Medical Informatics Platform (MIP): A Pilot Study Across Clinical Italian Cohorts
Introduction: With the shift of research focus to personalized medicine in Alzheimer's Dementia (AD), there is an urgent need for tools that are capable of quantifying a patient's risk using diagnostic biomarkers. The Medical Informatics Platform (MIP) is a distributed e-infrastructure fed...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-09-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fneur.2020.01021/full |
| _version_ | 1818967914088235008 |
|---|---|
| author | Alberto Redolfi Silvia De Francesco Silvia De Francesco Fulvia Palesi Fulvia Palesi Samantha Galluzzi Cristina Muscio Gloria Castellazzi Gloria Castellazzi Gloria Castellazzi Pietro Tiraboschi Giovanni Savini Anna Nigri Gabriella Bottini Maria Grazia Bruzzone Matteo Cotta Ramusino Matteo Cotta Ramusino Stefania Ferraro Claudia A. M. Gandini Wheeler-Kingshott Claudia A. M. Gandini Wheeler-Kingshott Claudia A. M. Gandini Wheeler-Kingshott Fabrizio Tagliavini Giovanni B. Frisoni Giovanni B. Frisoni Philippe Ryvlin Jean-François Demonet Ferath Kherif Stefano F. Cappa Stefano F. Cappa Egidio D'Angelo Egidio D'Angelo |
| author_facet | Alberto Redolfi Silvia De Francesco Silvia De Francesco Fulvia Palesi Fulvia Palesi Samantha Galluzzi Cristina Muscio Gloria Castellazzi Gloria Castellazzi Gloria Castellazzi Pietro Tiraboschi Giovanni Savini Anna Nigri Gabriella Bottini Maria Grazia Bruzzone Matteo Cotta Ramusino Matteo Cotta Ramusino Stefania Ferraro Claudia A. M. Gandini Wheeler-Kingshott Claudia A. M. Gandini Wheeler-Kingshott Claudia A. M. Gandini Wheeler-Kingshott Fabrizio Tagliavini Giovanni B. Frisoni Giovanni B. Frisoni Philippe Ryvlin Jean-François Demonet Ferath Kherif Stefano F. Cappa Stefano F. Cappa Egidio D'Angelo Egidio D'Angelo |
| author_sort | Alberto Redolfi |
| collection | DOAJ |
| description | Introduction: With the shift of research focus to personalized medicine in Alzheimer's Dementia (AD), there is an urgent need for tools that are capable of quantifying a patient's risk using diagnostic biomarkers. The Medical Informatics Platform (MIP) is a distributed e-infrastructure federating large amounts of data coupled with machine-learning (ML) algorithms and statistical models to define the biological signature of the disease. The present study assessed (i) the accuracy of two ML algorithms, i.e., supervised Gradient Boosting (GB) and semi-unsupervised 3C strategy (Categorize, Cluster, Classify—CCC) implemented in the MIP and (ii) their contribution over the standard diagnostic workup.Methods: We examined individuals coming from the MIP installed across 3 Italian memory clinics, including subjects with Normal Cognition (CN, n = 432), Mild Cognitive Impairment (MCI, n = 456), and AD (n = 451). The GB classifier was applied to best discriminate the three diagnostic classes in 1,339 subjects, and the CCC strategy was used to refine the classical disease categories. Four dementia experts provided their diagnostic confidence (DC) of MCI conversion on an independent cohort of 38 patients. DC was based on clinical, neuropsychological, CSF, and structural MRI information and again with addition of the outcome from the MIP tools.Results: The GB algorithm provided a classification accuracy of 85% in a nested 10-fold cross-validation for CN vs. MCI vs. AD discrimination. Accuracy increased to 95% in the holdout validation, with the omission of each Italian clinical cohort out in turn. CCC identified five homogeneous clusters of subjects and 36 biomarkers that represented the disease fingerprint. In the DC assessment, CCC defined six clusters in the MCI population used to train the algorithm and 29 biomarkers to improve patients staging. GB and CCC showed a significant impact, evaluated as +5.99% of increment on physicians' DC. The influence of MIP on DC was rated from “slight” to “significant” in 80% of the cases.Discussion: GB provided fair results in classification of CN, MCI, and AD. CCC identified homogeneous and promising classes of subjects via its semi-unsupervised approach. We measured the effect of the MIP on the physician's DC. Our results pave the way for the establishment of a new paradigm for ML discrimination of patients who will or will not convert to AD, a clinical priority for neurology. |
| first_indexed | 2024-12-20T13:56:22Z |
| format | Article |
| id | doaj.art-745fd21d6133415188340b5f95e4083c |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-12-20T13:56:22Z |
