Artificial intelligence and diabetes technology: A review

Enhancing communication skills in diabetes care: an observational study regarding the impact of role-playing training for medical staff

INTRODUCTION

Effective communication is crucial for supporting people with diabetes, yet many medical staff feel unsure about their skills in this area. We evaluated role-playing seminars as a method to improve communication skills among medical staff.

METHODS

From 2008 to 2024, we conducted 78 seminars with 2,458 participants, including nurses, dietitians, and pharmacists. Participants engaged in realistic simulated scenarios based on common clinical situations of patient-medical staff interactions, taking on roles as patients (patient performers), medical staff (medical staff performers), and observers. Due to the COVID-19 pandemic, some seminars were held online. Participants were asked to answer a questionnaire regarding their background, impressions of playing individual roles, general comments regarding the seminar, changes in their patient interactions, the possibility of conducting this seminar at their facilities, and impressions of online seminars compared with those of in-person seminars.

RESULTS

The responses of the participants to these seminars were mostly positive. The representative responses indicated that patient performers understood better patients' feelings and medical staff performers had a chance to recognize their insufficient knowledge. The observers also had the chance to learn new communication skills by observing the conversations of other role-players. Compared with in-person seminars, the positive aspects of online seminars were a reduction in time and travel costs and the removal of geographical obstacles. The negative aspects were mostly technology-related concerns.

CONCLUSION

Training seminars using in-person or online role-playing provided medical staff with opportunities and support to improve their communication skills. Further research on measures to improve the communication skills of medical staff and ways to evaluate their efficacy is warranted.

Metaverse-Aided Rehabilitation: A Perspective Review of Successes and Pitfalls

Background: The evolution of technology has continuously redefined the landscape of rehabilitation medicine. Researchers have long incorporated virtual reality (VR) as a promising intervention, providing immersive therapeutic environments for patients. The emergence of the metaverse has recently further expanded the potential applications of VR to augment the possibilities in rehabilitation. Rehabilitation is a crucial aspect of healthcare, and technological advancements have allowed new approaches to aid in this process. One such approach is the metaverse, a virtual world where users can interact with each other and their surroundings in a simulated environment. This comprehensive review aimed to analyze the scientific evidence using the term "metaverse" in rehabilitation and its potential patient benefits. Methods: We conducted a comprehensive literature search from the inception to September 2024 in PubMed, Scopus, Web of Science, and Cochrane Database to identify studies investigating the term "metaverse" and its role in rehabilitation. We then assessed these studies based on their methodology, patient population, technology used, and therapeutic outcomes. Results: Out of 81 articles, 55 remained after removing duplicates. After screening the title, abstract, and full text, we included five articles. Conclusions: Results from these studies suggested potential benefits in various rehabilitative areas, such as cerebral palsy, intellectual disabilities, pain management, and physical performance improvement among the elderly. The metaverse presents promising avenues for enhancing rehabilitation outcomes. While VR's effectiveness is well established, the metaverse, being a newer concept, necessitates further studies for a more comprehensive understanding.

Towards Personalized AI-Based Diabetes Therapy: A Review

Insulin pumps and other smart devices have recently made significant advancements in the treatment of diabetes, a disorder that affects people all over the world. The development of medical AI has been influenced by AI methods designed to help physicians make diagnoses, choose a course of therapy, and predict outcomes. In this article, we thoroughly analyse how AI is being used to enhance and personalize diabetes treatment. The search turned up 77 original research papers, from which we've selected the most crucial information regarding the learning models employed, the data typology, the deployment stage, and the application domains. We identified two key trends, enabled mostly by AI: patient-based therapy personalization and therapeutic algorithm optimization. In the meanwhile, we point out various shortcomings in the existing literature, like a lack of multimodal database analysis or a lack of interpretability. The rapid improvements in AI and the expansion of the amount of data already available offer the possibility to overcome these difficulties shortly and enable a wider deployment of this technology in clinical settings.

