Search

Your search keyword '"Varoquaux, Gael"' showing total 8 results
Start Over Author "Varoquaux, Gael" Publisher hal ccsd
8 results on '"Varoquaux, Gael"'

1. International comparisons of laboratory values from the 4CE collaborative to predict COVID-19 mortality

Author

Weber, Griffin, Hong, Chuan, Xia, Zongqi, Palmer, Nathan, Avillach, Paul, L’yi, Sehi, Keller, Mark, Murphy, Shawn, Gutiérrez-Sacristán, Alba, Bonzel, Clara-Lea, Serret-Larmande, Arnaud, Neuraz, Antoine, Omenn, Gilbert, Visweswaran, Shyam, Klann, Jeffrey, South, Andrew, Loh, Ne Hooi Will, Cannataro, Mario, Beaulieu-Jones, Brett, Bellazzi, Riccardo, Agapito, Giuseppe, Alessiani, Mario, Aronow, Bruce, Bell, Douglas, Benoit, Vincent, Bourgeois, Florence, Chiovato, Luca, Cho, Kelly, Dagliati, Arianna, Duvall, Scott, Barrio, Noelia García, Hanauer, David, Ho, Yuk-Lam, Holmes, John, Issitt, Richard, Liu, Molei, Luo, Yuan, Lynch, Kristine, Maidlow, Sarah, Malovini, Alberto, Mandl, Kenneth, Mao, Chengsheng, Matheny, Michael, Moore, Jason, Morris, Jeffrey, Morris, Michele, Mowery, Danielle, Ngiam, Kee Yuan, Patel, Lav, Pedrera Jiménez, Miguel, Ramoni, Rachel, Schriver, Emily, Schubert, Petra, Balazote, Pablo Serrano, Spiridou, Anastasia, Tan, Amelia, Tan, Byorn, Tibollo, Valentina, Torti, Carlo, Trecarichi, Enrico, Wang, Xuan, Aaron, James, Albayrak, Adem, Albi, Giuseppe, Balshi, James, Alloni, Anna, Amendola, Danilo, Angoulvant, François, Anthony, Li, Ashraf, Fatima, Atz, Andrew, Azevedo, Paula, Bellasi, Antonio, Beraghi, Michele, Bernal-Sobrino, José Luis, Bernaux, Mélodie, Bey, Romain, Bhatnagar, Surbhi, Blanco-Martínez, Alvar, Boeker, Martin, Booth, John, Bosari, Silvano, Bradford, Robert, Brat, Gabriel, Bréant, Stéphane, Brown, Nicholas, Bruno, Raffaele, Bryant, William, Bucalo, Mauro, Bucholz, Emily, Burgun, Anita, Cai, Tianxi, Carmona, Aldo, Caucheteux, Charlotte, Champ, Julien, Chen, Krista, Chen, Jin, Chiudinelli, Lorenzo, Cimino, James, Colicchio, Tiago, Cormont, Sylvie, Cossin, Sébastien, Craig, Jean, Cruz-Bermúdez, Juan Luis, Cruz-Rojo, Jaime, Daniar, Mohamad, Daniel, Christel, Das, Priyam, Devkota, Batsal, Garmire, Lana, Dionne, Audrey, Duan, Rui, Dubiel, Julien, Esteve, Loic, Estiri, Hossein, Fan, Shirley, Follett, Robert, Ganslandt, Thomas, García-Barrio, Noelia, Gehlenborg, Nils, Getzen, Emily, Geva, Alon, Gradinger, Tobias, Gramfort, Alexandre, Griffier, Romain, Griffon, Nicolas, Grisel, Olivier, Han, Larry, Haverkamp, Christian, Key, Daniel, Hazard, Derek, He, Bing, Henderson, Darren, Hilka, Martin, Huling, Kenneth, Hutch, Meghan, Jannot, Anne Sophie, Jouhet, Vianney, Kavuluru, Ramakanth, Kennedy, Chris, Kernan, Kate, Kirchoff, Katie, Kohane, Isaac, Krantz, Ian, Kraska, Detlef, Krishnamurthy, Ashok, Le, Trang, Leblanc, Judith, Lemaitre, Guillaume, Lenert, Leslie, Leprovost, Damien, Long, Qi, Lozano-Zahonero, Sara, Mahmood, Sadiqa, Makoudjou, Adeline, Maram, Anupama, Martel, Patricia, Martins, Marcelo, Marwaha, Jayson, Masino, Aaron, Mazzitelli, Maria, Mensch, Arthur, Milano, Marianna, Minicucci, Marcos, Moal, Bertrand, Ahooyi, Taha Mohseni, Moraleda, Cinta, Moshal, Karyn, Mousavi, Sajad, Murad, Douglas, Naughton, Thomas, Neto, Carlos Tadeu Breda, Newburger, Jane, Njoroge, Wanjiku, Norman, James, Obeid, Jihad, Okoshi, Marina, Olson, Karen, Orlova, Nina, Ostasiewski, Brian, Paris, Nicolas, Pedrera-Jiménez, Miguel, Pfaff, Ashley, Pfaff, Emily, Pillion, Danielle, Pizzimenti, Sara, Prokosch, Hans, Prudente, Robson, Prunotto, Andrea, Quirós-González, Víctor, Raskin, Maryna, Rieg, Siegbert, Roig-Domínguez, Gustavo, Rojo, Pablo, Rubio-Mayo, Paula, Sacchi, Paolo, Sáez, Carlos, Salamanca, Elisa, Samayamuthu, Malarkodi Jebathilagam, Sanchez-Pinto, L. Nelson, Sandrin, Arnaud, Santhanam, Nandhini, Santos, Janaina, Sanz Vidorreta, Fernando, Savino, Maria, Schuettler, Juergen, Scudeller, Luigia, Sebire, Neil, Serrano-Balazote, Pablo, Serre, Patricia, Shah, Mohsin, Abad, Zahra Shakeri Hossein, Silvio, Domenick, Sliz, Piotr, Son, Jiyeon, Sonday, Charles, Sperotto, Francesca, Strasser, Zachary, Tan, Bryce, Tanni, Suzana, Taylor, Deanne, Terriza-Torres, Ana, Tippmann, Patric, Toh, Emma, Tseng, Yi-Ju, Vallejos, Andrew, Varoquaux, Gael, Vella, Margaret, Verdy, Guillaume, Vie, Jill-Jênn, Vitacca, Michele, Wagholikar, Kavishwar, Waitman, Lemuel, Wassermann, Demian, Wolkewitz, Martin, Wong, Scott, Xiong, Xin, Ye, Ye, Yehya, Nadir, Yuan, William, Zambelli, Alberto, Zhang, Harrison, Zöller, Daniela, Zuccaro, Valentina, Zucco, Chiara, Harvard Medical School [Boston] (HMS), University of Pittsburgh (PITT), Pennsylvania Commonwealth System of Higher Education (PCSHE), Massachusetts General Hospital [Boston], Centre de Recherche des Cordeliers (CRC (UMR_S_1138 / U1138)), École Pratique des Hautes Études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPCité), Service d'informatique médicale et biostatistiques [CHU Necker], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-CHU Necker - Enfants Malades [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Université Paris Cité (UPCité), Health data- and model- driven Knowledge Acquisition (HeKA), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de Recherche des Cordeliers (CRC (UMR_S_1138 / U1138)), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPCité)-École Pratique des Hautes Études (EPHE), University of Michigan [Ann Arbor], University of Michigan System, Wake Forest School of Medicine [Winston-Salem], Wake Forest Baptist Medical Center, National University Health System [Singapore] (NUHS), Università degli Studi 'Magna Graecia' di Catanzaro = University of Catanzaro (UMG), Università degli Studi di Pavia = University of Pavia (UNIPV), Istituti Clinici Scientifici Maugeri [Pavia] (IRCCS Pavia - ICS Maugeri), ASST Pavia, University of Cincinnati (UC), University of California [Los Angeles] (UCLA), University of California (UC), VA Boston Healthcare System, Hospital Universitario 12 de Octubre [Madrid], University of Pennsylvania, Great Ormond Street Hospital for Children [London] (GOSH), Harvard School of Public Health, Northwestern University [Chicago, Ill. USA], VA Salt Lake City Health Care System, Boston Children's Hospital, University of Kansas [Kansas City], and National University Hospital [Singapore] (NUH)

