A Machine Learning-Based Test for Predicting Response to Psoriasis Biologics

Main Article Content

Jerry Bagel
Yipeng Wang
Paul Montgomery, III
Christian Abaya
Eric Andrade
Courtney Boyce
Tatiana Tomich
Byung-In Lee
David Pariser
Alan Menter
Tobin Dickerson

Keywords

psoriasis, biologics, precision medicine, machine learning

Abstract

Objective: This study was designed to develop and prospectively validate a machine learning based algorithm that could predict patient response to the most common biologic drug classes used in the management of psoriasis patients. This type of tool would allow clinicians to have greater confidence that a given patient will respond to a specific drug class, which could lead to improved health outcomes and reduced wasted healthcare spend.


Methods: Patients were enrolled into one of two observational studies (STAMP studies) where dermal biomarker patches (DBPs) were applied at baseline prior to drug exposure, followed by clinical evaluations at 12 weeks after exposure. PASI measurements were made at baseline and 12 weeks to evaluate clinical response to a clinical phenotype. Responders were defined as those who reached PASI75 at 12 weeks. The transcriptomes obtained from the DBPs were sequenced and analyzed to derive and/or validate classifiers for each biologic class, which were then combined to yield predictive responses for all three biologic drug classes (IL-23i, IL-17i, and TNFai).


Results: A total of 242 psoriasis patients were enrolled in these studies, including 118 patients (49.6%) treated with IL-23i, 79 patients (33.2%) treated with IL-17i, 35 patients (14.7%) treated with TNFai, and 6 patients (2.5%) treated with IL-12/23i. The IL-23i predictive classifier was developed from the earlier enrolled patients and independently validated with the latter enrolled patients. IL-17i and TNFai predictive classifiers were developed using publicly available datasets and independently validated with patients from the STAMP studies. In the independent validation, positive predictive values for three classifiers (IL-23i, IL-17i, and TNFai) were 93.1%, 92.3% and 85.7% respectively. Over the entire cohort, 99.5% of patients were predicted to respond to at least one drug class.


Conclusion: This study demonstrates the power of using baseline dermal biomarkers and machine learning methods as applied to the prediction of psoriasis biologic prior to drug exposure. Using this test, patients, physicians, and the health care system all can benefit in distinct ways. Precision medicine can be realized for individual patients as most will likely respond to their prescribed biologic the first time. Physicians can prescribe these drugs with increased confidence, and the healthcare system will realize lower net costs as well as greatly reduced wasted spend by significantly improving initial response rates to expensive biologic therapeutics.

References

1. Hamburg MA, Collins FS. The path to personalized medicine. N Engl J Med. 2010; 363:301-304. doi: 10.1056/NEJMp1006304

2. Schilsky RL. Personalized medicine in oncology: the future is now. Nat Rev Drug Discov. 2010;9(5):363-366. doi: 10.1038/nrd3181

3. Webster RM, Mentzer SE. The malignant melanoma landscape. Nat Rev Drug Discov. 2014;13(7):491-492. doi:10.1038/nrd4326

4. Menter A, Strober BE, Kaplan DH, et al. Joint AAD-NPF guidelines of care for the management and treatment of psoriasis with biologicsd. J Am Acad Dermatol. 2019;80:1029-1072. doi:10.1016/j.jaad.2018.11.057

5. Raju SS. Psoriasis and lasting implications. Expert Rev Clin Immunol. 2014;10(2):175-177. doi:10.1586/1744666X.2014.872033

6. Nograles KE, Davidovici B, Krueger JG. New insights in the Immunologic Basis of Psoriasis. Semin Cutan Med Surg. 2010;29(1):3-9. doi:10.1016/j.sder.2010.03.001

7. Kamata M, Tada Y. Safety of biologics in psoriasis. J Dermatol. 2018;45(3):279-286. doi:10.1111/1346-8138.14096

8. Strober, BE, van der Walt JM, Armstrong AW, et al. Clinical goals and barriers to effective psoriasis care. Dermatol Ther (Heidelb) 2019;9:5-18. doi: 10.1007/s13555-018-0279-5

