pith. machine review for the scientific record. sign in

arxiv: 2605.02952 · v1 · submitted 2026-05-02 · 🧬 q-bio.OT

Recognition: unknown

DynoSys: A Dynamic Systems Framework for Multimodal Integration of Genetic, Environmental, and Neurobiological Signals

Mengman Wei , Qian Peng
Authors on Pith no claims yet

Pith reviewed 2026-05-10 16:10 UTC · model grok-4.3

classification 🧬 q-bio.OT
keywords dynamic systems modelingmultimodal integrationgenetic environmental interactionsbehavioral phenotypeslongitudinal modelingsurvival analysisneuroimaging representationspolygenic risk
0
0 comments X

The pith

A dynamic systems framework models genetics as foundational state, environment as time-varying inputs, brain as mediator, and behavior as output.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes a unified quantitative framework that treats the human body as a dynamic system to integrate genetic predisposition, environmental exposures, and neurobiological processes over time. It constructs harmonized multi-domain representations for phenotypes including externalizing and internalizing behaviors plus substance use initiation, using stability selection and dimensionality reduction on polygenic, environmental, and neuroimaging data. The approach supports both continuous longitudinal modeling and survival-based event modeling through a single data structure. A sympathetic reader would care because it supplies an explicit structure for handling how these factors interact to shape observable outcomes, rather than treating them in isolation.

Core claim

We present a unified quantitative framework that models the human body as a dynamic system, where genetic factors form the foundational state, environmental exposures act as time-varying inputs, the brain might serve as a mediation processor, and behavioral phenotypes emerge as system outputs. Using longitudinal data, we construct harmonized multi-domain representations across six phenotypes and integrate polygenic risk scores, multi-domain environmental features, and multimodal neuroimaging representations derived through stability selection and dimensionality reduction. This supports downstream modeling with survival analysis, state-space models, and machine learning while producing domain

What carries the argument

Dynamic system representation treating genetics as initial state, environmental exposures as time-varying inputs, brain as mediation processor, and behavioral phenotypes as outputs.

If this is right

  • The framework unifies continuous longitudinal tracking with discrete event modeling such as substance use initiation in one data structure.
  • It produces interpretable summaries via principal components, weighted risk scores, and cluster-based representations for each domain.
  • These representations enable consistent application of survival analysis, state-space models, and machine learning to the same underlying data.
  • The approach identifies modifiable risk factors by isolating the contributions of environment and neurobiology to phenotypic change.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same state-input-output structure could be applied to other developmental windows or to non-behavioral outcomes such as physical health trajectories.
  • Treating interventions as additional inputs would turn the framework into a tool for simulating the effects of targeted environmental changes.
  • Validation would require checking whether the brain-mediated path improves out-of-sample prediction relative to direct genetic-environmental models on independent longitudinal cohorts.

Load-bearing premise

The brain serves as a mediation processor and the harmonized representations from stability selection and dimensionality reduction accurately capture interactions among genetic, environmental, and neurobiological signals over time.

What would settle it

A direct comparison in which the full integrated model shows no gain in predictive accuracy for behavioral outcomes over a reduced model that omits the brain-mediated representations.

Figures

Figures reproduced from arXiv: 2605.02952 by Mengman Wei, Qian Peng.

Figure 1
Figure 1. Figure 1: Conceptual framework of human behavior as a dynamic system. This figure shows human behavior as a system that changes over time and integrates multiple types of information. Genetic factors, such as DNA variation and polygenic risk scores (PRS) [11, 12, 13, 14], provide a basic biological foundation. At the same time, external inputs, such as sensory experiences, family environment, social context, and tec… view at source ↗
Figure 2
Figure 2. Figure 2: Systems-level modeling pipeline for multi-domain integration and time-aware analysis. Overview of the proposed systems-level modeling pipeline for understanding human behavior through multi-domain integration and time-aware analysis. The framework begins with two primary input domains: biological foundations, including genetic variation and polygenic risk scores (PRS), and dynamic environmental and experie… view at source ↗
Figure 3
Figure 3. Figure 3: Multi-task learning architecture. Multimodal predictors, including genetic, environ￾mental, and brain-derived features, were preprocessed separately from covariates. Non-covariate predictors were residualized against covariates using training-set estimates only, then imputed and scaled. Covariates were processed separately and concatenated with residualized predictors before entering a shared-bottom neural… view at source ↗
read the original abstract