Subjects
Health Information Management, Medicine (miscellaneous), Health Informatics, [SDV.SPEE]Life Sciences [q-bio]/Santé publique et épidémiologie, Computer Science Applications
Abstract

Given the growing number of prediction algorithms developed to predict COVID-19 mortality, we evaluated the transportability of a mortality prediction algorithm using a multi-national network of healthcare systems. We predicted COVID-19 mortality using baseline commonly measured laboratory values and standard demographic and clinical covariates across healthcare systems, countries, and continents. Specifically, we trained a Cox regression model with nine measured laboratory test values, standard demographics at admission, and comorbidity burden pre-admission. These models were compared at site, country, and continent level. Of the 39,969 hospitalized patients with COVID-19 (68.6% male), 5717 (14.3%) died. In the Cox model, age, albumin, AST, creatine, CRP, and white blood cell count are most predictive of mortality. The baseline covariates are more predictive of mortality during the early days of COVID-19 hospitalization. Models trained at healthcare systems with larger cohort size largely retain good transportability performance when porting to different sites. The combination of routine laboratory test values at admission along with basic demographic features can predict mortality in patients hospitalized with COVID-19. Importantly, this potentially deployable model differs from prior work by demonstrating not only consistent performance but also reliable transportability across healthcare systems in the US and Europe, highlighting the generalizability of this model and the overall approach.

Published
2022

2. Predicting future cognitive decline from non-brain and multimodal brain imaging data in healthy and pathological aging

Author

Hebling Vieira, Bruno, Liem, Franziskus, Dadi, Kamalaker, Engemann, Denis A, Gramfort, Alexandre, Bellec, Pierre, Craddock, Richard Cameron, Damoiseaux, Jessica S, Steele, Christopher J, Yarkoni, Tal, Langer, Nicolas, Margulies, Daniel S, Varoquaux, Gael, Universität Zürich [Zürich] = University of Zurich (UZH), Modèles et inférence pour les données de Neuroimagerie (MIND), IFR49 - Neurospin - CEA, Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Université du Québec à Montréal = University of Québec in Montréal (UQAM), The University of Texas Medical Branch (UTMB), Wayne State University [Detroit], Concordia University [Montreal], The University of Texas Medical School at Houston, Centre de Recherche de l'Institut du Cerveau et de la Moelle épinière (CRICM), Université Pierre et Marie Curie - Paris 6 (UPMC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Méthodes computationnelles et mathématiques pour comprendre la société et la santé à partir de données (SODA), Inria Saclay - Ile de France, ANR-20-IADJ-0002,AI-cog,IA pour les sociétés touchées par le vieillissement: des concepts fondamentaux aux outils pratiques pour l'apprentissage cognitif facilité par l'IA(2020), University of Zurich, and Hebling Vieira, Bruno

Subjects
Aging, Neuroimaging, 2717 Geriatrics and Gerontology, [STAT.OT]Statistics [stat]/Other Statistics [stat.ML], 1309 Developmental Biology, 1302 Aging, Activities of Daily Living, Biomarker, Machine learning, Predictive modeling, Cross-validation, Open science, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Cognitive Dysfunction, Aged, Aged, 80 and over, [STAT.AP]Statistics [stat]/Applications [stat.AP], 10093 Institute of Psychology, General Neuroscience, Brain, 2800 General Neuroscience, Middle Aged, Magnetic Resonance Imaging, 2728 Neurology (clinical), Neurology (clinical), Geriatrics and Gerontology, 150 Psychology, Developmental Biology
Abstract

