340) of 78 PDD and 62 DLB subjects whose diagnostic follow-up is available for at least 3 years after the baseline assessment. We used predictors such as clinico-demographic characteristics, 6 neuropsychological tests (mini mental, PD Cognitive Rating Scale, Brief Visuospatial Memory test, Symbol digit written, Wechsler adult intelligence scale, trail making A and B). We investigated logistic regression, K-Nearest Neighbors (K-NNs) Support Vector Machine (SVM), Naïve Bayes classifier, and Ensemble Model for their ability to predict successfully PDD or DLB diagnosis. The K-NN classification model had an accuracy 91.2% of overall cases based on 15 best clinical and cognitive scores achieving 96.42% sensitivity and 81% specificity on discriminating between DLB and PDD. The binomial logistic regression classification model achieved an accuracy of 87.5% based on 15 best features, showing 93.93% sensitivity and 87% specificity. The SVM classification model had an accuracy 84.6% of overall cases based on 15 best features achieving 90.62% sensitivity and 78.58% specificity. A model created on Naïve Bayes classification had 82.05% accuracy, 93.10% sensitivity and 74.41% specificity. Finally, an Ensemble model, synthesized by the individual ones, achieved 89.74% accuracy, 93.75% sensitivity and 85.73% specificity. Machine learning method predicted with high accuracy, sensitivity and specificity PDD or DLB diagnosis based on non-invasively and easily in-the-clinic and neuropsychological tests. |
| Author | Efthymiopoulou, Efthymia Zikos, Panagiotis Bougea, Anastasia Spanou, Ioanna |
| Author_xml | – sequence: 1 givenname: Anastasia orcidid: 0000-0003-3006-8711 surname: Bougea fullname: Bougea, Anastasia organization: First Department of Neurology, National and Kapodistrian University, Aiginition Hospital, Athens, Greece – sequence: 2 givenname: Efthymia surname: Efthymiopoulou fullname: Efthymiopoulou, Efthymia organization: Maison Sofos Elderly Care Unit, Athens, Greece – sequence: 3 givenname: Ioanna orcidid: 0000-0002-1743-9648 surname: Spanou fullname: Spanou, Ioanna organization: 251 General Air-Force Hospital, Athens, Greece – sequence: 4 givenname: Panagiotis surname: Zikos fullname: Zikos, Panagiotis organization: 251 General Air-Force Hospital, Athens, Greece |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/33550890$$D View this record in MEDLINE/PubMed |
| BookMark | eNpFkLtOAzEQRV0EkQf0VMgdNAv2PmK7TMJTCiESr3LleGcTg9cO9i4on8LfsoEgqtGce2aK20cd6ywgdETJGaWMnRMuqOCcxVSIJMuGHdTbomjLuqgfwishJBM82UfdpBXakPTQ1wjP3AcYfCfVSlvAU5DearvEI7N0XterCs89FFrVAV9ABbbWEr-0vDU_N3jsCg0BP4MPTcBz6d-0Dc6etLIOIAP8H43brcDO4onRVitpsLQFnkHj3Tps1MoZt_zBD8p5CAdor5QmwOFuDtDT1eXj5Caa3l_fTkbTSCUJqyMqSshIKYCylBeCLdKyTHmsYi4TAkJRDtlwUfKEUkIKUGqYykK1LZWExTwt4wE6_f279u69gVDnlQ4KjJEWXBPyOOUsTTKWsVY93qnNooIiX3tdSb_J_-qMvwE65nj4 |