Understanding the development of adolescent behavioral and mental health outcomes requires integrating genetic predisposition, environmental exposures, and neurobiological processes over time. Here, we present a unified quantitative framework that models the human body as a dynamic system, where genetic factors form the foundational state, environmental exposures act as time-varying inputs, the brain might serve as a mediation processor, and behavioral phenotypes emerge as system outputs. Using longitudinal data from the Adolescent Brain Cognitive Development (ABCD) Study, we construct harmonized multi-domain representations across six phenotypes: externalizing behavior, internalizing behavior, and four substance use initiation outcomes (alcohol, nicotine, cannabis, and any substance use). We integrate polygenic risk scores (PRS), multi-domain environmental features, and multimodal neuroimaging representations derived through stability selection and dimensionality reduction. Our framework supports both continuous longitudinal modeling and survival-based event modeling through a unified data structure. We further develop interpretable domain-level representations using principal components, weighted risk scores, and cluster-based summaries. These representations enable downstream modeling using survival analysis, state-space models, and machine learning approaches. This work establishes a scalable and interpretable framework for studying how genetic and environmental factors interact over time to shape behavioral outcomes, providing a foundation for identifying modifiable risk factors and informing early intervention strategies.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript introduces DynoSys, a dynamic systems framework for integrating genetic (PRS), environmental, and neurobiological (neuroimaging) signals from the ABCD longitudinal study. Genetic factors are positioned as the foundational state, environmental exposures as time-varying inputs, the brain as a potential mediation processor, and behavioral phenotypes (externalizing/internalizing behavior, substance use initiation) as outputs. Harmonized multi-domain representations are constructed via stability selection and dimensionality reduction, yielding a unified data structure intended to support survival analysis, state-space models, and machine learning.

Significance. If the integrated representations can be shown to capture temporal gene-environment-brain interactions and improve prediction or mediation inference over non-integrated baselines, the framework could offer a scalable template for multimodal developmental modeling. The emphasis on interpretable summaries (principal components, weighted scores, clusters) and public ABCD data is a constructive step toward reproducible pipelines in psychiatric genetics.

major comments (2)
  1. Abstract and framework description: The central claim that the approach 'models the human body as a dynamic system' with the brain as mediation processor is not supported by any state-space equations, transition functions, mediation tests, or fitted parameters. The text stops at data harmonization and states that the representations 'enable' downstream modeling without demonstrating any such modeling or its validity.
  2. No results or validation section: The manuscript reports no quantitative outcomes (prediction metrics, hazard ratios, mediation effects, model fits, or comparisons to non-integrated baselines) for the six phenotypes. Without these, the assertion that the harmonized representations accurately capture interactions over time remains untested and the dynamic-systems framing reduces to an unvalidated data-preparation pipeline.
minor comments (2)
  1. Abstract: The phrasing 'the brain might serve as a mediation processor' is tentative; the manuscript should either commit to a testable mediation hypothesis or reframe the brain component as one of several candidate mediators.
  2. Notation and reproducibility: Define the exact stability-selection procedure, dimensionality-reduction targets, and unified data structure (e.g., variable names, time indexing) so that other groups can replicate the representations on ABCD or similar cohorts.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive and detailed review. We address each major comment point by point below, with plans for revision where appropriate.

read point-by-point responses

  1. Referee: Abstract and framework description: The central claim that the approach 'models the human body as a dynamic system' with the brain as mediation processor is not supported by any state-space equations, transition functions, mediation tests, or fitted parameters. The text stops at data harmonization and states that the representations 'enable' downstream modeling without demonstrating any such modeling or its validity.