Previous literature has focused on predicting a diagnostic label from structural brain imaging. Since subtle changes in the brain precede a cognitive decline in healthy and pathological aging, our study predicts future decline as a continuous trajectory instead. Here, we tested whether baseline multimodal neuroimaging data improve the prediction of future cognitive decline in healthy and pathological aging. Nonbrain data (demographics, clinical, and neuropsychological scores), structural MRI, and functional connectivity data from OASIS-3 (N = 662; age = 46–96 years) were entered into cross-validated multitarget random forest models to predict future cognitive decline (measured by CDR and MMSE), on average 5.8 years into the future. The analysis was preregistered, and all analysis code is publicly available. Combining non-brain with structural data improved the continuous prediction of future cognitive decline (best test-set performance: R2 = 0.42). Cognitive performance, daily functioning, and subcortical volume drove the performance of our model. Including functional connectivity did not improve predictive accuracy. In the future, the prognosis of age-related cognitive decline may enable earlier and more effective individualized cognitive, pharmacological, and behavioral interventions., Neurobiology of Aging, 118, ISSN:0197-4580, ISSN:1558-1497

Published
2022

3. Evolving phenotypes of non-hospitalized patients that indicate long COVID

Author

ESTIRI, Hossein, Strasser, Zachary, Brat, Gabriel, Semenov, Yevgeniy, Patel, Chirag, Murphy, Shawn, Aaron, James, Agapito, Giuseppe, Albayrak, Adem, Alessiani, Mario, Amendola, Danilo, Anthony, Li, Aronow, Bruce, Ashraf, Fatima, Atz, Andrew, Avillach, Paul, Balshi, James, Beaulieu-Jones, Brett, Bell, Douglas, Bellasi, Antonio, Bellazzi, Riccardo, Benoit, Vincent, Beraghi, Michele, Sobrino, José Luis Bernal, Bernaux, Mélodie, Bey, Romain, Martínez, Alvar Blanco, Boeker, Martin, Bonzel, Clara-Lea, Booth, John, Bosari, Silvano, Bourgeois, Florence, Bradford, Robert, Bréant, Stéphane, Brown, Nicholas, Bryant, William, Bucalo, Mauro, Burgun, Anita, Cai, Tianxi, Cannataro, Mario, Carmona, Aldo, Caucheteux, Charlotte, Champ, Julien, Chen, Jin, Chen, Krista, Chiovato, Luca, Chiudinelli, Lorenzo, Cho, Kelly, Cimino, James, Colicchio, Tiago, Cormont, Sylvie, COSSIN, Sébastien, Craig, Jean, Bermúdez, Juan Luis Cruz, Rojo, Jaime Cruz, Dagliati, Arianna, Daniar, Mohamad, Daniel, Christel, Davoudi, Anahita, Devkota, Batsal, Dubiel, Julien, Esteve, Loic, Fan, Shirley, Follett, Robert, Gaiolla, Paula, Ganslandt, Thomas, Barrio, Noelia García, Garmire, Lana, Gehlenborg, Nils, GEVA, Alon, Gradinger, Tobias, Gramfort, Alexandre, Griffier, Romain, Griffon, Nicolas, Grisel, Olivier, Gutiérrez-Sacristán, Alba, Hanauer, David, Haverkamp, Christian, He, Bing, Henderson, Darren, Hilka, Martin, Holmes, John, Hong, Chuan, Horki, Petar, Huling, Kenneth, HUTCH, Meghan, Issitt, Richard, Jannot, Anne Sophie, Jouhet, Vianney, Keller, Mark, Kirchoff, Katie, Klann, Jeffrey, Kohane, Isaac, Krantz, Ian, Kraska, Detlef, Krishnamurthy, Ashok, L’Yi, Sehi, Le, Trang, Leblanc, Judith, Leite, Andressa, Lemaitre, Guillaume, Lenert, Leslie, Leprovost, Damien, Liu, Molei, LOH, Ne Hooi Will, Lozano-Zahonero, Sara, Luo, Yuan, Lynch, Kristine, Mahmood, Sadiqa, Maidlow, Sarah, Malovini, Alberto, Mandl, Kenneth, Mao, Chengsheng, Maram, Anupama, Martel, Patricia, Masino, Aaron, Mazzitelli, Maria, Mensch, Arthur, Milano, Marianna, Minicucci, Marcos, Moal, Bertrand, Moore, Jason, Moraleda, Cinta, Morris, Jeffrey, MORRIS, Michele, Moshal, Karyn, Mousavi, Sajad, Mowery, Danielle, Murad, Douglas, Naughton, Thomas, Neuraz, Antoine, Ngiam, Kee Yuan, Norman, James, Obeid, Jihad, Okoshi, Marina, Olson, Karen, Omenn, Gilbert, Orlova, Nina, Ostasiewski, Brian, Palmer, Nathan, Paris, Nicolas, Patel, Lav, Jimenez, Miguel Pedrera, Pfaff, Emily, Pillion, Danielle, Prokosch, Hans, Prudente, Robson, González, Víctor Quirós, Ramoni, Rachel, Raskin, Maryna, RIEG, Siegbert, Domínguez, Gustavo Roig, Rojo, Pablo, Sáez, Carlos, Salamanca, Elisa, Samayamuthu, Malarkodi, Sandrin, Arnaud, Santos, Janaina, Savino, Maria, SCHRIVER, Emily, Schubert, Petra, Schuettler, Juergen, Scudeller, Luigia, Sebire, Neil, Balazote, Pablo Serrano, Serre, Patricia, Serret-Larmande, Arnaud, Shakeri, Zahra, Silvio, Domenick, Sliz, Piotr, SON, Jiyeon, Sonday, Charles, South, Andrew, Spiridou, Anastasia, Tan, Amelia, Tan, Bryce, Tan, Byorn, Tanni, Suzana, Taylor, Deanne, Terriza Torres, Ana, Tibollo, Valentina, Tippmann, Patric, Torti, Carlo, Trecarichi, Enrico, Tseng, Yi-Ju, Vallejos, Andrew, Varoquaux, Gael, Vella, Margaret, Verdy, Guillaume, Vie, Jill-Jênn, Visweswaran, Shyam, Vitacca, Michele, Wagholikar, Kavishwar, Waitman, Lemuel, Wang, Xuan, Wassermann, Demian, Weber, Griffin, XIA, Zongqi, Yehya, Nadir, Yuan, William, Zambelli, Alberto, Zhang, Harrison, Zoeller, Daniel, Zucco, Chiara, Massachusetts General Hospital [Boston], Harvard Medical School [Boston] (HMS), Service d'informatique médicale et biostatistiques [CHU Necker], CHU Necker - Enfants Malades [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Health data- and model- driven Knowledge Acquisition (HeKA), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de Recherche des Cordeliers (CRC (UMR_S_1138 / U1138)), École pratique des hautes études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université de Paris (UP)-École pratique des hautes études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université de Paris (UP), Université de Paris - UFR Médecine Paris Centre [Santé] (UP Médecine Paris Centre), Université de Paris (UP), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-CHU Necker - Enfants Malades [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPC)-École pratique des hautes études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPC), Université Paris Cité - UFR Médecine Paris Centre [Santé] (UPC Médecine Paris Centre), Université Paris Cité (UPC), This work was supported by the National Human Genome Research Institute grant 3U01HG008685-05S2 and the National Library of Medicine grant T15LM007092., École Pratique des Hautes Études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPCité)-École Pratique des Hautes Études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPCité), UFR Médecine [Santé] - Université Paris Cité (UFR Médecine UPCité), and Université Paris Cité (UPCité)

