Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 45 min ago
Peer-reviewedCC BYFrontiers in Digital Health

Utilizing AI for decision support in severe asthma biological treatment

  • Bassam Mahboub1
  • Sameer Alawnah2
  • Salam Dhou2
  • Piotr Kuna3
  • Celine Bergeron4
  • Celine Bergeron5
  • Riyad Al-Lehebi6
  • Riyad Al-Lehebi7
  • Najla Alnahadi8
  • Noura Alhousani8
  • Assim Sagahyroon2
  • Asharaf Alzabi9
3 more authors
  • Asharaf Alzabi10
  • Laila Salameh1
  • Laila Salameh11
11 affiliations
  1. 1Pulmonary Medicine, Dubai Health, Dubai, United Arab Emirates
  2. 2Department of Computer Science and Engineering, American University of Sharjah, Sharjah, United Arab Emirates
  3. 3Division of Internal Medicine Asthma and Allergy, Medical University of Lodz, Lodz, Poland
  4. 4Department of Medicine, Centre for Lung Health, Vancouver General Hospital, Vancouver, Canada
  5. 5Department of Medicine, University of British Columbia, Vancouver, Canada
  6. 6Department of Pulmonology, King Fahad Medical City, Riyadh, Saudi Arabia
  7. 7College of Medicine, Alfaisal University, Riyadh, Saudi Arabia
  8. 8Respiratory Medicine Division, Zayed Military Hospital, Abu Dhabi, United Arab Emirates
  9. 9Department of Internal Medicine, College of Medicine and Health Sciences, United Arab University, Alain, United Arab Emirates
  10. 100Pulmonary Department, Mediclinic, Abu Dhabi, United Arab Emirates
  11. 111Research & Graduate Studies Department, Mohammed Bin Rashid University of Medicine and Health Sciences, Dubai Health, Dubai, United Arab Emirates
Read full textPDFDOICite

Abstract

BackgroundSevere asthma remains a major clinical challenge because of disease heterogeneity and variable response to biologic therapies. Despite the availability of clinical guidelines, clinicians often rely on a trial-and-error approach when selecting biologic treatments. We aimed to develop and validate an artificial intelligence (AI)-driven decision support system (DSS) to predict treatment response and support personalized biologic selection in severe asthma.MethodsA retrospective multinational cohort of 801 patients with severe asthma from the United Arab Emirates, Saudi Arabia, Poland, and Canada was analyzed. Random Forest (RF) models were developed to predict clinical improvement, and Recursive Feature Elimination was used to identify the most informative predictors. Counterfactual simulation was subsequently applied to evaluate alternative biologic treatment strategies.ResultsThe most important predictors of treatment response were Asthma Control Test (ACT) score, eosinophil count, and type 2 inflammatory comorbidities, particularly nasal polyposis and sinusitis. The optimized RF model improved specificity from 33.33% to 66.67% and increased overall accuracy from 78.57% to 82.14%. Counterfactual simulations demonstrated the model's ability to identify non-responder phenotypes and estimate alternative biologic options with higher predicted probabilities of improvement, including a 62% probability of improvement following a switch from anti-IgE therapy to anti-IL-5R therapy in selected patients.ConclusionThis study demonstrates the potential of AI-driven clinical decision support to support personalized biologic selection in severe asthma. By improving identification of likely non-responders and simulating alternative treatment pathways, the proposed framework may help reduce ineffective treatment exposure, improve clinical decision-making, and advance precision medicine in severe asthma management.