Recent progress in artificial intelligence and machine learning for novel diabetes mellitus medications development

Diabetes mellitus, stemming from either insulin resistance or inadequate insulin secretion, represents a complex ailment that results in prolonged hyperglycemia and severe complications. Patients endure severe ramifications such as kidney disease, vision impairment, cardiovascular disorders, and susceptibility to infections, leading to significant physical suffering and imposing substantial socio-economic burdens. This condition has evolved into an increasingly severe health crisis. There is an urgent need to develop new treatments with improved efficacy and fewer adverse effects to meet clinical demands. However, novel drug development is costly, time-consuming, and often associated with side effects and suboptimal efficacy, making it a major challenge. Artificial Intelligence (AI) and Machine Learning (ML) have revolutionized drug development across its comprehensive lifecycle, spanning drug discovery, preclinical studies, clinical trials, and post-market surveillance. These technologies have significantly accelerated the identification of promising therapeutic candidates, optimized trial designs, and enhanced post-approval safety monitoring. Recent advances in AI, including data augmentation, interpretable AI, and integration of AI with traditional experimental methods, offer promising strategies for overcoming the challenges inherent in AI-based drug discovery. Despite these advancements, there exists a notable gap in comprehensive reviews detailing AI and ML applications throughout the entirety of developing medications for diabetes mellitus. This review aims to fill this gap by evaluating the impact and potential of AI and ML technologies at various stages of diabetes mellitus drug development. It does that by synthesizing current research findings and technological advances so as to effectively control diabetes mellitus and mitigate its far-reaching social and economic impacts. The integration of AI and ML promises to revolutionize diabetes mellitus treatment strategies, offering hope for improved patient outcomes and reduced healthcare burdens worldwide.

A knowledge-based decision support system to support family doctors in personalizing type-2 diabetes mellitus medical nutrition therapy

BACKGROUND

Type-2 Diabetes Mellitus (T2D) is a growing concern worldwide, and family doctors are called to help diabetic patients manage this chronic disease, also with Medical Nutrition Therapy (MNT). However, MNT for Diabetes is usually standardized, while it would be much more effective if tailored to the patient. There is a gap in patient-tailored MNT which, if addressed, could support family doctors in delivering effective recommendations. In this context, decision support systems (DSSs) are valuable tools for physicians to support MNT for T2D patients - as long as DSSs are transparent to humans in their decision-making process. Indeed, the lack of transparency in data-driven DSS might hinder their adoption in clinical practice, thus leaving family physicians to adopt general nutrition guidelines provided by the national healthcare systems.

METHOD

This work presents a prototypical ontology-based clinical Decision Support System (OnT2D- DSS) aimed at assisting general practice doctors in managing T2D patients, specifically in creating a tailored dietary plan, leveraging clinical expert knowledge. OnT2D-DSS exploits clinical expert knowledge formalized as a domain ontology to identify a patient's phenotype and potential comorbidities, providing personalized MNT recommendations for macro- and micro-nutrient intake. The system can be accessed via a prototypical interface.

RESULTS

Two preliminary experiments are conducted to assess both the quality and correctness of the inferences provided by the system and the usability and acceptance of the OnT2D-DSS (conducted with nutrition experts and family doctors, respectively).

CONCLUSIONS

Overall, the system is deemed accurate by the nutrition experts and valuable by the family doctors, with minor suggestions for future improvements collected during the experiments.

Stenopool: A Comprehensive Platform for Consolidating Diabetes Device Data

BACKGROUND

The growing adoption of diabetes devices has highlighted the need for integrated platforms to consolidate data from various vendors and device types, enhancing the patient experience and treatment. This shift could pave the way for a transition from conventional outpatient diabetes clinics to advanced home monitoring and virtual care methods. Overall, we wished to empower individuals with diabetes and healthcare providers to interpret and utilize information from diabetes devices more effectively.

METHODS

Stenopool integrates most diabetes devices for glucose monitoring and insulin administration in our clinic. The platform was initially developed with inspiration from open-source software, and the current version is a unique digital platform for managing and analyzing diabetes device data. The development process, outcomes, and status are described.

