1
|
Poweleit EA, Vaughn SE, Desta Z, Dexheimer JW, Strawn JR, Ramsey LB. Machine Learning-Based Prediction of Escitalopram and Sertraline Side Effects With Pharmacokinetic Data in Children and Adolescents. Clin Pharmacol Ther 2024; 115:860-870. [PMID: 38297828 PMCID: PMC11046530 DOI: 10.1002/cpt.3184] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Accepted: 01/04/2024] [Indexed: 02/02/2024]
Abstract
Selective serotonin reuptake inhibitors (SSRI) are the first-line pharmacologic treatment for anxiety and depressive disorders in children and adolescents. Many patients experience side effects that are difficult to predict, are associated with significant morbidity, and can lead to treatment discontinuation. Variation in SSRI pharmacokinetics could explain differences in treatment outcomes, but this is often overlooked as a contributing factor to SSRI tolerability. This study evaluated data from 288 escitalopram-treated and 255 sertraline-treated patients ≤ 18 years old to develop machine learning models to predict side effects using electronic health record data and Bayesian estimated pharmacokinetic parameters. Trained on a combined cohort of escitalopram- and sertraline-treated patients, a penalized logistic regression model achieved an area under the receiver operating characteristic curve (AUROC) of 0.77 (95% confidence interval (CI): 0.66-0.88), with 0.69 sensitivity (95% CI: 0.54-0.86), and 0.82 specificity (95% CI: 0.72-0.87). Medication exposure, clearance, and time since the last dose increase were among the top features. Individual escitalopram and sertraline models yielded an AUROC of 0.73 (95% CI: 0.65-0.81) and 0.64 (95% CI: 0.55-0.73), respectively. Post hoc analysis showed sertraline-treated patients with activation side effects had slower clearance (P = 0.01), which attenuated after accounting for age (P = 0.055). These findings raise the possibility that a machine learning approach leveraging pharmacokinetic data can predict escitalopram- and sertraline-related side effects. Clinicians may consider differences in medication pharmacokinetics, especially during dose titration and as opposed to relying on dose, when managing side effects. With further validation, application of this model to predict side effects may enhance SSRI precision dosing strategies in youth.
Collapse
Affiliation(s)
- Ethan A. Poweleit
- Division of Biomedical Informatics, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
- Department of Biomedical Informatics, University of Cincinnati, College of Medicine, Cincinnati, OH, USA
- Division of Research in Patient Services, Department of Pediatrics, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
- Division of Clinical Pharmacology, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
| | - Samuel E. Vaughn
- Department of Pediatrics, University of Cincinnati, College of Medicine, Cincinnati, OH
- Division of Child and Adolescent Psychiatry, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati, College of Medicine, Cincinnati, OH, USA
| | - Zeruesenay Desta
- Division of Clinical Pharmacology, Indiana University, School of Medicine, Indianapolis, IN
| | - Judith W. Dexheimer
- Division of Biomedical Informatics, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
- Department of Pediatrics, University of Cincinnati, College of Medicine, Cincinnati, OH
- Division of Emergency Medicine, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH
| | - Jeffrey R. Strawn
- Division of Clinical Pharmacology, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
- Department of Pediatrics, University of Cincinnati, College of Medicine, Cincinnati, OH
- Division of Child and Adolescent Psychiatry, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati, College of Medicine, Cincinnati, OH, USA
| | - Laura B. Ramsey
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati, College of Medicine, Cincinnati, OH, USA
- Division of Clinical Pharmacology, Toxicology & Therapeutic Innovation, Children’s Mercy Kansas City, Kansas City, MO, USA
- School of Medicine, University of Missouri-Kansas City, Kansas City, Missouri, USA
| |
Collapse
|
2
|
Zhang Z, Guo Z, Tan Y, Li L, Wang Z, Wen Y, Huang S, Shang D. Population pharmacokinetic approach to guide personalized sertraline treatment in Chinese patients. Heliyon 2024; 10:e25231. [PMID: 38352761 PMCID: PMC10861969 DOI: 10.1016/j.heliyon.2024.e25231] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2023] [Revised: 01/23/2024] [Accepted: 01/23/2024] [Indexed: 02/16/2024] Open
Abstract