    Authors: We agree that the manuscript presents a conceptual framing of the human body as a dynamic system but implements the harmonization of genetic, environmental, and neurobiological data into unified representations without fitting explicit state-space models or conducting mediation tests. The phrasing in the abstract is intended to describe the overarching theoretical structure that the data pipeline supports, rather than to claim completed dynamic modeling. We will revise the abstract, introduction, and framework description to clarify this distinction, emphasizing that the current work delivers the harmonized data structure and interpretable summaries as a foundation for subsequent state-space, survival, or machine-learning analyses. We will also add a brief discussion outlining example transition functions and mediation pathways that could be applied to the unified representations in future extensions. revision: yes

  2. Referee: No results or validation section: The manuscript reports no quantitative outcomes (prediction metrics, hazard ratios, mediation effects, model fits, or comparisons to non-integrated baselines) for the six phenotypes. Without these, the assertion that the harmonized representations accurately capture interactions over time remains untested and the dynamic-systems framing reduces to an unvalidated data-preparation pipeline.

    Authors: The referee is correct that the manuscript contains no quantitative results or validation metrics for the six phenotypes. The primary contribution is the development of the integration framework and the construction of harmonized representations from ABCD data. To address this, we will add a validation section that reports basic quantitative checks, including stability of the dimensionality-reduced features, simple predictive performance comparisons (e.g., integrated vs. non-integrated features in logistic or Cox models for the phenotypes), and descriptive statistics on the unified data structure. These additions will provide initial evidence of utility while preserving the manuscript's focus on the methodological pipeline rather than exhaustive application results. revision: yes

Circularity Check

0 steps flagged

No circularity; framework is a descriptive data integration pipeline

full rationale

The manuscript presents a methodological framework for constructing harmonized multi-domain representations from the external ABCD dataset via stability selection and dimensionality reduction, then states that these enable downstream survival analysis, state-space models, and ML. No equations, fitted parameters, or predictions are shown that reduce by construction to the inputs (e.g., no self-definitional mapping of genetic state to outputs or fitted-input-called-prediction). No self-citations, uniqueness theorems, or ansatzes are invoked as load-bearing steps. The central claim is a positioning of the pipeline as a foundation for future modeling rather than a derivation that tautologically reproduces its own construction steps.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The central claim rests on the modeling premise that genetic factors, environmental inputs, and brain processes can be represented as a coherent dynamic system whose outputs are behavioral phenotypes; no specific numerical free parameters are stated in the abstract.

axioms (1)
  • domain assumption The brain serves as a mediation processor between genetic and environmental inputs and behavioral outputs.
    Explicitly stated in the abstract as part of the dynamic system model.
invented entities (1)
  • DynoSys framework no independent evidence
    purpose: To provide a unified data structure and modeling approach for integrating multimodal signals.
    Newly proposed construct in this paper with no independent evidence supplied.

pith-pipeline@v0.9.0 · 5527 in / 1378 out tokens · 66040 ms · 2026-05-10T16:10:03.153630+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

47 extracted references · 1 canonical work pages · 1 internal anchor

  1. [1]

    The bioecological model of human development

    Urie Bronfenbrenner and Pamela A Morris. The bioecological model of human development. Handbook of child psychology, 1, 2007

    2007

  2. [2]

    Toward the future of psychiatric diagnosis: the seven pillars of rdoc.BMC medicine, 11(1):126, 2013

    Bruce N Cuthbert and Thomas R Insel. Toward the future of psychiatric diagnosis: the seven pillars of rdoc.BMC medicine, 11(1):126, 2013

    2013

  3. [3]

    A neurodevelopmental perspective on the research domain criteria (rdoc) framework.Biological psychiatry, 76(5):350–353, 2014

    BJ Casey, Mary Ellen Oliveri, and Thomas Insel. A neurodevelopmental perspective on the research domain criteria (rdoc) framework.Biological psychiatry, 76(5):350–353, 2014

    2014

  4. [4]

    Imaging genetics and genomics in psychiatry: a critical review of progress and potential.Biological psychiatry, 82(3):165–175, 2017

    Ryan Bogdan, Betty Jo Salmeron, Caitlin E Carey, Arpana Agrawal, Vince D Calhoun, Hugh Garavan, Ahmad R Hariri, Andreas Heinz, Matthew N Hill, Andrew Holmes, et al. Imaging genetics and genomics in psychiatry: a critical review of progress and potential.Biological psychiatry, 82(3):165–175, 2017

