Knowledge Graphs and Large Language Models for Adult ADHD

Knowledge Graphs and  Large Language Models  for Adult ADHD
Slide Note
Embed
Share

In-depth exploration of stimulants for adult ADHD, focusing on managing insomnia side effects of methylphenidate. Leveraging AI for efficient information retrieval across medical resources like PubMed, Clinical Trials, and DrugBank. Delve into alternative stimulant options with less impact on sleep patterns.

  • Knowledge Graphs
  • Adult ADHD
  • Insomnia
  • Stimulants
  • Medical Resources

Uploaded on Feb 14, 2025 | 0 Views


Download Presentation

Please find below an Image/Link to download the presentation.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.

You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.

E N D

Presentation Transcript


  1. Knowledge Graphs and Large Language Models for Adult ADHD GRIGORIS ANTONIOU LEEDS BECKETT UNIVERSITY

  2. Motivation Motivation I ve been prescribed with methylphenidate but recently I ve been experiencing severe insomnia. This is a common side effect of methylphenidate. Are there stimulants with similar effects but less frequent reports of insomnia? 1. Web Search (not so reliable) 2. Publications on stimulants and insomnia 58 results only on adult ADHD! 3. Clinical Trials that tested stimulants on adults with ADHD (18 results) 4. Medication with similar response but less effects on sleep (sources?)

  3. I need HELP! Answering this question requires plenty of manual effort. Retrieve and link information from different medical resources. I ve been prescribed with methylphenidate but recently I ve been experiencing severe insomnia. This is a common side effect of methylphenidate. Are there stimulants with similar effects but less frequent reports of insomnia? Can AI-powered methods automate this process? 1. Web Search (not so reliable) 2. Publications on stimulants and insomnia 58 results only on adult ADHD! 3. Clinical Trials that tested stimulants on adults with ADHD (18 results) 4. Medication with similar response but less effects on sleep (sources?) ADHD-specific Knowledge Graph

  4. KGs in Medical Sciences KGs in Medical Sciences A collection of interlinked concepts, relations and events Extensively used in medical domains Knowledge representation Integration of multiple medical resources Searching about things not strings Knowledge discovery, denoising, forecasting and much more

  5. Data Resources for ADHD Data Resources for ADHD- -KG KG PubMed Publications in biomedical and life sciences Clinical trials Repository of medical studies DrugBank Detailed collection of drug data with drug target information. SIDER Collection of recorded adverse effects caused by marketed medicine MeSH Extensive thesaurus of medical concepts

  6. Information Linking Information Linking Direct: explicit references to resources Clinical trials might cite publications (vice versa) Resources contain MeSH references Publication: PID-123 DrugBank Drug-id: ID-1 Name: methylphenidate MeSH: methylphenidate SIDER C. Trial: CT-1 MeSH: methylphenidate SIDER-id: ID-3 Name: methylphenidate Ext. reference: Drug-id: ID-1 Side effect: Insomnia, 15% Ext. references: PID-123

  7. ADHD ADHD- -KG Architecture KG Architecture

  8. Demonstration Demonstration - - Comorbidities Comorbidities Most frequent comorbid mental disorders found in ADHD literature Traverse MeSH to retrieve labels of mental disorders Filter publications that contain explicit references or semantic annotations referring to disorders

  9. Demonstration - Sleep Deprivation & Stimulants

  10. Demonstration Demonstration - - Medicines & Receptors Medicines & Receptors Drug Action Target #Sodium-dependent dopamine transporter #Sodium-dependent noradrenaline transporter #Sodium-dependent noradrenaline transporter #G protein-activated inward rectifier potassium channel 1 #Cocaine- and amphetamine-regulated transcript protein # Trace amine-associated receptor 1 # Sodium-dependent noradrenaline transporter # Alpha adrenergic receptor # Beta adrenergic receptor #Synaptic vesicular amine transporter # Monoamine oxidase # Amine oxidase [flavin-containing] B #Sodium-dependent serotonin transporter #NMDA receptor #Kappa-type opioid receptor Methylphenidate inhibitor Atomoxetine inhibitor Amphetamine agonist Amphetamine inhibitor Atomoxetine Atomoxetine Atomoxetine binder blocker partial agonist

  11. GPT & Friends GPT & Friends - - Large Language Models Large Language Models Can engage in conversations with humans Can be used for decision support and decision making LLM in medicine Can potentially assist clinicians in decision making Can potentially provide advice to patients But is it safe?

  12. Validation of LLM & ADHD Validation of LLM & ADHD- -KG KG 1. Collect relevant queries from domain experts Medical queries (medical researchers & clinicians) Training queries (for doctors training to specialise on adult ADHD) Lay person queries (for the general public) 2. Seek answers from various LLMs and from the ADHD-KG 3. Get domain experts evaluate the answers

  13. Outlook Outlook Combination of LLM and KG technology LLM offers interface and can generate good answers KG provides grounding and evidence to ensure correctness

More Related Content