9. Menter A, Papp KA, Gooderham M, et al. Drug survival of biologic therapy in a large, disease-based registry of patients with psoriasis: results from the Psoriasis Longitudinal Assessment and Registry (PSOLAR). J Eur Acad Dermatol Venereol JEADV. 2016;30(7):1148-1158. doi:10.1111/jdv.13611

10. Enos CW, O'Connell KA, Harrison RW, et al. Psoriasis severity, comorbidities, and treatment response differ among geographic regions in the United States. JID Innovations. 2021;1(2):100025. doi:10.1016/j.xjidi.2021.100025

11. Wu JJ, Feldman S, Rastogi S, et al. Comparison of the cost-effectiveness of biologic drugs used for moderate-to-severe psoriasis treatment in the United States. J Dermatolog Treat. 2018;29(8):769-774. doi: 10.1080/09546634.2018.1466022

12. Ibrahim SF, Taft BJ, Wang Y, et al. Minimally invasive skin transcriptome extraction using a dermal biomarker patch. submitted.

13. Tomalin LE, Russell CB, Garcet S, et al. Short-term transcriptional response to IL-17 receptor-A antagonism in the treatment of psoriasis. J Allergy Clin Immunol. 2020;145(3):922-932. doi:10.1016/j.jaci.2019.10.041

14. Wang Y, Lee B-I, Montgomery III, P, et al. Efficient prediction of response to psoriasis biologics using a machine learning classifier. submitted.

15. Correa da Rosa, J, Kim J, Tian S, et al. Shrinking the psoriasis assessment gap: early gene-expression profiling accurately predicts response to long-term treatment. J Invest Dermatol. 2017;137(2):305-312. doi:10.1016/j.jid.2016.09.015

16. Zaba LC, Suarez-Farinas M, Fuentes-Duculan J, et al. Effective treatment of psoriasis with etanercept is linked to suppression of IL-17 signaling, not immediate response TNF genes. J Allergy Clin Immunol. 2009; 124(5):1022–10.e1-395. doi:10.1016/j.jaci.2009.08.046

17. Brodmerkel C, Li K, Garcet S, et al. Modulation of inflammatory gene transcripts in psoriasis vulgaris: differences between ustekinumab and etanercept. J Allergy Clin Immunol. 2019;143(5):1965-1969. doi:10.1016/j.jaci.2019.01.017

18. Foulkes AC, Watson DS, Carr DF, et al. A framework for multi-omic prediction of treatment response to biologic therapy for psoriasis. J Invest Dermatol. 2019;139(1):100-107. doi:10.1016/j.jid.2018.04.041

19. Ainali C, Valeyev N, Perera G, et al. Transcriptome classification reveals molecular subtypes in psoriasis. BMC Genomics. 2012;13:472. doi:10.1186/1471-2164-13-472

20. Jeong SH, Kim HJ, Jang Y, et al. Egr-1 is a key regulator of IL-17A-induced psoriasin upregulation in psoriasis. Exp Dermatol. 2014;23(12):890-5. doi:10.1111/exd.12554

21. Van Voorhees AS, Mason MA, Harrold LR, et al. Characterization of insufficient responders to anti-tumor necrosis factor therapies in patients with moderate to severe psoriasis: real-world data from the US Corrona Psoriasis Registry. J Dermatolog Treat. 2021;32(3):302-309. doi: 10.1080/09546634.2019.1656797

22. Lockshin B, Cronin A, Harrison RW, et al. Drug survival of ixekizumab, TNF inhibitors, and other IL-17 inhibitors in real-world patients with psoriasis: The Corrona Psoriasis Registry. Dermatol Ther. 2021;34(2):e14808. doi:10.1111/dth.14808

23. Bewley A, Hamptom PJ, Hughes J, et al. Secukinumab treatment results in sustained improvement in aPASI and drug survival: 24-month follow-up from the British Association of Dermatologists Biologics and Immunomodulators Register (BADBIR). AAD 2020. P18239

Similar Articles

You may also start an advanced similarity search for this article.

Most read articles by the same author(s)

1 2 3 > >>