    2017

  5. [5]

    Role of genotype in the cycle of violence in maltreated children.Science, 297(5582):851–854, 2002

    Avshalom Caspi, Joseph McClay, Terrie E Moffitt, Jonathan Mill, Judy Martin, Ian W Craig, Alan Taylor, and Richie Poulton. Role of genotype in the cycle of violence in maltreated children.Science, 297(5582):851–854, 2002

    2002

  6. [6]

    The free-energy principle: a unified brain theory?Nature reviews neuroscience, 11(2):127–138, 2010

    Karl Friston. The free-energy principle: a unified brain theory?Nature reviews neuroscience, 11(2):127–138, 2010

    2010

  7. [7]

    Genome-wide association studies of brain imaging phenotypes in uk biobank.Nature, 562(7726):210–216, 2018

    Lloyd T Elliott, Kevin Sharp, Fidel Alfaro-Almagro, Sinan Shi, Karla L Miller, Gwenaëlle Douaud, Jonathan Marchini, and Stephen M Smith. Genome-wide association studies of brain imaging phenotypes in uk biobank.Nature, 562(7726):210–216, 2018

    2018

  8. [8]

    Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications

    Sandra Vieira, Walter HL Pinaya, and Andrea Mechelli. Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications. Neuroscience & Biobehavioral Reviews, 74:58–75, 2017

    2017

  9. [9]

    The challenges and opportunities of small effects: The new normal in academic psychiatry.JAMA psychiatry, 76(4):353–354, 2019

    Martin P Paulus and Wesley K Thompson. The challenges and opportunities of small effects: The new normal in academic psychiatry.JAMA psychiatry, 76(4):353–354, 2019

    2019

  10. [10]

    A developmental psychopathology perspective on adolescence.Journal of consulting and clinical psychology, 70(1):6, 2002

    Dante Cicchetti and Fred A Rogosch. A developmental psychopathology perspective on adolescence.Journal of consulting and clinical psychology, 70(1):6, 2002

    2002

  11. [11]

    Research review: polygenic methods and their application to psychiatric traits.Journal of child psychology and psychiatry, 55(10):1068–1087, 2014

    Naomi R Wray, Sang Hong Lee, Divya Mehta, Anna AE Vinkhuyzen, Frank Dudbridge, and Christel M Middeldorp. Research review: polygenic methods and their application to psychiatric traits.Journal of child psychology and psychiatry, 55(10):1068–1087, 2014

    2014

  12. [12]

    Tutorial: a guide to performing polygenic risk score analyses.Nature protocols, 15(9):2759–2772, 2020

    Shing Wan Choi, Timothy Shin-Heng Mak, and Paul F O’Reilly. Tutorial: a guide to performing polygenic risk score analyses.Nature protocols, 15(9):2759–2772, 2020. 23

    2020

  13. [13]

    Polygenic risk scores in clinical psy- chology: bridging genomic risk to individual differences.Annual review of clinical psychology, 14:119–157, 2018

    Ryan Bogdan, David AA Baranger, and Arpana Agrawal. Polygenic risk scores in clinical psy- chology: bridging genomic risk to individual differences.Annual review of clinical psychology, 14:119–157, 2018

    2018

  14. [14]

    Multivariate analysis of 1.5 million people identifies genetic associations with traits related to self-regulation and addiction.Nature neuroscience, 24(10):1367–1376, 2021

    Richard Karlsson Linnér, Travis T Mallard, Peter B Barr, Sandra Sanchez-Roige, James W Madole, Morgan N Driver, Holly E Poore, Ronald de Vlaming, Andrew D Grotzinger, Jorim J Tielbeek, et al. Multivariate analysis of 1.5 million people identifies genetic associations with traits related to self-regulation and addiction.Nature neuroscience, 24(10):1367–1376, 2021

    2021

  15. [15]

    Guidelines for evaluating the comparability of down-sampled gwas summary statistics.Behavior Genetics, 53(5):404–415, 2023

