Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 21, 2021Frontiers in Computational NeuroscienceOpen Access

Accurate Prediction of Children's ADHD Severity Using Family Burden Information: A Neural Lasso Approach

View Full Paper
Ask AI
Bookmark
Share

Key result

Deep lasso algorithm predicts parent-assessed child inattention from seven family items with ~0.34 correlation.

  • n=73

Why the study?

To introduce the deep lasso algorithm and determine whether it can predict symptom severity in children with ADHD using family burden, family functioning, parental satisfaction, and parental mental health scales.

Can the deep lasso algorithm predict ADHD symptom severity in children using family burden information?

Population

Children with ADHD

Comparison

Deep lasso (dlasso) vs traditional statistical linear lasso

Authors

JLJuan C. LariaDDDavid Delgado‐GómezIPInmaculada Peñuelas‐Calvo

Discussion

Loading...

Member takes

Overview

May inform brief family-based ADHD screening; hypothesis-generating for machine learning in pediatric psychiatry.

Study Design

Type

Observational (n=73)

Multicenter

No

Structured PICO

Can the deep lasso algorithm predict ADHD symptom severity in children using family burden information?

P
Population
Children with ADHD and their parents
I
Intervention
Deep lasso algorithm (dlasso)
C
Comparator
Traditional lasso algorithm
O
Outcome
Prediction of parents' assessment of the severity of their children's inattentionsurrogate

Main Result

Absolute Event Rate: 0.34% vs -0.01%

The deep lasso algorithm effectively predicts ADHD severity in children using a small subset of family burden and parental satisfaction items.

Limitations

  • Small sample size of 73 children
  • The algorithm was unable to accurately estimate the severity of children's hyperactivity/impulsivity
  • Inability to determine whether parental stress is caused by children's symptoms or external factors

Cite This Study

Laria et al. (2021) conducted an observational in Attention-deficit hyperactivity disorder (ADHD) (n=73). Deep lasso (dlasso) algorithm vs. Multiple linear regression was evaluated on Correlation between predicted and actual SWAN inattention subscale scores. The deep lasso algorithm predicted parents' assessment of their children's inattention severity using only seven items related to family burden and satisfaction, achieving an average correlation of 0.34.

synapsesocial.com/papers/6a0d53451e1a6dfdb4ba787ehttps://doi.org/10.3389/fncom.2021.674028
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1The Zarit Burden Interview2001 · 1,725 citations
  2. 2Early detection and intervention for attention-deficit/hyperactivity disorder2011 · 153 citations
  3. 3Prevalence of Attention-Deficit/Hyperactivity Disorder: A Systematic Review and Meta-analysis2015 · 1,984 citations