An individualized medication model of sodium valproate for patients with bipolar disorder based on machine learning and deep learning techniques

AI-driven early diagnosis of specific mental disorders: a comprehensive study

One of the areas where artificial intelligence (AI) technologies are used is the detection and diagnosis of mental disorders. AI approaches, including machine learning and deep learning models, can identify early signs of bipolar disorder, schizophrenia, autism spectrum disorder, depression, suicidality, and dementia by analyzing speech patterns, behaviors, and physiological data. These approaches increase diagnostic accuracy and enable timely intervention, which is crucial for effective treatment. This paper presents a comprehensive literature review of AI approaches applied to mental disorder detection using various data sources, such as survey, Electroencephalography (EEG) signal, text and image. Applications include predicting anxiety and depression levels in online games, detecting schizophrenia from EEG signals, detecting autism spectrum disorder, analyzing text-based indicators of suicidality and depression, and diagnosing dementia from magnetic resonance imaging images. eXtreme Gradient Boosting (XGBoost), light gradient-boosting machine (LightGBM), random forest (RF), support vector machine (SVM), K-nearest neighbor were designed as machine learning models, and convolutional neural networks (CNN), long short-term memory (LSTM) and gated recurrent unit (GRU) models suitable for the dataset were designed as deep learning models. Data preprocessing techniques such as wavelet transforms, normalization, clustering were used to optimize model performances, and hyperparameter optimization and feature extraction were performed. While the LightGBM technique had the highest performance with 96% accuracy for anxiety and depression prediction, the optimized SVM stood out with 97% accuracy. Autism spectrum disorder classification reached 98% accuracy with XGBoost, RF and LightGBM. The LSTM model achieved a high accuracy of 83% in schizophrenia diagnosis. The GRU model showed the best performance with 93% accuracy in text-based suicide and depression detection. In the detection of dementia, LSTM and GRU models have demonstrated their effectiveness in data analysis by reaching 99% accuracy. The findings of the study highlight the effectiveness of LSTM and GRU for sequential data analysis and their applicability in medical imaging or natural language processing. XGBoost and LightGBM are noted to be highly accurate ML tools for clinical diagnoses. In addition, hyperparameter optimization and advanced data pre-processing approaches are confirmed to significantly improve model performance. The results obtained with this study have revealed the potential to improve clinical decision support systems for mental disorders with AI, facilitating early diagnosis and personalized treatment strategies.

Developing a machine learning algorithm to predict psychotropic drugs-induced weight gain and the effectiveness of anti-obesity drugs in patients with severe mental illness: Protocol for a prospective cohort study

Obesity is a global public health concern, often co-occurring in patients with severe mental illnesses. The impact of psychotropic drugs-induced weight gain is augmenting the disease burden and healthcare expenditure. However, predictors of psychotropic drug-induced weight gain and the efficacy of anti-obesity drugs remain underexplored. This study aims to develop a machine learning algorithm to predict both psychotropic drugs-induced weight gain and metabolic changes, and the potential of anti-obesity drugs. We plan to enroll 300 patients with severe mental illnesses, including schizophrenia, bipolar disorder, and major depressive disorder. In Phase 1, the study will predict weight gain and metabolic changes after the psychotropic treatment. Data on demographics, lifestyle, medical history, psychological factors, anthropometrics, and laboratory results will be collected at baseline and re-evaluated 24 weeks post-treatment. Participants classified as obese (body mass index ≥ 25 kg/m²) or overweight (body mass index of 23-24.9 kg/m²) at the 24-week follow-up will proceed to Phase 2, which focuses on predicting the promise of anti-obesity drugs. The study participants will receive anti-obesity medications for 24 weeks, and the same variables from Phase 1 will be reassessed. A machine learning model will be developed to predict both psychotropic drug-induced weight gain and anti-obesity medications that will be effective. The algorithm will be tailored to each patient to guide clinicians in personalizing psychiatric and obesity treatment plans. The clinical trial is registered with the Clinical Research Information Service, part of the WHO International Clinical Trials Registry Platform (approval number: KCT0009769).

