Your browser doesn't support javascript.
loading
Personalized venlafaxine dose prediction using artificial intelligence technology: a retrospective analysis based on real-world data.
Liu, Yimeng; Yu, Ze; Ye, Xuxiao; Zhang, Jinyuan; Hao, Xin; Gao, Fei; Yu, Jing; Zhou, Chunhua.
Afiliación
  • Liu Y; Department of Clinical Pharmacy, The First Hospital of Hebei Medical University, Shijiazhuang, 050017, People's Republic of China.
  • Yu Z; The Technology Innovation Center for Artificial Intelligence in Clinical Pharmacy of Hebei Province, The First Hospital of Hebei Medical University, Shijiazhuang, 050017, People's Republic of China.
  • Ye X; Beijing Medicinovo Technology Co., Ltd, Beijing, 100161, People's Republic of China.
  • Zhang J; Department of Urology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, 200233, People's Republic of China.
  • Hao X; Beijing Medicinovo Technology Co., Ltd, Beijing, 100161, People's Republic of China.
  • Gao F; Dalian Medicinovo Technology Co., Ltd., Dalian, 116021, People's Republic of China.
  • Yu J; Beijing Medicinovo Technology Co., Ltd, Beijing, 100161, People's Republic of China.
  • Zhou C; Department of Clinical Pharmacy, The First Hospital of Hebei Medical University, Shijiazhuang, 050017, People's Republic of China. 38565914@qq.com.
Int J Clin Pharm ; 46(4): 926-936, 2024 Aug.
Article en En | MEDLINE | ID: mdl-38733475
ABSTRACT

BACKGROUND:

Venlafaxine dose regimens vary considerably between individuals, requiring personalized dosing.

AIM:

This study aimed to identify dose-related influencing factors of venlafaxine through real-world data analysis and to construct a personalized dose model using advanced artificial intelligence techniques.

METHOD:

We conducted a retrospective study on patients with depression treated with venlafaxine. Significant variables were selected through a univariate analysis. Subsequently, the predictive performance of seven models (XGBoost, LightGBM, CatBoost, GBDT, ANN, TabNet, and DT) was compared. The algorithm that demonstrated optimal performance was chosen to establish the dose prediction model. Model validation used confusion matrices and ROC analysis. Additionally, a dose subgroup analysis was conducted.

RESULTS:

A total of 298 patients were included. TabNet was selected to establish the venlafaxine dose prediction model, which exhibited the highest performance with an accuracy of 0.80. The analysis identified seven crucial variables correlated with venlafaxine daily dose, including blood venlafaxine concentration, total protein, lymphocytes, age, globulin, cholinesterase, and blood platelet count. The area under the curve (AUC) for predicting venlafaxine doses of 75 mg, 150 mg, and 225 mg were 0.90, 0.85, and 0.90, respectively.

CONCLUSION:

We successfully developed a TabNet model to predict venlafaxine doses using real-world data. This model demonstrated substantial predictive accuracy, offering a personalized dosing regimen for venlafaxine. These findings provide valuable guidance for the clinical use of the drug.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Inteligencia Artificial / Relación Dosis-Respuesta a Droga / Medicina de Precisión / Clorhidrato de Venlafaxina Límite: Adult / Aged / Female / Humans / Male / Middle aged Idioma: En Revista: Int J Clin Pharm Año: 2024 Tipo del documento: Article Pais de publicación: Países Bajos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Inteligencia Artificial / Relación Dosis-Respuesta a Droga / Medicina de Precisión / Clorhidrato de Venlafaxina Límite: Adult / Aged / Female / Humans / Male / Middle aged Idioma: En Revista: Int J Clin Pharm Año: 2024 Tipo del documento: Article Pais de publicación: Países Bajos