Introducing the AltPAI and EnsPAI as Alternatives to the Personalized Advantage Index

Abstract

Background: The Personalized Advantage Index (PAI) has evolved into a standard framework to identify the individually optimal treatment from available alternatives in mental health and beyond. The traditional PAI compares a patient’s predicted post-treatment symptom scores across treatment alternatives to identify the treatment with the most favorable predicted score. However, clinicians may wish to select the treatment that maximizes that patient’s predicted probability of achieving a clinically defined outcome, such as remission. This study presents an Alternative PAI (AltPAI) optimized for this purpose and evaluates its performance. Methods: We used routine care data (n = 1,264) to implement the traditional PAI and AltPAI using random forests. The indices were compared regarding the benefit for patients in terms of dimensional improvement and remission. Exploratively, the PAI and AltPAI were combined into an ensemble (EnsPAI). Results: The AltPAI outperformed the PAI descriptively but not significantly, yielding higher symptom change (cohens d = 0.09) and remission probability (OR = 1.32) for optimally treated patients with higher index values. Regarding symptom improvement, the PAI performed worse than chance. The EnsPAI was the only algorithm to perform significantly better than chance in terms of symptom remission. Conclusions: The AltPAI and EnsPAI demonstrated performance that was generally descriptively superior to the PAI. The approaches should therefore be investigated in combination with the PAI in future treatment stratification analyses. Additionally, more advanced implementations of the EnsPAI are discussed that would allow the ensemble to be calibrated on the error of the base indices, potentially increasing prediction performance.

Bridging Conventional and Natural Therapies for Recurrent Aphthous Stomatitis: A Systematic Review and Meta-Analysis of Triamcinolone and Non-Steroidal Alternatives
Rana A. Elbeshbeishy, Biji Thomas George, Mohamed Anas Patni +3
Biomedicines1 Oct 2026Peer-reviewedCC BYFull textGeneral medicineEurope PMC
Introducing the Climate Change Special Issue.
Gary Gaddis, Shahram Lotfipour
The western journal of emergency medicine24 Sep 2026Peer-reviewedCC BYFull textPharmacology & toxicologyEurope PMC
Introducing Aaron Y. Lee and Cecilia S. Lee, the 2026 Recipients of the Cogan Award
Emily Y. Chew
Investigative ophthalmology & visual science1 Oct 2026Peer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMCPMC
Introducing Geeta K. Vemuganti: The 2025 Recipient of the Weisenfeld Award
Martine J. Jager, Sarah E. Coupland, Hans E. Grossniklaus
Investigative ophthalmology & visual science1 Oct 2026Peer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMC
Introducing Infrastructure as Code for deployment and governance of medical AI: A case study
M. Vogel, N. Reuter, S. Ruf +6
medRxiv12 Oct 2026PreprintAll rights reservedFull textEpidemiology & public healthmedRxiv

Cite

BibTeX RIS

BibTeX

@misc{jacobs2026introducing,
  title = {{Introducing the AltPAI and EnsPAI as Alternatives to the Personalized Advantage Index}},
  author = {Niklas Jacobs and Brian Schwartz and Charlotte Meinke and Werner W. Wittmann and Wolfgang Lutz and Kevin Hilbert},
  howpublished = {PsyArXiv},
  year = {2026},
  month = oct,
  doi = {10.31234/osf.io/ztb5a_v1},
  url = {https://osf.io/preprints/psyarxiv/ztb5a_v1/},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Introducing the AltPAI and EnsPAI as Alternatives to the Personalized Advantage Index
AU  - Niklas Jacobs
AU  - Brian Schwartz
AU  - Charlotte Meinke
AU  - Werner W. Wittmann
AU  - Wolfgang Lutz
AU  - Kevin Hilbert
PY  - 2026
DA  - 2026/10/20
PB  - PsyArXiv
DO  - 10.31234/osf.io/ztb5a_v1
UR  - https://osf.io/preprints/psyarxiv/ztb5a_v1/
AB  - Background: The Personalized Advantage Index (PAI) has evolved into a standard framework to identify the individually optimal treatment from available alternatives in mental health and beyond. The traditional PAI compares a patient’s predicted post-treatment symptom scores across treatment alternatives to identify the treatment with the most favorable predicted score. However, clinicians may wish to select the treatment that maximizes that patient’s predicted probability of achieving a clinically defined outcome, such as remission. This study presents an Alternative PAI (AltPAI) optimized for this purpose and evaluates its performance. Methods: We used routine care data (n = 1,264) to implement the traditional PAI and AltPAI using random forests. The indices were compared regarding the benefit for patients in terms of dimensional improvement and remission. Exploratively, the PAI and AltPAI were combined into an ensemble (EnsPAI). Results: The AltPAI outperformed the PAI descriptively but not significantly, yielding higher symptom change (cohens d = 0.09) and remission probability (OR = 1.32) for optimally treated patients with higher index values. Regarding symptom improvement, the PAI performed worse than chance. The EnsPAI was the only algorithm to perform significantly better than chance in terms of symptom remission. Conclusions: The AltPAI and EnsPAI demonstrated performance that was generally descriptively superior to the PAI. The approaches should therefore be investigated in combination with the PAI in future treatment stratification analyses. Additionally, more advanced implementations of the EnsPAI are discussed that would allow the ensemble to be calibrated on the error of the base indices, potentially increasing prediction performance.
ER  -

Abstract

Related

Cite