Object: Sertraline is a first-line SSRI for the treatment of depression and has the same effectiveness along with a superior safety profile compared to other medications. There are few population pharmacokinetic (PPK) studies of sertraline and a lack of studies in the Chinese population. Therefore, we performed a PPK analysis of Chinese patients treated with sertraline to identify factors that can influence drug exposure. In addition, the dosing and discontinuation regimen of sertraline when applied to adolescents was explored. Methods: Sertraline serum drug concentration data were collected from 140 hospitalized patients to generate a sertraline PPK dataset, and data evaluation and examination of the effects of covariates on drug exposure in the final model were performed using nonlinear mixed-effects models (NONMEM) and first-order conditional estimation with interaction (FOCE-I). Examining rational medication administration and rational withdrawal of sertraline based on significant covariates and final modeling. Results: A one-compartment model with first-order absorption and elimination of sertraline was developed for Chinese patients with psychiatric disorders. Analysis of covariates revealed that age was a covariate that significantly affected sertraline CL/F (P < 0.01) and that sertraline clearance decreased progressively with aging, whereas other factors had no effect on CL/F and V/F of sertraline. In the age range of 11-79, there were 54 adolescent patients (about 1/3) aged 13-18 years, and the safe and effective optimal daily dose for adolescent patients based on the final model simulations was 50-250 mg/d. For adolescent patients, serum concentration fluctuations were moderate for OD doses of 50 mg and 100 mg, using a fixed dose-descent regimen. For patients with OD doses of 150-200 mg and BID doses of 100-200 mg, a more gradual decrease in serum concentration was achieved with a fixed dose interval of 7 or 14 days for 25 mg as the regimen of descent. Conclusions: To our knowledge, this may be the first PPK study of sertraline in Chinese patients. We found that age was an important factor affecting clearance in Chinese patients taking sertraline. Patients taking sertraline may be exposed to increased amounts of sertraline due to decreased clearance with increasing age. The rational dosing and safe discontinuation of sertraline in adolescent patients can be appropriately referenced to the results of the model simulation, thus providing assistance for individualized dosing in adolescents.
Collapse
Affiliation(s)
- Zi Zhang
- Department of Pharmacy, The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou, 510000, China
| | - Zhihao Guo
- Department of Pharmacy, The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou, 510000, China
| | - Yaqian Tan
- Department of Pharmacy, The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou, 510000, China
- Key Laboratory of Neurogenetics and Channelopathies of Guangdong Province and the Ministry of Education of China, Guangzhou Medical University, Guangzhou, 510000, China
| | - Lu Li
- Department of Pharmacy, The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou, 510000, China
- Key Laboratory of Neurogenetics and Channelopathies of Guangdong Province and the Ministry of Education of China, Guangzhou Medical University, Guangzhou, 510000, China
| | - Zhanzhang Wang
- Department of Pharmacy, The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou, 510000, China
- Key Laboratory of Neurogenetics and Channelopathies of Guangdong Province and the Ministry of Education of China, Guangzhou Medical University, Guangzhou, 510000, China
| | - Yuguan Wen
- Department of Pharmacy, The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou, 510000, China
- Key Laboratory of Neurogenetics and Channelopathies of Guangdong Province and the Ministry of Education of China, Guangzhou Medical University, Guangzhou, 510000, China
| | - Shanqing Huang
- Department of Pharmacy, The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou, 510000, China
- Key Laboratory of Neurogenetics and Channelopathies of Guangdong Province and the Ministry of Education of China, Guangzhou Medical University, Guangzhou, 510000, China
| | - Dewei Shang
- Department of Pharmacy, The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou, 510000, China
- Key Laboratory of Neurogenetics and Channelopathies of Guangdong Province and the Ministry of Education of China, Guangzhou Medical University, Guangzhou, 510000, China
| |
Collapse
|
3
|
Malik S, Verma P, Ruaño G, Al Siaghy A, Dilawar A, Bishop JR, Strawn JR, Namerow LB. Pharmacogenetics in Child and Adolescent Psychiatry: Background and Evidence-Based Clinical Applications. J Child Adolesc Psychopharmacol 2024; 34:4-20. [PMID: 38377525 DOI: 10.1089/cap.2023.0074] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/22/2024]
Abstract
The efficacy and tolerability of psychotropic medications can vary significantly among children and adolescents, and some of this variability relates to pharmacogenetic factors. Pharmacogenetics (PGx) in child and adolescent psychiatry can potentially improve treatment outcomes and minimize adverse drug reactions. This article reviews key pharmacokinetic and pharmacodynamic genes and principles of pharmacogenetic testing and discusses the evidence base for clinical decision-making concerning PGx testing. This article reviews current guidelines from the United States Food and Drug Administration (FDA), the Clinical Pharmacogenetics Implementation Consortium (CPIC), and the Dutch Pharmacogenetics Working Group (DPWG) and explores potential future directions. This review discusses key clinical considerations for clinicians prescribing psychotropic medications in children and adolescents, focusing on antidepressants, antipsychotics, stimulants, norepinephrine reuptake inhibitors, and alpha-2 agonists. Finally, this review synthesizes the practical use of pharmacogenetic testing and clinical decision support systems.