Subjects
medicine.medical_specialty, Neurological disorder, Chest pain, MESH: Phenotype, Article, 03 medical and health sciences, 0302 clinical medicine, Post-Acute COVID-19 Syndrome, Diabetes mellitus, Internal medicine, Machine learning, medicine, Chronic fatigue syndrome, Humans, Electronic health records, Post-acute sequelae of SARS-CoV-2, MESH: COVID-19, 030304 developmental biology, Retrospective Studies, 0303 health sciences, MESH: Humans, business.industry, Medical record, Type 2 Diabetes Mellitus, COVID-19, Retrospective cohort study, MESH: Retrospective Studies, General Medicine, medicine.disease, 3. Good health, Dysgeusia, Phenotypes, Phenotype, Medicine, [SDV.SPEE]Life Sciences [q-bio]/Santé publique et épidémiologie, medicine.symptom, business, 030217 neurology & neurosurgery, Research Article, Cohort study
Abstract

Background For some SARS-CoV-2 survivors, recovery from the acute phase of the infection has been grueling with lingering effects. Many of the symptoms characterized as the post-acute sequelae of COVID-19 (PASC) could have multiple causes or are similarly seen in non-COVID patients. Accurate identification of PASC phenotypes will be important to guide future research and help the healthcare system focus its efforts and resources on adequately controlled age- and gender-specific sequelae of a COVID-19 infection. Methods In this retrospective electronic health record (EHR) cohort study, we applied a computational framework for knowledge discovery from clinical data, MLHO, to identify phenotypes that positively associate with a past positive reverse transcription-polymerase chain reaction (RT-PCR) test for COVID-19. We evaluated the post-test phenotypes in two temporal windows at 3–6 and 6–9 months after the test and by age and gender. Data from longitudinal diagnosis records stored in EHRs from Mass General Brigham in the Boston Metropolitan Area was used for the analyses. Statistical analyses were performed on data from March 2020 to June 2021. Study participants included over 96 thousand patients who had tested positive or negative for COVID-19 and were not hospitalized. Results We identified 33 phenotypes among different age/gender cohorts or time windows that were positively associated with past SARS-CoV-2 infection. All identified phenotypes were newly recorded in patients’ medical records 2 months or longer after a COVID-19 RT-PCR test in non-hospitalized patients regardless of the test result. Among these phenotypes, a new diagnosis record for anosmia and dysgeusia (OR 2.60, 95% CI [1.94–3.46]), alopecia (OR 3.09, 95% CI [2.53–3.76]), chest pain (OR 1.27, 95% CI [1.09–1.48]), chronic fatigue syndrome (OR 2.60, 95% CI [1.22–2.10]), shortness of breath (OR 1.41, 95% CI [1.22–1.64]), pneumonia (OR 1.66, 95% CI [1.28–2.16]), and type 2 diabetes mellitus (OR 1.41, 95% CI [1.22–1.64]) is one of the most significant indicators of a past COVID-19 infection. Additionally, more new phenotypes were found with increased confidence among the cohorts who were younger than 65. Conclusions The findings of this study confirm many of the post-COVID-19 symptoms and suggest that a variety of new diagnoses, including new diabetes mellitus and neurological disorder diagnoses, are more common among those with a history of COVID-19 than those without the infection. Additionally, more than 63% of PASC phenotypes were observed in patients under 65 years of age, pointing out the importance of vaccination to minimize the risk of debilitating post-acute sequelae of COVID-19 among younger adults.