| CitedBy_id | crossref_primary_10_1371_journal_pone_0303644 crossref_primary_10_2196_42637 crossref_primary_10_3389_fncom_2022_865805 crossref_primary_10_3390_bioengineering9080370 crossref_primary_10_1159_000547180 crossref_primary_10_1016_j_arr_2024_102417 crossref_primary_10_3390_jpm12010037 crossref_primary_10_1088_1742_6596_2571_1_012022 crossref_primary_10_3390_cells13231965 crossref_primary_10_7759_cureus_47004 crossref_primary_10_1007_s10916_023_01906_7 crossref_primary_10_1111_jnp_70009 crossref_primary_10_1007_s40031_025_01259_4 crossref_primary_10_1080_13854046_2025_2513446 |
| ContentType | Journal Article |
| DBID | CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1177/0891988721993556 |
| DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Medicine |
| ExternalDocumentID | 33550890 |
| Genre | Journal Article |
| GroupedDBID | --- -TM -~X .2E .2F .2G .2J .2N .GJ 01A 0R~ 18M 1~K 29K 31R 31S 31U 31X 31Y 31Z 39C 4.4 53G 54M 5GY 5RE 5VS AABMB AABOD AACKU AACMV AACTG AADUE AAEJI AAEWN AAGGD AAGLT AAGMC AAJIQ AAJOX AAJPV AAKGS AANSI AAPEO AAPII AAQDB AAQXH AAQXI AARDL AARIX AATAA AATBZ AAUAS AAWTL AAXOT AAYTG AAZBJ ABAWC ABAWP ABCCA ABCJG ABDWY ABEIX ABFWQ ABHKI ABHQH ABIDT ABIVO ABJIS ABJNI ABJZC ABKRH ABLUO ABNCE ABPGX ABPNF ABQKF ABQXT ABRHV ABUJY ABVFX ABVVC ABYTW ACARO ACDSZ ACDXX ACFEJ ACFMA ACFYK ACGBL ACGFO ACGFS ACGZU ACJER ACJTF ACLFY ACLHI ACLZU ACNXM ACOFE ACOXC ACROE ACRPL ACSIQ ACUAV ACUIR ACXKE ACXMB ADBBV ADDLC ADEBD ADEIA ADMPF ADNBR ADNMO ADNON ADRRZ ADSTG ADTBJ ADUKL ADVBO ADYCS ADZYD ADZZY AECGH AECVZ AEDTQ AEKYL AENEX AEPTA AEQLS AERKM AESZF AEUHG AEWDL AEWHI AEXFG AEXNY AFEET AFKBI AFKRG AFMOU AFQAA AFUIA AFVCE AFWMB AGHKR AGKLV AGNHF AGPXR AGQPQ AGWFA AGWNL AHDMH AHHFK AHMBA AIGRN AJABX AJEFB AJGYC AJMMQ AJSCY AJUZI AJVBE AJXAJ AJXGE ALKWR ALMA_UNASSIGNED_HOLDINGS AMCVQ ANDLU ARTOV ASPBG AUTPY AUVAJ AVWKF AYAKG AZFZN B3H B8M B8O B8R B8Z B93 B94 BBRGL BDDNI BKIIM BKSCU BPACV BSEHC BWJAD BYIEH C45 CAG CBRKF CDWPY CFDXU CGR COF CORYS CQQTX CS3 CUTAK CUY CVF D-I DB0 DC- DC. DC0 DD- DD0 DE- DF0 DO- DOPDO DU5 DV7 DV9 D~Y EBS ECM EIF EJD EMOBN EX3 F5P FEDTE FHBDP GROUPED_SAGE_PREMIER_JOURNAL_COLLECTION H13 HF~ HVGLF HZ~ IAO ICQ IEA IHR J8X K.F K.J N9A NPM O9- OVD P.B P2P PQQKQ Q1R Q7K Q7L Q7R Q7U Q7X Q82 Q83 ROL RWL RXW S01 SASJQ SAUOL SBI SCNPE SDB SFB SFC SFK SFT SGA SGO SGP SGR SGV SGX SGZ SHG SNB SPJ SPP SPQ SPV SQCSI STM TAE TEORI WOW ZONMY ZPPRI ZRKOI ZSSAH 7X8 AJHME |
| ID | FETCH-LOGICAL-c337t-19fe50f9e1748d97b4ff482c28a30e9c18e56bf831100decc64adc721f07284f2 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 12 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000619970100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0891-9887 |
| IngestDate | Thu Oct 02 04:24:47 EDT 2025 Mon Jul 21 05:29:05 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Keywords | K-nearest neighbors (K-NNs) dementia with Lewy bodies (DLB) machine learning Parkinson’s disease dementia (PDD) |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c337t-19fe50f9e1748d97b4ff482c28a30e9c18e56bf831100decc64adc721f07284f2 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0003-3006-8711 0000-0002-1743-9648 |