Related

  1. Shared Decision-Making and Decision Support in Advanced Chronic Kidney Disease: A Systematic Review of Models, Treatment Pathways, and Patient-Centered Outcomes
    Awais Naeem, Zulfiqar Ashraf, Sajjad Ali +8
    CureusPeer-reviewedCC BYFull textGeneral medicineEurope PMC
  2. Developing a shared decision-making intervention to support choices about prophylactic cranial irradiation treatment for small-cell lung cancer: a study protocol.
    Katie Dixon, Marianne Aznar, Hilary Bekker +5
    BMJ openPeer-reviewedCC BYFull textGeneral medicineEurope PMCCrossref
  3. Development and usability testing of a machine learning clinical decision support tool for suggesting etiologies and treatment of clinical deterioration
    Oliver T. Nguyen, Douglas A. Wiegmann, James Haddad +9
    Journal of critical carePeer-reviewedLicence not statedFull textGeneral medicinePMC
  4. Artificial Intelligence in Eye Disease: A Systematic Review of Screening, Diagnosis, Prognosis, Treatment-Response Prediction, and Clinical Decision Support
    Manal M. Alharbi, Emtenan M. Alharbi, Alanoud Suliman Alsalamah +4
    Journal of Clinical MedicinePeer-reviewedCC BY 4.0Full textMedical imaging & radiologyCrossrefEurope PMC
  5. Utilizing a Structured Flowchart to Improve Breastfeeding Support in the Golden Hour
    Stephanie Gedzyk-Nieman, Gretchen White, Nathan Wilson +1
    The Journal of Perinatal EducationPeer-reviewedLicence not statedFull textEpidemiology & public healthPMC

Cite

BibTeXRIS
BibTeX
@article{mahboub2026utilizing,
  title = {{Utilizing AI for decision support in severe asthma biological treatment}},
  author = {Bassam Mahboub and Sameer Alawnah and Salam Dhou and Piotr Kuna and Celine Bergeron and Celine Bergeron and Riyad Al-Lehebi and Riyad Al-Lehebi and Najla Alnahadi and Noura Alhousani and Assim Sagahyroon and Asharaf Alzabi and Asharaf Alzabi and Laila Salameh and Laila Salameh},
  journal = {Frontiers in Digital Health},
  year = {2026},
  month = oct,
  doi = {10.3389/fdgth.2026.1939100},
  url = {https://doi.org/10.3389/fdgth.2026.1939100},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Utilizing AI for decision support in severe asthma biological treatment
AU  - Bassam Mahboub
AU  - Sameer Alawnah
AU  - Salam Dhou
AU  - Piotr Kuna
AU  - Celine Bergeron
AU  - Celine Bergeron
AU  - Riyad Al-Lehebi
AU  - Riyad Al-Lehebi
AU  - Najla Alnahadi
AU  - Noura Alhousani
AU  - Assim Sagahyroon
AU  - Asharaf Alzabi
AU  - Asharaf Alzabi
AU  - Laila Salameh
AU  - Laila Salameh
PY  - 2026
DA  - 2026/10/30
JO  - Frontiers in Digital Health
DO  - 10.3389/fdgth.2026.1939100
UR  - https://doi.org/10.3389/fdgth.2026.1939100
AB  - BackgroundSevere asthma remains a major clinical challenge because of disease heterogeneity and variable response to biologic therapies. Despite the availability of clinical guidelines, clinicians often rely on a trial-and-error approach when selecting biologic treatments. We aimed to develop and validate an artificial intelligence (AI)-driven decision support system (DSS) to predict treatment response and support personalized biologic selection in severe asthma.MethodsA retrospective multinational cohort of 801 patients with severe asthma from the United Arab Emirates, Saudi Arabia, Poland, and Canada was analyzed. Random Forest (RF) models were developed to predict clinical improvement, and Recursive Feature Elimination was used to identify the most informative predictors. Counterfactual simulation was subsequently applied to evaluate alternative biologic treatment strategies.ResultsThe most important predictors of treatment response were Asthma Control Test (ACT) score, eosinophil count, and type 2 inflammatory comorbidities, particularly nasal polyposis and sinusitis. The optimized RF model improved specificity from 33.33% to 66.67% and increased overall accuracy from 78.57% to 82.14%. Counterfactual simulations demonstrated the model's ability to identify non-responder phenotypes and estimate alternative biologic options with higher predicted probabilities of improvement, including a 62% probability of improvement following a switch from anti-IgE therapy to anti-IL-5R therapy in selected patients.ConclusionThis study demonstrates the potential of AI-driven clinical decision support to support personalized biologic selection in severe asthma. By improving identification of likely non-responders and simulating alternative treatment pathways, the proposed framework may help reduce ineffective treatment exposure, improve clinical decision-making, and advance precision medicine in severe asthma management.
SN  - 2673-253X
ER  -