    Camille M Williams, Holly Poore, Peter T Tanksley, Hyeokmoon Kweon, Natasia S Courchesne- Krak, Diego Londono-Correa, Travis T Mallard, Peter Barr, Philipp D Koellinger, Irwin D Waldman, et al. Guidelines for evaluating the comparability of down-sampled gwas summary statistics.Behavior Genetics, 53(5):404–415, 2023

    2023

  16. [16]

    Adolescent Brain Cognitive Development (ABCD) Study®

    National Institutes of Health. Adolescent Brain Cognitive Development (ABCD) Study®. https://abcdstudy.org

  17. [17]

    Neuroanatomical variability and substance use initiation in late childhood and early adolescence.JAMA network open, 7(12):e2452027, 2024

    Alex P Miller, David AA Baranger, Sarah E Paul, Hugh Garavan, Scott Mackey, Susan F Tapert, Kimberly H LeBlanc, Arpana Agrawal, and Ryan Bogdan. Neuroanatomical variability and substance use initiation in late childhood and early adolescence.JAMA network open, 7(12):e2452027, 2024

    2024

  18. [18]

    A global reference for human genetic variation.nature, 526(7571):68, 2015

    Adam Auton, Gonçalo R Abecasis, David M Altshuler, Richard M Durbin, David R Bentley, Aravinda Chakravarti, Andrew G Clark, Peter Donnelly, Evan E Eichler, Paul Flicek, et al. A global reference for human genetic variation.nature, 526(7571):68, 2015

    2015

  19. [19]

    Genome-wide meta-analysis of depression identifies 102 independent variants and highlights the importance of the prefrontal brain regions.Nature neuroscience, 22(3):343–352, 2019

    David M Howard, Mark J Adams, Toni-Kim Clarke, Jonathan D Hafferty, Jude Gibson, Masoud Shirali, Jonathan RI Coleman, Saskia P Hagenaars, Joey Ward, Eleanor M Wigmore, et al. Genome-wide meta-analysis of depression identifies 102 independent variants and highlights the importance of the prefrontal brain regions.Nature neuroscience, 22(3):343–352, 2019

    2019

  20. [20]

    Gene discovery and biological insights into anxiety disorders from a large-scale multi-ancestry genome-wide association study.Nature genetics, 56(10):2036–2045, 2024

    Eleni Friligkou, Solveig Løkhammer, Brenda Cabrera-Mendoza, Jie Shen, Jun He, Giovanni Deiana, Mihaela Diana Zanoaga, Zeynep Asgel, Abigail Pilcher, Luciana Di Lascio, et al. Gene discovery and biological insights into anxiety disorders from a large-scale multi-ancestry genome-wide association study.Nature genetics, 56(10):2036–2045, 2024

    2036

  21. [21]

    Item-level analyses reveal genetic heterogeneity in neuroticism.Nature communications, 9(1):905, 2018

    Mats Nagel, Kyoko Watanabe, Sven Stringer, Danielle Posthuma, and Sophie Van Der Sluis. Item-level analyses reveal genetic heterogeneity in neuroticism.Nature communications, 9(1):905, 2018

    2018

  22. [22]

    Genome-wide association meta-analysis of childhood and adolescent internalizing symptoms.Journal of the American Academy of Child & Adolescent Psychiatry, 61(7):934–945, 2022

    Eshim S Jami, Anke R Hammerschlag, Hill F Ip, Andrea G Allegrini, Beben Benyamin, Richard Border, Elizabeth W Diemer, Chang Jiang, Ville Karhunen, Yi Lu, et al. Genome-wide association meta-analysis of childhood and adolescent internalizing symptoms.Journal of the American Academy of Child & Adolescent Psychiatry, 61(7):934–945, 2022

    2022

  23. [23]

    Multi-ancestry study of the genetics of problematic alcohol use in over 1 million individuals.Nature Medicine, 29(12):3184–3192, 2023

    Hang Zhou, Rachel L Kember, Joseph D Deak, Heng Xu, Sylvanus Toikumo, Kai Yuan, Penelope A Lind, Leila Farajzadeh, Lu Wang, Alexander S Hatoum, et al. Multi-ancestry study of the genetics of problematic alcohol use in over 1 million individuals.Nature Medicine, 29(12):3184–3192, 2023

    2023

  24. [24]