RESULTS

Since November 2021, Stenopool has been used in our outpatient clinic to integrate over 30 different diabetes devices from around 7000 individuals. Data are primarily uploaded via wired connections, but also using semi-automated and automated cloud-to-cloud data transfers. The platform offers a streamlined workflow for healthcare providers and displays data from various glucose meter, insulin pump, and continuous glucose monitor (CGM) vendors on a single screen in a manner that healthcare providers can modify. A data warehouse with data from Stenopool and electronical health records is nearing completion, preparing the development of tools for population health management, quality assessment, and risk stratification of patients.

CONCLUSION

Using Stenopool, we aimed to enhance diabetes device data management, facilitate the future for virtual patient care pathways, and improve outcomes. This article outlines the platform's development process and challenges.

Application of machine learning in affordable and accessible insulin management for type 1 and 2 diabetes: A comprehensive review

Proper insulin management is vital for maintaining stable blood sugar levels and preventing complications associated with diabetes. However, the soaring costs of insulin present significant challenges to ensuring affordable management. This paper conducts a comprehensive review of current literature on the application of machine learning (ML) in insulin management for diabetes patients, particularly focusing on enhancing affordability and accessibility within the United States. The review encompasses various facets of insulin management, including dosage calculation and response, prediction of blood glucose and insulin sensitivity, initial insulin estimation, resistance prediction, treatment adherence, complications, hypoglycemia prediction, and lifestyle modifications. Additionally, the study identifies key limitations in the utilization of ML within the insulin management literature and suggests future research directions aimed at furthering accessible and affordable insulin treatments. These proposed directions include exploring insurance coverage, optimizing insulin type selection, assessing the impact of biosimilar insulin and market competition, considering mental health factors, evaluating insulin delivery options, addressing cost-related issues affecting insulin usage and adherence, and selecting appropriate patient cost-sharing programs. By examining the potential of ML in addressing insulin management affordability and accessibility, this work aims to envision improved and cost-effective insulin management practices. It not only highlights existing research gaps but also offers insights into future directions, guiding the development of innovative solutions that have the potential to revolutionize insulin management and benefit patients reliant on this life-saving treatment.

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

BACKGROUND

Being one of the most widespread, pervasive, and troublesome illnesses in the world, depression causes dysfunction in various spheres of individual and social life. Regrettably, despite obtaining evidence-based antidepressant medication, up to 70% of people are going to continue to experience troublesome symptoms. Quetiapine, as one of the most commonly prescribed antipsychotic medication worldwide, has been reported as an effective augmentation strategy to antidepressants. The right quetiapine dose and personalized quetiapine treatment are frequently challenging for clinicians. This study aimed to identify important influencing variables for quetiapine dose by maximizing the use of data from real world, and develop a predictive model of quetiapine dose through machine learning techniques to support selections for treatment regimens.

METHODS

The study comprised 308 depressed patients who were medicated with quetiapine and hospitalized in the First Hospital of Hebei Medical University, from November 1, 2019, to August 31, 2022. To identify the important variables influencing the dose of quetiapine, a univariate analysis was applied. The prediction abilities of nine machine learning models (XGBoost, LightGBM, RF, GBDT, SVM, LR, ANN, DT) were compared. Algorithm with the optimal model performance was chosen to develop the prediction model.

RESULTS

Four predictors were selected from 38 variables by the univariate analysis (p < 0.05), including quetiapine TDM value, age, mean corpuscular hemoglobin concentration, and total bile acid. Ultimately, the XGBoost algorithm was used to create a prediction model for quetiapine dose that had the greatest predictive performance (accuracy = 0.69) out of nine models. In the testing cohort (62 cases), a total of 43 cases were correctly predicted of the quetiapine dose regimen. In dose subgroup analysis, AUROC for patients with daily dose of 100 mg, 200 mg, 300 mg and 400 mg were 0.99, 0.75, 0.93 and 0.86, respectively.

CONCLUSIONS

In this work, machine learning techniques are used for the first time to estimate the dose of quetiapine for patients with depression, which is valuable for the clinical drug recommendations.

