Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Aug 24:6:1229609.
doi: 10.3389/frai.2023.1229609. eCollection 2023.

A risk identification model for detection of patients at risk of antidepressant discontinuation

Ali Zolnour  1 , Christina E Eldredge  2 , Anthony Faiola  3 , Yadollah Yaghoobzadeh  1 , Masoud Khani  4 , Doreen Foy  5 , Maxim Topaz  6   7 , Hadi Kharrazi  8 , Kin Wah Fung  9 , Paul Fontelo  9 , Anahita Davoudi  7 , Azade Tabaie  10 , Scott A Breitinger  11 , Tyler S Oesterle  11 , Masoud Rouhizadeh  12 , Zahra Zonnor  13 , Hans Moen  14 , Timothy B Patrick  4 , Maryam Zolnoori  6   11
Affiliations

A risk identification model for detection of patients at risk of antidepressant discontinuation

Ali Zolnour et al. Front Artif Intell. .

Abstract

Purpose: Between 30 and 68% of patients prematurely discontinue their antidepressant treatment, posing significant risks to patient safety and healthcare outcomes. Online healthcare forums have the potential to offer a rich and unique source of data, revealing dimensions of antidepressant discontinuation that may not be captured by conventional data sources.

Methods: We analyzed 891 patient narratives from the online healthcare forum, "askapatient.com," utilizing content analysis to create PsyRisk-a corpus highlighting the risk factors associated with antidepressant discontinuation. Leveraging PsyRisk, alongside PsyTAR [a publicly available corpus of adverse drug reactions (ADRs) related to antidepressants], we developed a machine learning-driven algorithm for proactive identification of patients at risk of abrupt antidepressant discontinuation.

Results: From the analyzed 891 patients, 232 reported antidepressant discontinuation. Among these patients, 92% experienced ADRs, and 72% found these reactions distressful, negatively affecting their daily activities. Approximately 26% of patients perceived the antidepressants as ineffective. Most reported ADRs were physiological (61%, 411/673), followed by cognitive (30%, 197/673), and psychological (28%, 188/673) ADRs. In our study, we employed a nested cross-validation strategy with an outer 5-fold cross-validation for model selection, and an inner 5-fold cross-validation for hyperparameter tuning. The performance of our risk identification algorithm, as assessed through this robust validation technique, yielded an AUC-ROC of 90.77 and an F1-score of 83.33. The most significant contributors to abrupt discontinuation were high perceived distress from ADRs and perceived ineffectiveness of the antidepressants.

Conclusion: The risk factors identified and the risk identification algorithm developed in this study have substantial potential for clinical application. They could assist healthcare professionals in identifying and managing patients with depression who are at risk of prematurely discontinuing their antidepressant treatment.

Keywords: adverse drug events; antidepressant discontinuation; antidepressant effectiveness; content analysis; machine learning; online healthcare forums.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. The handling editor LW declared a shared affiliation with author DF at the time of the review. The reviewer LT declared a shared affiliation with the authors MK and TP at the time of the review.

Figures

Figure 1
Figure 1
A schematic view of the methodology of the study.
Figure 2
Figure 2
Top five ADRs reported for SSRI and SNRI antidepressants.
Figure 3
Figure 3
Most informative ADRs identified using JMIM feature selection method.
Figure 4
Figure 4
(A, B) The most informative features that influence patients' non-adherence behavior to antidepressants, as identified by the Extra-Trees and Random Forest classifiers, respectively.
Figure 5
Figure 5
Performance of the Extra-Trees classifier (best performing model) and the added value of qualitative risk factors, demographic information, and type of ADRs. (A) ROC. (B) Precision vs. recall. (C) Cumulative gains curve. (D) Positive predictive value. (E) Sensitivity. (F) Prediction density.
See this image and copyright information in PMC

References

    1. Aikens J. E., Nease D. E., Klinkman M. S. (2008). Explaining patients' beliefs about the necessity and harmfulness of antidepressants. Ann. Fam. Med. 6, 23–29. 10.1370/afm.759 - DOI - PMC - PubMed
    1. Anderson C., Roy T. (2013). Patient experiences of taking antidepressants for depression: a secondary qualitative analysis. Res. Soc. Adm. Pharm. 9, 884–902. 10.1016/j.sapharm.2012.11.002 - DOI - PubMed
    1. Ben-Hur I., Weston J. (2010). A user's guide to support vector machines, in Data Mining Techniques for the Life Sciences, eds Carugo O., Eisenhaber F. (Berlin: Springer; ), 223–239. 10.1007/978-1-60327-241-4_13 - DOI - PubMed
    1. Bennasar M., Hicks Y., Setchi R. (2015). Feature selection using joint mutual information maximisation. Expert Syst. Appl. 42, 8520–8532. 10.1016/j.eswa.2015.07.007 - DOI
    1. Charan J., Biswas T. (2013). How to calculate sample size for different study designs in medical research? Indian J. Psychol. Med. 35, 121. 10.4103/0253-7176.116232 - DOI - PMC - PubMed

LinkOut - more resources