    Multi- ancestry genome-wide association study of cannabis use disorder yields insight into disease biology and public health implications.Nature Genetics, 55(12):2094–2103, 2023

    Daniel F Levey, Marco Galimberti, Joseph D Deak, Frank R Wendt, Arjun Bhattacharya, Dora Koller, Kelly M Harrington, Rachel Quaden, Emma C Johnson, Priya Gupta, et al. Multi- ancestry genome-wide association study of cannabis use disorder yields insight into disease biology and public health implications.Nature Genetics, 55(12):2094–2103, 2023

    2094

  25. [25]

    Association studies of up to 1.2 million individuals yield new insights into the genetic etiology of tobacco and alcohol use

    Mengzhen Liu, Yu Jiang, Robbee Wedow, Yue Li, David M Brazel, Fang Chen, Gargi Datta, Jose Davila-Velderrain, Daniel McGuire, Chao Tian, et al. Association studies of up to 1.2 million individuals yield new insights into the genetic etiology of tobacco and alcohol use. Nature genetics, 51(2):237–244, 2019

    2019

  26. [26]

    Multivariate genome-wide association meta-analysis of over 1 million subjects identifies loci underlying multiple substance use disorders.Nature mental health, 1(3):210–223, 2023

    Alexander S Hatoum, Sarah MC Colbert, Emma C Johnson, Spencer B Huggett, Joseph D Deak, Gita A Pathak, Mariela V Jennings, Sarah E Paul, Nicole R Karcher, Isabella Hansen, et al. Multivariate genome-wide association meta-analysis of over 1 million subjects identifies loci underlying multiple substance use disorders.Nature mental health, 1(3):210–223, 2023. 24

    2023

  27. [27]

    Polygenic prediction via bayesian regression and continuous shrinkage priors.Nature communications, 10(1):1776, 2019

    Tian Ge, Chia-Yen Chen, Yang Ni, Yen-Chen Anne Feng, and Jordan W Smoller. Polygenic prediction via bayesian regression and continuous shrinkage priors.Nature communications, 10(1):1776, 2019

    2019

  28. [28]

    Second-generation plink: rising to the challenge of larger and richer datasets.Gigascience, 4(1):s13742–015, 2015

    Christopher C Chang, Carson C Chow, Laurent CAM Tellier, Shashaank Vattikuti, Shaun M Purcell, and James J Lee. Second-generation plink: rising to the challenge of larger and richer datasets.Gigascience, 4(1):s13742–015, 2015

    2015

  29. [29]

    The adolescent brain cognitive development (abcd) study: imaging acquisition across 21 sites

    Betty Jo Casey, Tariq Cannonier, May I Conley, Alexandra O Cohen, Deanna M Barch, Mary M Heitzeg, Mary E Soules, Theresa Teslovich, Danielle V Dellarco, Hugh Garavan, et al. The adolescent brain cognitive development (abcd) study: imaging acquisition across 21 sites. Developmental cognitive neuroscience, 32:43–54, 2018

    2018

  30. [30]

    John Wiley & Sons, 2019

    Roderick JA Little and Donald B Rubin.Statistical analysis with missing data. John Wiley & Sons, 2019

    2019

  31. [31]

    The elements of statistical learning: data mining, inference, and prediction, 2009

    Trevor Hastie. The elements of statistical learning: data mining, inference, and prediction, 2009

    2009

  32. [32]

    Ian T Jolliffe and Jorge Cadima. Principal component analysis: a review and recent devel- opments.Philosophical transactions of the royal society A: Mathematical, Physical and Engineering Sciences, 374(2065):20150202, 2016

    2065

  33. [33]

    Image processing and analysis methods for the adolescent brain cognitive development study.Neuroimage, 202:116091, 2019

    Donald J Hagler Jr, SeanN Hatton, M Daniela Cornejo, Carolina Makowski, Damien A Fair, Anthony Steven Dick, Matthew T Sutherland, BJ Casey, Deanna M Barch, Michael P Harms, et al. Image processing and analysis methods for the adolescent brain cognitive development study.Neuroimage, 202:116091, 2019

    2019

  34. [34]