Postpartum defects in inflammatory response after gestational diabetes precede progression to type 2 diabetes: a nested case-control study within the SWIFT study

BACKGROUND

Gestational diabetes (GDM) is a distinctive form of diabetes that first presents in pregnancy. While most women return to normoglycemia after delivery, they are nearly ten times more likely to develop type 2 diabetes than women with uncomplicated pregnancies. Current prevention strategies remain limited due to our incomplete understanding of the early underpinnings of progression.

AIM

To comprehensively characterize the postpartum profiles of women shortly after a GDM pregnancy and identify key mechanisms responsible for the progression to overt type 2 diabetes using multi-dimensional approaches.

METHODS

We conducted a nested case-control study of 200 women from the Study of Women, Infant Feeding and Type 2 Diabetes After GDM Pregnancy (SWIFT) to examine biochemical, proteomic, metabolomic, and lipidomic profiles at 6-9 weeks postpartum (baseline) after a GDM pregnancy. At baseline and annually up to two years, SWIFT administered research 2-hour 75-gram oral glucose tolerance tests. Women who developed incident type 2 diabetes within four years of delivery (incident case group, n = 100) were pair-matched by age, race, and pre-pregnancy body mass index to those who remained free of diabetes for at least 8 years (control group, n = 100). Correlation analyses were used to assess and integrate relationships across profiling platforms.

RESULTS

At baseline, all 200 women were free of diabetes. The case group was more likely to present with dysglycemia (e.g., impaired fasting glucose levels, glucose tolerance, or both). We also detected differences between groups across all omic platforms. Notably, protein profiles revealed an underlying inflammatory response with perturbations in protease inhibitors, coagulation components, extracellular matrix components, and lipoproteins, whereas metabolite and lipid profiles implicated disturbances in amino acids and triglycerides at individual and class levels with future progression. We identified significant correlations between profile features and fasting plasma insulin levels, but not with fasting glucose levels. Additionally, specific cross-omic relationships, particularly among proteins and lipids, were accentuated or activated in the case group but not the control group.

CONCLUSIONS

Overall, we applied orthogonal, complementary profiling techniques to uncover an inflammatory response linked to elevated triglyceride levels shortly after a GDM pregnancy, which is more pronounced in women who progress to overt diabetes.

Diabetes risk prediction model based on community follow-up data using machine learning

Diabetes is a chronic metabolic disease characterized by hyperglycemia, the follow-up management of diabetes patients is mostly in the community, but the relationship between key lifestyle indicators in community follow-up and the risk of diabetes is unclear. In order to explore the association between key life characteristic indicators of community follow-up and the risk of diabetes, 252,176 follow-up records of people with diabetes patients from 2016 to 2023 were obtained from Haizhu District, Guangzhou. According to the follow-up data, the key life characteristic indicators that affect diabetes are determined, and the optimal feature subset is obtained through feature selection technology to accurately assess the risk of diabetes. A diabetes risk assessment model based on a random forest classifier was designed, which used optimal feature parameter selection and algorithm model comparison, with an accuracy of 91.24% and an AUC corresponding to the ROC curve of 97%. In order to improve the applicability of the model in clinical and real life, a diabetes risk score card was designed and tested using the original data, the accuracy was 95.15%, and the model reliability was high. The diabetes risk prediction model based on community follow-up big data mining can be used for large-scale risk screening and early warning by community doctors based on patient follow-up data, further promoting diabetes prevention and control strategies, and can also be used for wearable devices or intelligent biosensors for individual patient self examination, in order to improve lifestyle and reduce risk factor levels.

A machine learning model for predicting blood concentration of quetiapine in patients with schizophrenia and depression based on real-world data

AIMS

This study aimed to establish a prediction model of quetiapine concentration in patients with schizophrenia and depression, based on real-world data via machine learning techniques to assist clinical regimen decisions.

METHODS

A total of 650 cases of quetiapine therapeutic drug monitoring (TDM) data from 483 patients at the First Hospital of Hebei Medical University from 1 November 2019 to 31 August 2022 were included in the study. Univariate analysis and sequential forward selection (SFS) were implemented to screen the important variables influencing quetiapine TDM. After 10-fold cross validation, the algorithm with the optimal model performance was selected for predicting quetiapine TDM among nine models. SHapley Additive exPlanation was applied for model interpretation.