Collapse
Affiliation(s)
- Salma Malik
- Department of Psychiatry, University of Connecticut School of Medicine, Farmington, Connecticut, USA
- Division of Child and Adolescent Psychiatry, Institute of Living/Hartford Hospital, Hartford, Connecticut, USA
| | - Pragya Verma
- Division of Child and Adolescent Psychiatry, Institute of Living/Hartford Hospital, Hartford, Connecticut, USA
| | - Gualberto Ruaño
- Department of Psychiatry, University of Connecticut School of Medicine, Farmington, Connecticut, USA
| | - Areej Al Siaghy
- Division of Child and Adolescent Psychiatry, Institute of Living/Hartford Hospital, Hartford, Connecticut, USA
| | | | - Jeffrey R Bishop
- Department of Experimental and Clinical Pharmacology, University of Minnesota College of Pharmacy, Minneapolis, Minnesota, USA
- Department of Psychiatry, University of Minnesota Medical School, Minneapolis, Minnesota, USA
| | - Jeffrey R Strawn
- Department of Psychiatry & Behavioral Neuroscience, University of Cincinnati, College of Medicine, Cincinnati, Ohio, USA
| | - Lisa B Namerow
- Department of Psychiatry, University of Connecticut School of Medicine, Farmington, Connecticut, USA
| |
Collapse
|
4
|
Fu R, Yu Z, Zhou C, Zhang J, Gao F, Wang D, Hao X, Pang X, Yu J. Artificial intelligence-based model for dose prediction of sertraline in adolescents: a real-world study. Expert Rev Clin Pharmacol 2024; 17:177-187. [PMID: 38197873 DOI: 10.1080/17512433.2024.2304009] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2023] [Accepted: 01/08/2024] [Indexed: 01/11/2024]
Abstract
BACKGROUND Variability exists in sertraline pharmacokinetic parameters in individuals, especially obvious in adolescents. We aimed to establish an individualized dosing model of sertraline for adolescents with depression based on artificial intelligence (AI) techniques. METHODS Data were collected from 258 adolescent patients treated at the First Hospital of Hebei Medical University between December 2019 to July 2022. Nine different algorithms were used for modeling to compare the prediction abilities on sertraline daily dose, including XGBoost, LGBM, CatBoost, GBDT, SVM, ANN, TabNet, KNN, and DT. Performance of four dose subgroups (50 mg, 100 mg, 150 mg, and 200 mg) were analyzed. RESULTS CatBoost was chosen to establish the individualized medication model with the best performance. Six important variables were found to be correlated with sertraline dose, including plasma concentration, PLT, MPV, GL, A/G, and LDH. The ROC curve and confusion matrix exhibited the good prediction performance of CatBoost model in four dose subgroups (the AUC of 50 mg, 100 mg, 150 mg, and 200 mg were 0.93, 0.81, 0.93, and 0.93, respectively). CONCLUSION The AI-based dose prediction model of sertraline in adolescents with depression had a good prediction ability, which provides guidance for clinicians to propose the optimal medication regimen.
Collapse
Affiliation(s)
- Ran Fu
- Department of Clinical Pharmacy, The First Hospital of Hebei Medical University, Shijiazhuang, China
- The Technology Innovation Center for Artificial Intelligence in Clinical Pharmacy of Hebei Province, The First Hospital of Hebei Medical University, Shijiazhuang, China
| | - Ze Yu
- Institute of Interdisciplinary Integrative Medicine Research, Shanghai University of Traditional Chinese Medicine, Shanghai, China
- Beijing Medicinovo Technology Co., Ltd, Beijing, China
| | - Chunhua Zhou
- Department of Clinical Pharmacy, The First Hospital of Hebei Medical University, Shijiazhuang, China
- The Technology Innovation Center for Artificial Intelligence in Clinical Pharmacy of Hebei Province, The First Hospital of Hebei Medical University, Shijiazhuang, China
| | - Jinyuan Zhang
- Beijing Medicinovo Technology Co., Ltd, Beijing, China
| | - Fei Gao
- Beijing Medicinovo Technology Co., Ltd, Beijing, China
| | - Donghan Wang
- Department of Clinical Pharmacy, The First Hospital of Hebei Medical University, Shijiazhuang, China
- The Technology Innovation Center for Artificial Intelligence in Clinical Pharmacy of Hebei Province, The First Hospital of Hebei Medical University, Shijiazhuang, China
| | - Xin Hao
- Dalian Medicinovo Technology Co., Ltd, Dalian, China
| | - Xiaolu Pang
- Department of Physical Diagnostics, Hebei Medical University, Shijiazhuang, China
| | - Jing Yu
- Department of Clinical Pharmacy, The First Hospital of Hebei Medical University, Shijiazhuang, China
- The Technology Innovation Center for Artificial Intelligence in Clinical Pharmacy of Hebei Province, The First Hospital of Hebei Medical University, Shijiazhuang, China
| |
Collapse
|