| PMID | 33550890 |
| PQID | 2487435757 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2487435757 pubmed_primary_33550890 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-May 20220501 |
| PublicationDateYYYYMMDD | 2022-05-01 |
| PublicationDate_xml | – month: 05 year: 2022 text: 2022-May |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Journal of geriatric psychiatry and neurology |
| PublicationTitleAlternate | J Geriatr Psychiatry Neurol |
| PublicationYear | 2022 |
| SSID | ssj0005983 |
| Score | 2.4054306 |
| Snippet | Our aim was to develop a machine learning algorithm based only on non-invasively clinic collectable predictors, for the accurate diagnosis of these disorders.... Our aim was to develop a machine learning algorithm based only on non-invasively clinic collectable predictors, for the accurate diagnosis of these... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | 317 |
| SubjectTerms | Algorithms Alzheimer Disease - diagnosis Bayes Theorem Dementia Humans Lewy Body Disease - diagnosis Machine Learning Neuropsychological Tests Parkinson Disease - diagnosis Prospective Studies |
| Title | A Novel Machine Learning Algorithm Predicts Dementia With Lewy Bodies Versus Parkinson's Disease Dementia Based on Clinical and Neuropsychological Scores |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/33550890 https://www.proquest.com/docview/2487435757 |
| Volume | 35 |
| WOSCitedRecordID | wos000619970100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1La8MwDDZ7MXbZ-_1Ag8FOYU2cxPFpdI-yS0thG-utuI7cFbqka7qN_ZT928lOSncZDHYJWMghWJKtSPInxs5iLbkiOXtchbEX-iQLKUzkIUcuUWOgpXLNJkSrlXQ6sl0F3IqqrHK6J7qNOs21jZFfBORZ09EuInE5evVs1yibXa1aaMyzRU6ujNVq0ZmhhUeyhOFMpO9JsqZZmvLC0iwpsAVsURT_7mC6g6ax9t9PXGerlYsJ9VInNtgcZptsuVkl0bfYVx1a-TsOoekKKREqjNU-1Id9et_k-QXaY8s-KeDGhQ8HCp6ITpwfn3CV28pDsJG2twLstWl3g-ycmMtsz2zSFY1SyDOo4EeHoLIUHCDI6OfOC_cWTbPYZo-N24frO6_q0OBpzsXE86XBqGYk0n9NkkrRC40Jk0AHieI1lNpPMIp7JuEWmC4lbYlDlWpadFMTdC6aYIctZHmGewwUkYTBtKeVCRUPejH6KFUYKmUx69J9djpd9C5ZgE1rqAzzt6I7W_Z9tltKrjsqoTq6nGRLoq4d_GH2IVsJ7N0GV814xBYN2T8esyX9PhkU4xOnWvRstZvfffTa5A |
| linkProvider | ProQuest |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+Novel+Machine+Learning+Algorithm+Predicts+Dementia+With+Lewy+Bodies+Versus+Parkinson%27s+Disease+Dementia+Based+on+Clinical+and+Neuropsychological+Scores&rft.jtitle=Journal+of+geriatric+psychiatry+and+neurology&rft.au=Bougea%2C+Anastasia&rft.au=Efthymiopoulou%2C+Efthymia&rft.au=Spanou%2C+Ioanna&rft.au=Zikos%2C+Panagiotis&rft.date=2022-05-01&rft.issn=0891-9887&rft.volume=35&rft.issue=3&rft.spage=317&rft_id=info:doi/10.1177%2F0891988721993556&rft_id=info%3Apmid%2F33550890&rft_id=info%3Apmid%2F33550890&rft.externalDocID=33550890 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0891-9887&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0891-9887&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0891-9887&client=summon |