RESULTS

Four variables (daily dose of quetiapine, type of mental illness, sex and CYP2D6 competitive substrates) were selected through univariate analysis (P < .05) and SFS to establish the models. The CatBoost algorithm with the best predictive ability (mean [SD] R2  = 0.63 ± 0.02, RMSE = 137.39 ± 10.56, MAE = 103.24 ± 7.23) was chosen for predicting quetiapine TDM among nine models. The mean (SD) accuracy of the predicted TDM within ±30% of the actual TDM was 49.46 ± 3.00%, and that of the recommended therapeutic range (200-750 ng mL-1 ) was 73.54 ± 8.3%. Compared with the PBPK model in a previous study, the CatBoost model shows slightly higher accuracy within ±100% of the actual value.

CONCLUSIONS

This work is the first real-world study to predict the blood concentration of quetiapine in patients with schizophrenia and depression using artificial intelligent techniques, which is of significance and value for clinical medication guidance.

Machine learning based study for the classification of Type 2 diabetes mellitus subtypes

PURPOSE

Data-driven diabetes research has increased its interest in exploring the heterogeneity of the disease, aiming to support in the development of more specific prognoses and treatments within the so-called precision medicine. Recently, one of these studies found five diabetes subgroups with varying risks of complications and treatment responses. Here, we tackle the development and assessment of different models for classifying Type 2 Diabetes (T2DM) subtypes through machine learning approaches, with the aim of providing a performance comparison and new insights on the matter.

METHODS

We developed a three-stage methodology starting with the preprocessing of public databases NHANES (USA) and ENSANUT (Mexico) to construct a dataset with N = 10,077 adult diabetes patient records. We used N = 2,768 records for training/validation of models and left the remaining (N = 7,309) for testing. In the second stage, groups of observations -each one representing a T2DM subtype- were identified. We tested different clustering techniques and strategies and validated them by using internal and external clustering indices; obtaining two annotated datasets Dset A and Dset B. In the third stage, we developed different classification models assaying four algorithms, seven input-data schemes, and two validation settings on each annotated dataset. We also tested the obtained models using a majority-vote approach for classifying unseen patient records in the hold-out dataset.

RESULTS

From the independently obtained bootstrap validation for Dset A and Dset B, mean accuracies across all seven data schemes were [Formula: see text] ([Formula: see text]) and [Formula: see text] ([Formula: see text]), respectively. Best accuracies were [Formula: see text] and [Formula: see text]. Both validation setting results were consistent. For the hold-out dataset, results were consonant with most of those obtained in the literature in terms of class proportions.

CONCLUSION

The development of machine learning systems for the classification of diabetes subtypes constitutes an important task to support physicians for fast and timely decision-making. We expect to deploy this methodology in a data analysis platform to conduct studies for identifying T2DM subtypes in patient records from hospitals.

Immunodiagnosis - the promise of personalized immunotherapy

Immunotherapy showed remarkable efficacy in several cancer types. However, the majority of patients do not benefit from immunotherapy. Evaluating tumor heterogeneity and immune status before treatment is key to identifying patients that are more likely to respond to immunotherapy. Demographic characteristics (such as sex, age, and race), immune status, and specific biomarkers all contribute to response to immunotherapy. A comprehensive immunodiagnostic model integrating all these three dimensions by artificial intelligence would provide valuable information for predicting treatment response. Here, we coined the term "immunodiagnosis" to describe the blueprint of the immunodiagnostic model. We illustrated the features that should be included in immunodiagnostic model and the strategy of constructing the immunodiagnostic model. Lastly, we discussed the incorporation of this immunodiagnosis model in clinical practice in hopes of improving the prognosis of tumor immunotherapy.

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.

Circulating Bile Acids as Biomarkers for Disease Diagnosis and Prevention

CONTEXT

Bile acids (BAs) are pivotal signaling molecules that regulate energy metabolism and inflammation. Recent epidemiological studies have reported specific alterations in circulating BA profiles in certain disease states, including obesity, type 2 diabetes mellitus (T2DM), nonalcoholic fatty liver disease (NAFLD), and Alzheimer disease (AD). In the past decade, breakthroughs have been made regarding the translation of BA profiling into clinical use for disease prediction. In this review, we summarize and synthesize recent data on variation in circulating BA profiles in patients with various diseases to evaluate the value of these biomarkers in human plasma for early diagnosis.