Published
2021

4. International Analysis of Electronic Health Records of Children and Youth Hospitalized With COVID-19 Infection in 6 Countries

Author

Bourgeois, Florence, Gutiérrez-Sacristán, Alba, Keller, Mark, Liu, Molei, Hong, Chuan, Bonzel, Clara-Lea, Tan, Amelia, Aronow, Bruce, Boeker, Martin, Booth, John, Cruz Rojo, Jaime, Devkota, Batsal, García Barrio, Noelia, Gehlenborg, Nils, Geva, Alon, Hanauer, David, Hutch, Meghan, Issitt, Richard, Klann, Jeffrey, Luo, Yuan, Mandl, Kenneth, Mao, Chengsheng, Moal, Bertrand, Moshal, Karyn, Murphy, Shawn, Neuraz, Antoine, Ngiam, Kee Yuan, Omenn, Gilbert, Patel, Lav, Jiménez, Miguel Pedrera, Sebire, Neil, Balazote, Pablo Serrano, Serret-Larmande, Arnaud, South, Andrew, Spiridou, Anastasia, Taylor, Deanne, Tippmann, Patric, Visweswaran, Shyam, Weber, Griffin, Kohane, Isaac, Cai, Tianxi, Avillach, Paul, Cruz-Rojo, Jaime, García-Barrio, Noelia, Pedrera-Jiménez, Miguel, Serrano-Balazote, Pablo, Aaron, James, Agapito, Giuseppe, Albayrak, Adem, Alessiani, Mario, Amendola, Danilo, Angoulvant, François, Anthony, Li Llj, Atz, Andrew, Balshi, James, Beaulieu-Jones, Brett, Bell, Douglas, Bellasi, Antonio, Bellazzi, Riccardo, Benoit, Vincent, Beraghi, Michele, Bernal Sobrino, José Luis, Bernaux, Mélodie, Bey, Romain, Blanco Martínez, Alvar, Bosari, Silvano, Bradford, Robert, Brat, Gabriel, Bréant, Stéphane, Brown, Nicholas, Bryant, William, Bucalo, Mauro, Burgun, Anita, Cannataro, Mario, Carmona, Aldo, Caucheteux, Charlotte, Champ, Julien, Chen, Krista, Chen, Jin, Chiovato, Luca, Chiudinelli, Lorenzo, Cimino, James, Colicchio, Tiago, Cormont, Sylvie, Cossin, Sébastien, Craig, Jean, Cruz Bermúdez, Juan Luis, Dagliati, Arianna, Daniar, Mohamad, Daniel, Christel, Davoudi, Anahita, Dubiel, Julien, Duvall, Scott, Esteve, Loic, Fan, Shirley, Follett, Robert, Gaiolla, Paula Sa, Ganslandt, Thomas, Garmire, Lana, Gradinger, Tobias, Gramfort, Alexandre, Griffier, Romain, Griffon, Nicolas, Grisel, Olivier, Haverkamp, Christian, He, Bing, Henderson, Darren, Hilka, Martin, Holmes, John, Horki, Petar, Huling, Kenneth, Jannot, Anne Sophie, Jouhet, Vianney, Kavuluru, Ramakanth, Kirchoff, Katie, Krantz, Ian, Kraska, Detlef, Krishnamurthy, Ashok, L'Yi, Sehi, Le, Trang, Leblanc, Judith, Leite, Andressa Rr, Lemaitre, Guillaume, Lenert, Leslie, Leprovost, Damien, Loh, Ne Hooi Will, Lynch, Kristine, Mahmood, Sadiqa, Maidlow, Sarah, Malovini, Alberto, Maram, Anupama, Martel, Patricia, Masino, Aaron, Matheny, Michael, Maulhardt, Thomas, Mazzitelli, Maria, Mcduffie, Michael, Mensch, Arthur, Milano, Marianna, Minicucci, Marcos, Moore, Jason, Moraleda, Cinta, Morris, Jeffrey, Morris, Michele, Mousavi, Sajad, Mowery, Danielle, Murad, Douglas, Naughton, Thomas, Norman, James, Obeid, Jihad, Okoshi, Marina, Olson, Karen, Orlova, Nina, Ostasiewski, Brian, Palmer, Nathan, Paris, Nicolas, Pfaff, Emily, Pillion, Danielle, Prokosch, Hans, Prudente, Robson, Quirós González, Víctor, Ramoni, Rachel, Raskin, Maryna, Rieg, Siegbert, Roig Domínguez, Gustavo, Rojo, Pablo, Sáez, Carlos, Salamanca, Elisa, Samayamuthu, Malarkodi, Sandrin, Arnaud, Santos, Janaina Cc, Savino, Maria, Schriver, Emily, Schuettler, Juergen, Scudeller, Luigia, Serre, Patricia, Silvio, Domenick, Sliz, Piotr, Son, Jiyeon, Sonday, Charles, Tan, Bryce Wq, Tan, Byorn Wl, Tanni, Suzana, Terriza Torres, Ana, Tibollo, Valentina, Torti, Carlo, Trecarichi, Enrico, Tseng, Yi-Ju, Vallejos, Andrew, Varoquaux, Gael, Vie, Jill-Jênn, Vitacca, Michele, Wagholikar, Kavishwar, Waitman, Lemuel, Wassermann, Demian, William, Yuan, Xia, Zongqi, Yehya, Nadir, Zambelli, Alberto, Zhang, Harrison, Zucco, Chiara, Service d'informatique médicale et biostatistiques [CHU Necker], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-CHU Necker - Enfants Malades [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Health data- and model- driven Knowledge Acquisition (HeKA), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de Recherche des Cordeliers (CRC (UMR_S_1138 / U1138)), École Pratique des Hautes Études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPCité)-École Pratique des Hautes Études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPCité), UFR Médecine [Santé] - Université Paris Cité (UFR Médecine UPCité), Université Paris Cité (UPCité), Dr Bourgeois was funded by a grant from the Burroughs Wellcome Fund and supported by the Harvard-MIT Center for Regulatory Science. Mr Keller was funded by grant 5T32HG002295-18 from the National Human Genome Research Institute (NHGRI). Dr Aronow was funded by grant U24 HL148865 from the National Heart, Lung, and Blood Institute (NHLBI). Ms García Barrio was supported by grant PI18/00981 from the Carlos III Health Institute. Dr Gehlenborg was funded by grant T15 LM007092 from the NIH National Library of Medicine. Dr Geva was funded by grant K12 HD047349 from the NIH and Eunice Kennedy Shriver National Institute of Child Health and Human Development. Dr Hanauer was funded by grant UL1TR002240 from the National Center for Advancing Translational Sciences (NCATS). Drs Klann and Murphy were funded by grant 5UL1TR001857-05 from the NCATS and grant 5R01HG009174-04 from the NHGRI. Dr Luo was funded by grant R01LM013337 from the NLM. Mr Patel was funded by grant UL1TR002366 from the NCATS. Dr Gutiérrez-Sacristán was funded by grants K23HL148394 and L40HL148910 from the NIH NHLBI and grant UL1TR001420 from the NIH NCATS. Dr Visweswaran was funded by grant R01LM012095 from the NLM and grant UL1TR001857 from the NCATS. Dr Weber was supported by grants UL1TR002541 and UL1TR000005 from the NIH-NCATS, and grant R01LM013345 from the NLM., CHU Necker - Enfants Malades [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), École pratique des hautes études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université de Paris (UP)-École pratique des hautes études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université de Paris (UP), Université de Paris - UFR Médecine Paris Centre [Santé] (UP Médecine Paris Centre), Université de Paris (UP), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPC)-École pratique des hautes études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPC), Université Paris Cité - UFR Médecine Paris Centre [Santé] (UPC Médecine Paris Centre), and Université Paris Cité (UPC)