    Freesurfer.Neuroimage, 62(2):774–781, 2012

    Bruce Fischl. Freesurfer.Neuroimage, 62(2):774–781, 2012

    2012

  35. [35]

    Quantitative assessment of structural image quality.Neuroimage, 169:407–418, 2018

    Adon FG Rosen, David R Roalf, Kosha Ruparel, Jason Blake, Kevin Seelaus, Lakshmi P Villa, Rastko Ciric, Philip A Cook, Christos Davatzikos, Mark A Elliott, et al. Quantitative assessment of structural image quality.Neuroimage, 169:407–418, 2018

    2018

  36. [36]

    Principal components analysis corrects for stratification in genome-wide association studies.Nature genetics, 38(8):904–909, 2006

    Alkes L Price, Nick J Patterson, Robert M Plenge, Michael E Weinblatt, Nancy A Shadick, and David Reich. Principal components analysis corrects for stratification in genome-wide association studies.Nature genetics, 38(8):904–909, 2006

    2006

  37. [37]

    Methods and considerations for longitudinal structural brain imaging analysis across development.Developmental cognitive neuroscience, 9:172–190, 2014

    Kathryn L Mills and Christian K Tamnes. Methods and considerations for longitudinal structural brain imaging analysis across development.Developmental cognitive neuroscience, 9:172–190, 2014

    2014

  38. [38]

    Regression models and life-tables.Journal of the royal statistical society: Series B (methodological), 34(2):187–202, 1972

    David R Cox. Regression models and life-tables.Journal of the royal statistical society: Series B (methodological), 34(2):187–202, 1972

    1972

  39. [39]

    Regression shrinkage and selection via the lasso.Journal of the Royal Statistical Society Series B: Statistical Methodology, 58(1):267–288, 1996

    Robert Tibshirani. Regression shrinkage and selection via the lasso.Journal of the Royal Statistical Society Series B: Statistical Methodology, 58(1):267–288, 1996

    1996

  40. [40]

    Regularization paths for cox’s proportional hazards model via coordinate descent.Journal of statistical software, 39:1–13, 2011

    Noah Simon, Jerome H Friedman, Trevor Hastie, and Rob Tibshirani. Regularization paths for cox’s proportional hazards model via coordinate descent.Journal of statistical software, 39:1–13, 2011

    2011

  41. [41]

    Stability selection.Journal of the Royal Statistical Society: Series B (Statistical Methodology), 72(4):417–473, 2010

    Nicolai Meinshausen and Peter Bühlmann. Stability selection.Journal of the Royal Statistical Society: Series B (Statistical Methodology), 72(4):417–473, 2010

    2010

  42. [42]

    Multitask learning.Machine learning, 28(1):41–75, 1997

    Rich Caruana. Multitask learning.Machine learning, 28(1):41–75, 1997

    1997

  43. [43]

    An Overview of Multi-Task Learning in Deep Neural Networks

    Sebastian Ruder. An overview of multi-task learning in deep neural networks.arXiv preprint arXiv:1706.05098, 2017

    work page internal anchor Pith review arXiv 2017

  44. [44]

    A survey on multi-task learning.IEEE transactions on knowledge and data engineering, 34(12):5586–5609, 2021

    Yu Zhang and Qiang Yang. A survey on multi-task learning.IEEE transactions on knowledge and data engineering, 34(12):5586–5609, 2021

    2021

  45. [45]

    A nonstochastic interpretation of reported significance levels

    David Freedman and David Lane. A nonstochastic interpretation of reported significance levels. Journal of Business & Economic Statistics, 1(4):292–298, 1983. 25

    1983

  46. [46]

    Root-n-consistent semiparametric regression.Econometrica: journal of the Econometric Society, pages 931–954, 1988

    Peter M Robinson. Root-n-consistent semiparametric regression.Econometrica: journal of the Econometric Society, pages 931–954, 1988

    1988

  47. [47]

    Double/debiased machine learning for treatment and structural parameters, 2018

    Victor Chernozhukov, Denis Chetverikov, Mert Demirer, Esther Duflo, Christian Hansen, Whitney Newey, and James Robins. Double/debiased machine learning for treatment and structural parameters, 2018. 26

    2018