EVIDENCE ACQUISITION

This review is based on a collection of primary and review literature gathered from a PubMed search for BAs, obesity, T2DM, insulin resistance (IR), NAFLD, hepatocellular carcinoma (HCC), cholangiocarcinoma (CCA), colon cancer, and AD, among other keywords.

EVIDENCE SYNTHESIS

Individuals with obesity, T2DM, HCC, CCA, or AD showed specific alterations in circulating BA profiles. These alterations may have existed long before the initial diagnosis of these diseases. The intricate relationship between obesity, IR, and NAFLD complicates the establishment of clear and independent associations between BA profiles and nonalcoholic steatohepatitis. Alterations in the levels of total BAs and several BA species were seen across the entire spectrum of NAFLD, demonstrating significant increases with the worsening of histological features.

CONCLUSIONS

Aberrant circulating BA profiles are an early event in the onset and progression of obesity, T2DM, HCC, and AD. The pleiotropic effects of BAs explain these broad connections. Circulating BA profiles could provide a basis for the development of biomarkers for the diagnosis and prevention of a wide range of diseases.

Review: Machine learning in precision pharmacotherapy of type 2 diabetes-A promising future or a glimpse of hope?

Precision pharmacotherapy of diabetes requires judicious selection of the optimal therapeutic agent for individual patients. Artificial intelligence (AI), a swiftly expanding discipline, holds substantial potential to transform current practices in diabetes diagnosis and management. This manuscript provides a comprehensive review of contemporary research investigating drug responses in patient subgroups, stratified via either supervised or unsupervised machine learning approaches. The prevalent algorithmic workflow for investigating drug responses using machine learning involves cohort selection, data processing, predictor selection, development and validation of machine learning methods, subgroup allocation, and subsequent analysis of drug response. Despite the promising feature, current research does not yet provide sufficient evidence to implement machine learning algorithms into routine clinical practice, due to a lack of simplicity, validation, or demonstrated efficacy. Nevertheless, we anticipate that the evolving evidence base will increasingly substantiate the role of machine learning in molding precision pharmacotherapy for diabetes.

Artificial Intelligence Methodologies Applied to Technologies for Screening, Diagnosis and Care of the Diabetic Foot: A Narrative Review

Diabetic foot syndrome is a multifactorial pathology with at least three main etiological factors, i.e., peripheral neuropathy, peripheral arterial disease, and infection. In addition to complexity, another distinctive trait of diabetic foot syndrome is its insidiousness, due to a frequent lack of early symptoms. In recent years, it has become clear that the prevalence of diabetic foot syndrome is increasing, and it is among the diabetes complications with a stronger impact on patient's quality of life. Considering the complex nature of this syndrome, artificial intelligence (AI) methodologies appear adequate to address aspects such as timely screening for the identification of the risk for foot ulcers (or, even worse, for amputation), based on appropriate sensor technologies. In this review, we summarize the main findings of the pertinent studies in the field, paying attention to both the AI-based methodological aspects and the main physiological/clinical study outcomes. The analyzed studies show that AI application to data derived by different technologies provides promising results, but in our opinion future studies may benefit from inclusion of quantitative measures based on simple sensors, which are still scarcely exploited.

Applying machine learning to the pharmacokinetic modeling of cyclosporine in adult renal transplant recipients: a multi-method comparison

Objective: The aim of this study was to identify the important factors affecting cyclosporine (CsA) blood concentration and estimate CsA concentration using seven different machine learning (ML) algorithms. We also assessed the predictability of established ML models and previously built population pharmacokinetic (popPK) model. Finally, the most suitable ML model and popPK model to guide precision dosing were determined.