Subjects
medicine.medical_specialty, MESH: Pandemics, education, Health Informatics, MESH: Global Health, MESH: Hospitalization, Procalcitonin, 03 medical and health sciences, 0302 clinical medicine, 030225 pediatrics, Internal medicine, MESH: Child, Epidemiology, medicine, Infection control, MESH: COVID-19, MESH: SARS-CoV-2, 030212 general & internal medicine, health care economics and organizations, MESH: Electronic Health Records, Original Investigation, MESH: Adolescent, Disease surveillance, MESH: Humans, business.industry, Research, MESH: Infant, Newborn, MESH: Child, Preschool, Retrospective cohort study, MESH: Retrospective Studies, General Medicine, medicine.disease, MESH: Infant, MESH: Male, 3. Good health, Online Only, Respiratory failure, Viral pneumonia, Cohort, [SDV.SPEE]Life Sciences [q-bio]/Santé publique et épidémiologie, business, MESH: Female
Abstract

This cohort study aims to describe international hospitalization trends and key epidemiological and clinical features of children and youth with COVID-19., Key Points Question What are international trends in hospitalizations for children and youth with SARS-CoV-2, and what are the epidemiological and clinical features of these patients? Findings This cohort study of 671 children and youth found discrete surges in hospitalizations with variable trends and timing across countries. Common complications included cardiac arrhythmias and viral pneumonia, and laboratory findings included elevations in markers of inflammation and abnormalities of coagulation; few children and youth were treated with medications directed specifically at SARS-CoV-2. Meaning These findings suggest large-scale informatics-based approaches used to incorporate electronic health record data across health care systems can provide an efficient source of information to monitor disease activity and define epidemiological and clinical features of pediatric patients hospitalized with SARS-CoV-2 infections., Importance Additional sources of pediatric epidemiological and clinical data are needed to efficiently study COVID-19 in children and youth and inform infection prevention and clinical treatment of pediatric patients. Objective To describe international hospitalization trends and key epidemiological and clinical features of children and youth with COVID-19. Design, Setting, and Participants This retrospective cohort study included pediatric patients hospitalized between February 2 and October 10, 2020. Patient-level electronic health record (EHR) data were collected across 27 hospitals in France, Germany, Spain, Singapore, the UK, and the US. Patients younger than 21 years who tested positive for COVID-19 and were hospitalized at an institution participating in the Consortium for Clinical Characterization of COVID-19 by EHR were included in the study. Main Outcomes and Measures Patient characteristics, clinical features, and medication use. Results There were 347 males (52%; 95% CI, 48.5-55.3) and 324 females (48%; 95% CI, 44.4-51.3) in this study’s cohort. There was a bimodal age distribution, with the greatest proportion of patients in the 0- to 2-year (199 patients [30%]) and 12- to 17-year (170 patients [25%]) age range. Trends in hospitalizations for 671 children and youth found discrete surges with variable timing across 6 countries. Data from this cohort mirrored national-level pediatric hospitalization trends for most countries with available data, with peaks in hospitalizations during the initial spring surge occurring within 23 days in the national-level and 4CE data. A total of 27 364 laboratory values for 16 laboratory tests were analyzed, with mean values indicating elevations in markers of inflammation (C-reactive protein, 83 mg/L; 95% CI, 53-112 mg/L; ferritin, 417 ng/mL; 95% CI, 228-607 ng/mL; and procalcitonin, 1.45 ng/mL; 95% CI, 0.13-2.77 ng/mL). Abnormalities in coagulation were also evident (D-dimer, 0.78 ug/mL; 95% CI, 0.35-1.21 ug/mL; and fibrinogen, 477 mg/dL; 95% CI, 385-569 mg/dL). Cardiac troponin, when checked (n = 59), was elevated (0.032 ng/mL; 95% CI, 0.000-0.080 ng/mL). Common complications included cardiac arrhythmias (15.0%; 95% CI, 8.1%-21.7%), viral pneumonia (13.3%; 95% CI, 6.5%-20.1%), and respiratory failure (10.5%; 95% CI, 5.8%-15.3%). Few children were treated with COVID-19–directed medications. Conclusions and Relevance This study of EHRs of children and youth hospitalized for COVID-19 in 6 countries demonstrated variability in hospitalization trends across countries and identified common complications and laboratory abnormalities in children and youth with COVID-19 infection. Large-scale informatics-based approaches to integrate and analyze data across health care systems complement methods of disease surveillance and advance understanding of epidemiological and clinical features associated with COVID-19 in children and youth.