Construction and evaluation of glucocorticoid dose prediction model based on genetic and clinical characteristics of patients with systemic lupus erythematosus

Currently, no glucocorticoid dose prediction model is available for clinical practice. This study aimed to utilise machine learning techniques to develop and validate personalised dosage models. Participants were patients with SLE who were registered at Nanfang Hospital and received prednisone. Univariate analysis was used to confirm the feature variables. Subsequently, the random forest (RF) algorithm was utilised to interpolate the absent values of the feature variables. Finally, we assessed the prediction capabilities of 11 machine learning and deep-learning algorithms (Logistic, SVM, RF, Adaboost, Bagging, XGBoost, LightGBM, CatBoost, MLP, and TabNet). Finally, a confusion matrix was used to validate the three regimens. In total, 129 patients met the inclusion criteria. The XGBoost algorithm was selected as the preferred method because of its superior performance, achieving an accuracy of 0.81. The factors exhibiting the highest correlation with the prednisone dose were CYP3A4 (rs4646437), albumin (ALB), haemoglobin (HGB), anti-double-stranded DNA antibodies (Anti-dsDNA), erythrocyte sedimentation rate (ESR), age, and HLA-DQA1 (rs2187668). Based on validation, the precision and recall rates for low-dose prednisone (⩾5 mg but <7.5 mg/d) were 100% and 40% respectively. Similarly, for medium-dose prednisone (⩾7.5 mg but <30 mg/d), the accuracy and recall rates were 88% and 88%, and for high-dose prednisone (⩾30 mg but ⩽100 mg/d), the accuracy and recall rates were 62% and 100% respectively. A robust machine learning model was developed to accurately predict prednisone dosage by integrating the identified genetic and clinical factors.

Prediction Trough Concentrations of Valproic Acid Among Chinese Adult Patients with Epilepsy Using Machine Learning Techniques

OBJECTIVE

This study aimed to establish an optimal model based on machine learning (ML) to predict Valproic acid (VPA) trough concentrations in Chinese adult epilepsy patients.

METHODS

A single-center retrospective study was carried out at the Jinshan Hospital affiliated with Fudan University from January 2022 to December 2023. A total of 102 VPA trough concentrations were split into a derivation cohort and a validation cohort at a ratio of 8:2. Thirteen ML algorithms were developed using 27 variables in the derivation cohort and were filtered by the lowest mean absolute error (MAE) value. In addition, feature selection was applied to optimize the model.

RESULTS

Ultimately, the extra tree algorithm was chosen to establish the personalized VPA trough concentration prediction model due to its best performance (MAE = 13.08). The SHapley Additive exPlanations (SHAP) plots were used to visualize and rank the importance of features, providing insights into how each feature influences the model's predictions. After feature selection, we found that the model with the top 9 variables [including daily dose, last dose, uric acid (UA), platelet (PLT), combination, gender, weight, albumin (ALB), aspartate aminotransferase (AST)] outperformed the model with 27 variables, with MAE of 6.82, RMSE of 9.62, R2 value of 0.720, relative accuracy (±20%) of 61.90%, and absolute accuracy (±20 mg/L) of 90.48%.

CONCLUSION

In conclusion, the trough concentration prediction model for VPA in Chinese adult epileptic patients based on the extra tree algorithm demonstrated strong predictive ability which is valuable for clinicians in medication guidance.

Vancomycin trough concentration in adult patients with periprosthetic joint infection: A machine learning-based covariate model

AIMS

Although there are various model-based approaches to individualized vancomycin (VCM) administration, few have been reported for adult patients with periprosthetic joint infection (PJI). This work attempted to develop a machine learning (ML)-based model for predicting VCM trough concentration in adult PJI patients.

METHODS

The dataset of 287 VCM trough concentrations from 130 adult PJI patients was split into a training set (229) and a testing set (58) at a ratio of 8:2, and an independent external 32 concentrations were collected as a validation set. A total of 13 covariates and the target variable (VCM trough concentration) were included in the dataset. A covariate model was respectively constructed by support vector regression, random forest regression and gradient boosted regression trees and interpreted by SHapley Additive exPlanation (SHAP).