Methods: In total, 3,407 whole-blood trough and peak concentrations of CsA were obtained from 183 patients who underwent initial renal transplantation. These samples were divided into model-building and evaluation sets. The model-building set was analyzed using seven different ML algorithms. The effects of potential covariates were evaluated using the least absolute shrinkage and selection operator algorithms. A separate evaluation set was used to assess the ability of all models to predict CsA blood concentration. R squared (R2) scores, median prediction error (MDPE), median absolute prediction error (MAPE), and the percentages of PE within 20% (F20) and 30% (F30) were calculated to assess the predictive performance of these models. In addition, previously built popPK model was included for comparison.

Results: Sixteen variables were selected as important covariates. Among ML models, the predictive performance of nonlinear-based ML models was superior to that of linear regression (MDPE: 3.27%, MAPE: 34.21%, F20: 30.63%, F30: 45.03%, R2 score: 0.68). The ML model built with the artificial neural network algorithm was considered the most suitable (MDPE: −0.039%, MAPE: 25.60%, F20: 39.35%, F30: 56.46%, R2 score: 0.75). Its performance was superior to that of the previously built popPK model (MDPE: 5.26%, MAPE: 29.22%, F20: 33.94%, F30: 51.22%, R2 score: 0.68). Furthermore, the application of the most suitable model and the popPK model in clinic showed that most dose regimen recommendations were reasonable.

Conclusion: The performance of these ML models indicate that a nonlinear relationship for covariates may help to improve model predictability. These results might facilitate the application of ML models in clinic, especially for patients with unstable status or during initial dose optimization.

Construction and Interpretation of Prediction Model of Teicoplanin Trough Concentration via Machine Learning

Objective

To establish an optimal model to predict the teicoplanin trough concentrations by machine learning, and explain the feature importance in the prediction model using the SHapley Additive exPlanation (SHAP) method.

Methods

A retrospective study was performed on 279 therapeutic drug monitoring (TDM) measurements obtained from 192 patients who were treated with teicoplanin intravenously at the First Affiliated Hospital of Army Medical University from November 2017 to July 2021. This study included 27 variables, and the teicoplanin trough concentrations were considered as the target variable. The whole dataset was divided into a training group and testing group at the ratio of 8:2, and predictive performance was compared among six different algorithms. Algorithms with higher model performance (top 3) were selected to establish the ensemble prediction model and SHAP was employed to interpret the model.

Results

Three algorithms (SVR, GBRT, and RF) with high R² scores (0.676, 0.670, and 0.656, respectively) were selected to construct the ensemble model at the ratio of 6:3:1. The model with R² = 0.720, MAE = 3.628, MSE = 22.571, absolute accuracy of 83.93%, and relative accuracy of 60.71% was obtained, which performed better in model fitting and had better prediction accuracy than any single algorithm. The feature importance and direction of each variable were visually demonstrated by SHAP values, in which teicoplanin administration and renal function were the most important factors.

Conclusion

We firstly adopted a machine learning approach to predict the teicoplanin trough concentration, and interpreted the prediction model by the SHAP method, which is of great significance and value for the clinical medication guidance.

Insulin discovery: A pivotal point in medical history

The discovery of insulin in 1921 - due to the efforts of the Canadian research team based in Toronto - has been a landmark achievement in the history of medicine. Lives of people with diabetes were changed forever, considering that in the pre-insulin era this was a deadly condition. Insulin, right after its discovery, became the first hormone to be purified for human use, the first to be unraveled in its amino acid sequence and to be synthetized by DNA-recombinant technique, the first to be modified in its amino acid sequence to modify its duration of action. As such the discovery of insulin represents a pivotal point in medical history. Since the early days of its production, insulin has been improved in its pharmacokinetic and pharmacodynamic properties in the attempt to faithfully reproduce diurnal physiologic plasma insulin fluctuations. The evolution of insulin molecule has been paralleled by evolution in the way the hormone is administered. Once-weekly insulins will be available soon, and glucose-responsive "smart" insulins start showing their potential in early clinical studies. The first century of insulin as therapy was marked by relentless search for better formulations, a search that has not stopped yet. New technologies may have, indeed, the potential to provide further improvement of safety and efficacy of insulin therapy and, therefore, contribute to improvement of the quality of life of people with diabetes.