Published
2021

5. Combining magnetoencephalography with magnetic resonance imaging enhances learning of surrogate-biomarkers

Author

Engemann, Denis A, Kozynets, Oleh, Sabbagh, David, Lemaître, Guillaume, Varoquaux, Gael, Liem, Franziskus, Gramfort, Alexandre, Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), University Research Priority Program Dynamics of Healthy Aging [Zurich] (URPP Dynamics of Healthy Aging ), Universität Zürich [Zürich] = University of Zurich (UZH), European Project: 676943,H2020,SLAB(2016), University of Zurich, Engemann, Denis A, Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay

Subjects
Adult, Male, Adolescent, QH301-705.5, Science, [SCCO.COMP]Cognitive science/Computer science, UFSP13-4 Dynamics of Healthy Aging, Neuropsychological Tests, Multimodal Imaging, magnetoencephalogrphy, Young Adult, Cognition, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Predictive Value of Tests, 1300 General Biochemistry, Genetics and Molecular Biology, 2400 General Immunology and Microbiology, Reaction Time, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, magnetic resonance imaging, Biology (General), Human Biology and Medicine, Aged, Aged, 80 and over, [SDV.NEU.PC]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Psychology and behavior, 10093 Institute of Psychology, Functional Neuroimaging, [SCCO.NEUR]Cognitive science/Neuroscience, aging, Age Factors, Brain, Magnetoencephalography, 2800 General Neuroscience, Middle Aged, Brain Waves, Tools and Resources, machine learning, Cognitive Aging, oscillations, [SCCO.PSYC]Cognitive science/Psychology, Medicine, biomarker, Female, 150 Psychology, Algorithms, Neuroscience, Human
Abstract

Electrophysiological methods, that is M/EEG, provide unique views into brain health. Yet, when building predictive models from brain data, it is often unclear how electrophysiology should be combined with other neuroimaging methods. Information can be redundant, useful common representations of multimodal data may not be obvious and multimodal data collection can be medically contraindicated, which reduces applicability. Here, we propose a multimodal model to robustly combine MEG, MRI and fMRI for prediction. We focus on age prediction as a surrogate biomarker in 674 subjects from the Cam-CAN dataset. Strikingly, MEG, fMRI and MRI showed additive effects supporting distinct brain-behavior associations. Moreover, the contribution of MEG was best explained by cortical power spectra between 8 and 30 Hz. Finally, we demonstrate that the model preserves benefits of stacking when some data is missing. The proposed framework, hence, enables multimodal learning for a wide range of biomarkers from diverse types of brain signals., eLife digest How old are you? What about your body, and your brain? People are used to answering this question by counting the years since birth. However, biological age could also be measured by looking at the integrity of the DNA in cells or by measuring the levels of proteins in the blood. Whether one goes by chronological age or biological age, each is simply an indicator of general health – but people with the same chronological age may have different biological ages, and vice versa. There are different imaging techniques that can be used to study the brain. A method called MRI reveals the brain’s structure and the different types of tissue present, like white and grey matter. Functional MRIs (fMRIs for short) measure activity across different brain regions, while electrophysiology records electrical signals sent between neurons. Distinct features measured by all three techniques – MRI, fMRI and electrophysiology – have been associated with aging. For example, differences between younger and older people have been observed in the proportion of grey to white matter, the communication between certain brain regions, and the intensity of neural activity. MRIs, with their anatomical detail, remain the go-to for predicting the biological age of the brain. Patterns of neuronal activity captured by electrophysiology also provide information about how well the brain is working. However, it remains unclear how electrophysiology could be combined with other brain imaging methods, like MRI and fMRI. Can data from these three techniques be combined to better predict brain age? Engemann et al. designed a computer algorithm stacking electrophysiology data on top of MRI and fMRI imaging to assess the benefit of this three-pronged approach compared to using MRI alone. Brain scans from healthy people between 17 and 90 years old were used to build the computer model. The experiments showed that combining all three methods predicted brain age better. The predictions also correlated with the cognitive fitness of individuals. People whose brains were predicted to be older than their years tended to complain about the quality of their sleep and scored worse on memory and speed-thinking tasks. Crucially, Engemann et al. tested how the algorithm would hold up if some data were missing. This can happen in clinical practice where some tests are required but not others. Positively, prediction was maintained even with incomplete data, meaning this could be a useful clinical tool for characterizing the brain.