| publishDate | 2020-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-745fd21d6133415188340b5f95e4083c2022-12-21T19:38:26ZengFrontiers Media S.A.Frontiers in Neurology1664-22952020-09-011110.3389/fneur.2020.01021538781Medical Informatics Platform (MIP): A Pilot Study Across Clinical Italian CohortsAlberto Redolfi0Silvia De Francesco1Silvia De Francesco2Fulvia Palesi3Fulvia Palesi4Samantha Galluzzi5Cristina Muscio6Gloria Castellazzi7Gloria Castellazzi8Gloria Castellazzi9Pietro Tiraboschi10Giovanni Savini11Anna Nigri12Gabriella Bottini13Maria Grazia Bruzzone14Matteo Cotta Ramusino15Matteo Cotta Ramusino16Stefania Ferraro17Claudia A. M. Gandini Wheeler-Kingshott18Claudia A. M. Gandini Wheeler-Kingshott19Claudia A. M. Gandini Wheeler-Kingshott20Fabrizio Tagliavini21Giovanni B. Frisoni22Giovanni B. Frisoni23Philippe Ryvlin24Jean-François Demonet25Ferath Kherif26Stefano F. Cappa27Stefano F. Cappa28Egidio D'Angelo29Egidio D'Angelo30Laboratory of Neuroinformatics, IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli, Brescia, ItalyLaboratory of Neuroinformatics, IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli, Brescia, ItalyLaboratory of Alzheimer's Neuroimaging and Epidemiology - LANE, IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli, Brescia, ItalyDepartment of Brain and Behavioral Sciences, University of Pavia, Pavia, ItalyIRCCS Mondino Foundation, Pavia, ItalyLaboratory of Alzheimer's Neuroimaging and Epidemiology - LANE, IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli, Brescia, ItalyDivision of Neurology V/Neuropathology, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, ItalyIRCCS Mondino Foundation, Pavia, ItalyNMR Research Unit, Queen Square MS Center, Department of Neuroinflammation, UCL Institute of Neurology, London, United KingdomDepartment of Computer, Electrical and Biomedical Engineering, University of Pavia, Pavia, ItalyDivision of Neurology V/Neuropathology, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, ItalyIRCCS Mondino Foundation, Pavia, ItalyDepartment of Neuroradiology, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, ItalyNeuropsychology Center, ASST Grande Ospedale Metropolitano Niguarda, Milan, ItalyDepartment of Neuroradiology, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, ItalyIRCCS Mondino Foundation, Pavia, Italy0Memory Clinic and LANVIE - Laboratory of Neuroimaging of Aging, University Hospitals and University of Geneva, Geneva, SwitzerlandDepartment of Neuroradiology, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, ItalyDepartment of Brain and Behavioral Sciences, University of Pavia, Pavia, ItalyIRCCS Mondino Foundation, Pavia, ItalyNMR Research Unit, Queen Square MS Center, Department of Neuroinflammation, UCL Institute of Neurology, London, United KingdomDivision of Neurology V/Neuropathology, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, ItalyLaboratory of Alzheimer's Neuroimaging and Epidemiology - LANE, IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli, Brescia, Italy0Memory Clinic and LANVIE - Laboratory of Neuroimaging of Aging, University Hospitals and University of Geneva, Geneva, Switzerland1Department of Clinical Neurosciences, Leenaards Memory Center, Center Hospitalier Universitaire Vaudois and University of Lausanne, Lausanne, Switzerland1Department of Clinical Neurosciences, Leenaards Memory Center, Center Hospitalier Universitaire Vaudois and University of Lausanne, Lausanne, Switzerland1Department of Clinical Neurosciences, Leenaards Memory Center, Center Hospitalier Universitaire Vaudois and University of Lausanne, Lausanne, SwitzerlandIRCCS Mondino Foundation, Pavia, Italy2University School of Advanced Studies, Pavia, ItalyDepartment of Brain and Behavioral Sciences, University of Pavia, Pavia, ItalyIRCCS Mondino Foundation, Pavia, ItalyIntroduction: With the shift of research focus to personalized medicine in Alzheimer's Dementia (AD), there is an urgent need for tools that are capable of quantifying a patient's risk using diagnostic biomarkers. The Medical Informatics Platform (MIP) is a distributed e-infrastructure federating large amounts of data coupled with machine-learning (ML) algorithms and statistical models to define the biological signature of the disease. The present study assessed (i) the accuracy of two ML algorithms, i.e., supervised Gradient Boosting (GB) and semi-unsupervised 3C strategy (Categorize, Cluster, Classify—CCC) implemented in the MIP and (ii) their contribution over the standard diagnostic workup.Methods: We examined individuals coming from the MIP installed across 3 Italian memory clinics, including subjects with Normal Cognition (CN, n = 432), Mild Cognitive Impairment (MCI, n = 456), and AD (n = 451). The GB classifier was applied to best discriminate the three diagnostic classes in 1,339 subjects, and the CCC strategy was used to refine the classical disease categories. Four dementia experts provided their diagnostic confidence (DC) of MCI conversion on an independent cohort of 38 patients. DC was based on clinical, neuropsychological, CSF, and structural MRI information and again with addition of the outcome from the MIP tools.Results: The GB algorithm provided a classification accuracy of 85% in a nested 10-fold cross-validation for CN vs. MCI vs. AD discrimination. Accuracy increased to 95% in the holdout validation, with the omission of each Italian clinical cohort out in turn. CCC identified five homogeneous clusters of subjects