RESULTS

The SHAP plots visualized the weight of the covariates in the models, with estimated glomerular filtration rate and VCM daily dose as the 2 most important factors, which were adopted for the model construction. Random forest regression was the optimal ML algorithm with a relative accuracy of 82.8% and absolute accuracy of 67.2% (R2 =.61, mean absolute error = 2.4, mean square error = 10.1), and its prediction performance was verified in the validation set.

CONCLUSION

The proposed ML-based model can satisfactorily predict the VCM trough concentration in adult PJI patients. Its construction can be facilitated with only 2 clinical parameters (estimated glomerular filtration rate and VCM daily dose), and prediction accuracy can be rationalized by SHAP values, which highlights a profound practical value for clinical dosing guidance and timely treatment.

Pre-treatment risk predictors of valproic acid-induced dyslipidemia in pediatric patients with epilepsy

Background: Valproic acid (VPA) stands as one of the most frequently prescribed medications in children with newly diagnosed epilepsy. Despite its infrequent adverse effects within therapeutic range, prolonged VPA usage may result in metabolic disturbances including insulin resistance and dyslipidemia. These metabolic dysregulations in childhood are notably linked to heightened cardiovascular risk in adulthood. Therefore, identification and effective management of dyslipidemia in children hold paramount significance. Methods: In this retrospective cohort study, we explored the potential associations between physiological factors, medication situation, biochemical parameters before the first dose of VPA (baseline) and VPA-induced dyslipidemia (VID) in pediatric patients. Binary logistic regression was utilized to construct a predictive model for blood lipid disorders, aiming to identify independent pre-treatment risk factors. Additionally, The Receiver Operating Characteristic (ROC) curve was used to evaluate the performance of the model. Results: Through binary logistic regression analysis, we identified for the first time that direct bilirubin (DBIL) (odds ratios (OR) = 0.511, p = 0.01), duration of medication (OR = 0.357, p = 0.009), serum albumin (ALB) (OR = 0.913, p = 0.043), BMI (OR = 1.140, p = 0.045), and aspartate aminotransferase (AST) (OR = 1.038, p = 0.026) at baseline were independent risk factors for VID in pediatric patients with epilepsy. Notably, the predictive ability of DBIL (AUC = 0.690, p < 0.0001) surpassed that of other individual factors. Furthermore, when combined into a predictive model, incorporating all five risk factors, the predictive capacity significantly increased (AUC = 0.777, p < 0.0001), enabling the forecast of 77.7% of dyslipidemia events. Conclusion: DBIL emerges as the most potent predictor, and in conjunction with the other four factors, can effectively forecast VID in pediatric patients with epilepsy. This insight can guide the formulation of individualized strategies for the clinical administration of VPA in children.

Machine Learning: A New Approach for Dose Individualization

The application of machine learning (ML) has shown promising results in precision medicine due to its exceptional performance in dealing with complex multidimensional data. However, using ML for individualized dosing of medicines is still in its early stage, meriting further exploration. A systematic review of study designs and modeling details of using ML for individualized dosing of different drugs was performed. We have summarized the status of the study populations, predictive targets, and data sources for ML modeling, the selection of ML algorithms and features, and the evaluation and validation of their predictive performance. We also used the Prediction model Risk of Bias Assessment Tool (PROBAST) to assess the risk of bias of included studies. Currently, ML can be used for both a priori and a posteriori dose selection and optimization, and it can also assist the implementation of therapeutic drug monitoring. However, studies are mainly focused on drugs with narrow therapeutic windows, predominantly immunosuppressants (N = 23, 35.9%) and anti-infectives (N = 21, 32.8%), and there is currently only very limited attention for special populations, such as children (N = 22, 34.4%). Most studies showed poor methodological quality and a high risk of bias. The lack of external validation and clinical utility evaluation currently limits the further clinical implementation of ML for dose individualization. We therefore have proposed several ways to improve the clinical relevance of the studies and facilitate the translation of ML models into clinical practice.

Effects of Sex Differences and Combined Use of Clozapine on Initial Dosage Optimization of Valproic Acid in Patients with Bipolar Disorder

BACKGROUND

Due to the narrow therapeutic window and large pharmacokinetic variation of valproic acid (VPA), it is difficult to make an optimal dosage regimen. The present study aims to optimize the initial dosage of VPA in patients with bipolar disorder.