Published
2020

6. Beyond brain age: Empirically-derived proxy measures of mental health

Author

Dadi, Kamalaker, Varoquaux, Gael, Houenou, Josselin, Bzdok, Danilo, Thirion, Bertrand, Engemann, Denis, Engemann, Denis-Alexander, Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Montreal Institute for Learning Algorithms [Montréal] (MILA), Centre de Recherches Mathématiques [Montréal] (CRM), Université de Montréal (UdeM)-Université de Montréal (UdeM), CHU Henri Mondor, Department of Psychiatry, Psychotherapy and Psychosomatics [Aachen], Rheinisch-Westfälische Technische Hochschule Aachen University (RWTH), Max Planck Institute for Human Cognitive and Brain Sciences [Leipzig] (IMPNSC), Max-Planck-Gesellschaft, Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Rheinisch-Westfälische Technische Hochschule Aachen (RWTH), and CHU Henri Mondor [Créteil]

Subjects
[SHS.STAT]Humanities and Social Sciences/Methods and statistics, [SDV.NEU.PC]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Psychology and behavior, [SDV]Life Sciences [q-bio], [SCCO.NEUR]Cognitive science/Neuroscience, [SCCO.NEUR] Cognitive science/Neuroscience, [SDV.NEU.PC] Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Psychology and behavior, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, [SHS.PSY]Humanities and Social Sciences/Psychology, [SCCO] Cognitive science, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], [INFO] Computer Science [cs], [SHS.PSY] Humanities and Social Sciences/Psychology, [SDV] Life Sciences [q-bio], [SCCO]Cognitive science, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [SHS.STAT] Humanities and Social Sciences/Methods and statistics, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, [INFO]Computer Science [cs]
Abstract

Biological aging is revealed by physical measures, e.g., DNA probes or brain scans. Individual differences in personal functioning are instead explained by psychological constructs.Constructs such as intelligence or neuroticism are typically assessed by specialized workforce through tailored questionnaires and tests. Similar to how brain age captures biological aging, intelligence and neuroticism may provide empirical proxies for mental health. Could the combination of brain imaging and sociodemographic information yield measures for these constructs that do not rely on human judgment? Here, we built proxy measures by applying machine learning on multimodal MR images and rich sociodemographic informationfrom the largest brain-imaging cohort to date: the UK Biobank. Objective comparisons revealed that all proxies captured the target constructs and related to health-contributing habits beyond the measures they were derived from. Our results demonstrate that proxies targeting classical psychological constructs reveal facets of mental health complementary to information conveyed by brain age.

Published
2020

7. Inter-subject registration of functional images: do we need anatomical images ?

Author

Dohmatob, Elvis, Varoquaux, Gael, Thirion, Bertrand, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), and Dohmatob, Elvis

Subjects
[STAT.AP]Statistics [stat]/Applications [stat.AP], B0 inhomogeneity, General Neuroscience, [SCCO.NEUR]Cognitive science/Neuroscience, [SCCO.NEUR] Cognitive science/Neuroscience, human brain-mapping, high-resolution EPI, distortions, lcsh:RC321-571, inter-subject registration, [STAT.AP] Statistics [stat]/Applications [stat.AP], Methods, functional MRI, [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM], lcsh:Neurosciences. Biological psychiatry. Neuropsychiatry, [INFO.INFO-BI] Computer Science [cs]/Bioinformatics [q-bio.QM], Neuroscience
Abstract

International audience; In Echo-Planar Imaging (EPI)-based MRI (Magnetic Resonance Imaging), inter-subject registration typically uses the subject's T1-weighted (T1w) anatomical image to learn deformations of the subject's brain onto a template. The estimated deformation fields are then applied to the subject's EPI scans (functional or diffusion-weighted images) to warp the latter to a template space. Historically, such indirect T1w-based registration was motivated by the lack of clear anatomical details in low-resolution EPI images: a direct registration of the EPI scans to template space would be futile. A central prerequisite in such indirect methods is that the anatomical (aka the T1w) image of each subject is well aligned with their EPI images via rigid coregistration. We provide experimental evidence that things have changed: nowadays, there is a decent amount of anatomical contrast in high-resolution EPI data. That notwithstanding, EPI distortions due to B0 inhomogeneities cannot be fully corrected. Residual uncorrected distortions induce non-rigid deformations between the EPI scans and the same subject's anatomical scan. In this manuscript, we contribute a computationally cheap pipeline that leverages the high spatial resolution of modern EPI scans for direct inter-subject matching. Our pipeline is direct and does not rely on the T1w scan to estimate the inter-subject deformation. Results on a large dataset show that this new pipeline outperforms the classical indirect T1w-based registration scheme, across a variety of post-registration quality-assessment metrics including: Normalized Mutual Information, relative variance (variance-to-mean ratio), and to a lesser extent, improved peaks of group-level General Linear Model (GLM) activation maps.

Published
2018

8. Mapping cognitive ontologies to and from the brain

Author

Varoquaux Gael, Schwartz Yannick, Thirion Bertrand, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Laboratoire de Neuroimagerie Assistée par Ordinateur (LNAO), Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay

Subjects
FOS: Computer and information sciences, Cognitive science, reverse inference, Computer science, fMRI, Biomedical Engineering, Neuroscience (miscellaneous), Machine Learning (stat.ML), Cognition, Machine Learning (cs.LG), Computer Science Applications, Computer Science - Learning, multilabel learning, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Statistics - Machine Learning, meta-analyses, Quantitative Biology - Neurons and Cognition, FOS: Biological sciences, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Neurons and Cognition (q-bio.NC), forward inference
Abstract

Imaging neuroscience links brain activation maps to behavior and cognition via correlational studies. Due to the nature of the individual experiments, based on eliciting neural response from a small number of stimuli, this link is incomplete, and unidirectional from the causal point of view. To come to conclusions on the function implied by the activation of brain regions, it is necessary to combine a wide exploration of the various brain functions and some inversion of the statistical inference. Here we introduce a methodology for accumulating knowledge towards a bidirectional link between observed brain activity and the corresponding function. We rely on a large corpus of imaging studies and a predictive engine. Technically, the challenges are to find commonality between the studies without denaturing the richness of the corpus. The key elements that we contribute are labeling the tasks performed with a cognitive ontology, and modeling the long tail of rare paradigms in the corpus. To our knowledge, our approach is the first demonstration of predicting the cognitive content of completely new brain images. To that end, we propose a method that predicts the experimental paradigms across different studies., Comment: NIPS (Neural Information Processing Systems), United States (2013)

Published
2013

Catalog

Books, media, physical & digital resources
See catalog results