and 36 biomarkers that represented the disease fingerprint. In the DC assessment, CCC defined six clusters in the MCI population used to train the algorithm and 29 biomarkers to improve patients staging. GB and CCC showed a significant impact, evaluated as +5.99% of increment on physicians' DC. The influence of MIP on DC was rated from “slight” to “significant” in 80% of the cases.Discussion: GB provided fair results in classification of CN, MCI, and AD. CCC identified homogeneous and promising classes of subjects via its semi-unsupervised approach. We measured the effect of the MIP on the physician's DC. Our results pave the way for the establishment of a new paradigm for ML discrimination of patients who will or will not convert to AD, a clinical priority for neurology.https://www.frontiersin.org/article/10.3389/fneur.2020.01021/fullAlzheimer's Dementia (AD)biomarkersdiagnostic confidenceMedical Informatics Platform (MIP)disease signature |
| spellingShingle | Alberto Redolfi Silvia De Francesco Silvia De Francesco Fulvia Palesi Fulvia Palesi Samantha Galluzzi Cristina Muscio Gloria Castellazzi Gloria Castellazzi Gloria Castellazzi Pietro Tiraboschi Giovanni Savini Anna Nigri Gabriella Bottini Maria Grazia Bruzzone Matteo Cotta Ramusino Matteo Cotta Ramusino Stefania Ferraro Claudia A. M. Gandini Wheeler-Kingshott Claudia A. M. Gandini Wheeler-Kingshott Claudia A. M. Gandini Wheeler-Kingshott Fabrizio Tagliavini Giovanni B. Frisoni Giovanni B. Frisoni Philippe Ryvlin Jean-François Demonet Ferath Kherif Stefano F. Cappa Stefano F. Cappa Egidio D'Angelo Egidio D'Angelo Medical Informatics Platform (MIP): A Pilot Study Across Clinical Italian Cohorts Frontiers in Neurology Alzheimer's Dementia (AD) biomarkers diagnostic confidence Medical Informatics Platform (MIP) disease signature |
| title | Medical Informatics Platform (MIP): A Pilot Study Across Clinical Italian Cohorts |
| title_full | Medical Informatics Platform (MIP): A Pilot Study Across Clinical Italian Cohorts |
| title_fullStr | Medical Informatics Platform (MIP): A Pilot Study Across Clinical Italian Cohorts |
| title_full_unstemmed | Medical Informatics Platform (MIP): A Pilot Study Across Clinical Italian Cohorts |
| title_short | Medical Informatics Platform (MIP): A Pilot Study Across Clinical Italian Cohorts |
| title_sort | medical informatics platform mip a pilot study across clinical italian cohorts |
| topic | Alzheimer's Dementia (AD) biomarkers diagnostic confidence Medical Informatics Platform (MIP) disease signature |
| url | https://www.frontiersin.org/article/10.3389/fneur.2020.01021/full |
| work_keys_str_mv | AT albertoredolfi medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT silviadefrancesco medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT silviadefrancesco medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT fulviapalesi medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT fulviapalesi medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT samanthagalluzzi medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT cristinamuscio medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT gloriacastellazzi medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT gloriacastellazzi medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT gloriacastellazzi medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT pietrotiraboschi medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT giovannisavini medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT annanigri medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT gabriellabottini medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT mariagraziabruzzone medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT matteocottaramusino medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT matteocottaramusino medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT stefaniaferraro medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT claudiaamgandiniwheelerkingshott medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT claudiaamgandiniwheelerkingshott medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT claudiaamgandiniwheelerkingshott medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT fabriziotagliavini medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT giovannibfrisoni medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT giovannibfrisoni medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT philipperyvlin medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT jeanfrancoisdemonet medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT ferathkherif medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT stefanofcappa medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT stefanofcappa medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT egidiodangelo medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts AT egidiodangelo medicalinformaticsplatformmipapilotstudyacrossclinicalitaliancohorts |