METHODS

A total of 126 patients with bipolar disorder treated by VPA were included to construct the VPA population pharmacokinetic model retrospectively. Sex differences and combined use of clozapine were found to significantly affect VPA clearance in patients with bipolar disorder. The initial dosage of VPA was further optimized in male patients without the combined use of clozapine, female patients without the combined use of clozapine, male patients with the combined use of clozapine, and female patients with the combined use of clozapine, respectively.

RESULTS

The CL/F and V/F of VPA in patients with bipolar disorder were 11.3 L/h and 36.4 L, respectively. It was found that sex differences and combined use of clozapine significantly affected VPA clearance in patients with bipolar disorder. At the same weight, the VPA clearance rates were 1.134, 1, 1.276884, and 1.126 in male patients without the combined use of clozapine, female patients without the combined use of clozapine, male patients with the combined use of clozapine, and female patients with the combined use of clozapine, respectively. This study further optimized the initial dosage of VPA in male patients without the combined use of clozapine, female patients without the combined use of clozapine, male patients with the combined use of clozapine, and female patients with the combined use of clozapine, respectively.

CONCLUSION

This study is the first to investigate the initial dosage optimization of VPA in patients with bipolar disorder based on sex differences and the combined use of clozapine. Male patients had higher clearance, and the recommended initial dose decreased with increasing weight, providing a reference for the precision drug use of VPA in clinical patients with bipolar disorder.

Predicting plasma concentration of quetiapine in patients with depression using machine learning techniques based on real-world evidence

OBJECTIVES

We develop a model for predicting quetiapine levels in patients with depression, using machine learning to support decisions on clinical regimens.

METHODS

Inpatients diagnosed with depression at the First Hospital of Hebei Medical University from 1 November 2019, to 31 August were enrolled. The ratio of training cohort to testing cohort was fixed at 80%:20% for the whole dataset. Univariate analysis was executed on all information to screen the important variables influencing quetiapine TDM. The prediction abilities of nine machine learning and deep learning algorithms were compared. The prediction model was created using an algorithm with better model performance, and the model's interpretation was done using the SHapley Additive exPlanation.

RESULTS

There were 333 individuals and 412 cases of quetiapine TDM included in the study. Six significant variables were selected to establish the individualized medication model. A quetiapine concentration prediction model was created through CatBoost. In the testing cohort, the projected TDM's accuracy was 61.45%. The prediction accuracy of quetiapine concentration within the effective range (200-750 ng/mL) was 75.47%.

CONCLUSIONS

This study predicts the plasma concentration of quetiapine in depression patients by machine learning, which is meaningful for the clinical medication guidance.

Joint use of population pharmacokinetics and machine learning for optimizing antiepileptic treatment in pediatric population

PURPOSE

Unpredictable drug efficacy and safety of combined antiepileptic therapy is a major challenge during pharmacotherapy decisions in everyday clinical practice. The aim of this study was to describe the pharmacokinetics of valproic acid (VA), lamotrigine (LTG), and levetiracetam (LEV) in a pediatric population using nonlinear mixed-effect modeling, while machine learning (ML) algorithms were applied to identify any relationships among the plasma levels of the three medications and patients' characteristics, as well as to develop a predictive model for epileptic seizures.

METHODS

The study included 71 pediatric patients of both genders, aged 2-18 years, on combined antiepileptic therapy. Population pharmacokinetic (PopPK) models were developed separately for VA, LTG, and LEV. Based on the estimated pharmacokinetic parameters and the patients' characteristics, three ML approaches were applied (principal component analysis, factor analysis of mixed data, and random forest). PopPK models and ML models were developed, allowing for greater insight into the treatment of children on antiepileptic treatment.

RESULTS

Results from the PopPK model showed that the kinetics of LEV, LTG, and VA were best described by a one compartment model with first-order absorption and elimination kinetics. Reliance on random forest model is a compelling vision that shows high prediction ability for all cases. The main factor that can affect antiepileptic activity is antiepileptic drug levels, followed by body weight, while gender is irrelevant. According to our study, children's age is positively associated with LTG levels, negatively with LEV and without the influence of VA.

CONCLUSION

The application of PopPK and ML models may be useful to improve epilepsy management in vulnerable pediatric population during the period of growth and development.