ChatMol: interactive molecular discovery with natural language.

MOTIVATION: Natural language is poised to become a key medium for human-machine interactions in the era of large language models. In the field of biochemistry, tasks such as property prediction and molecule mining are critically important yet technically challenging. Bridging molecular expressions in natural language and chemical language can significantly enhance the interpretability and ease of these tasks. Moreover, it can integrate chemical knowledge from various sources, leading to a deeper understanding of molecules. RESULTS: Recognizing these advantages, we introduce the concept of conversational molecular design, a novel task that utilizes natural language to describe and edit target molecules. To better accomplish this task, we develop ChatMol, a knowledgeable and versatile generative pretrained model. This model is enhanced by incorporating experimental property information, molecular spatial knowledge, and the associations between natural and chemical languages. Several typical solutions including large language models (e.g. ChatGPT) are evaluated, proving the challenge of conversational molecular design and the effectiveness of our knowledge enhancement approach. Case observations and analysis offer insights and directions for further exploration of natural-language interaction in molecular discovery. AVAILABILITY AND IMPLEMENTATION: Codes and data are provided in https://github.com/Ellenzzn/ChatMol/tree/main.

Reinforcement Learning to Optimize Ventilator Settings for Patients on Invasive Mechanical Ventilation: A Retrospective Study.

BACKGROUND: One of the significant changes in intensive care medicine over the past two decades is the acknowledgement that improper mechanical ventilation settings substantially contribute to pulmonary injury in critically ill patients. Artificial intelligence (AI) solutions can be used to optimize mechanical ventilation settings in intensive care units (ICUs) and to improve patient outcomes. Specifically, machine learning algorithms can be trained on large datasets of patient information and mechanical ventilation settings. These algorithms can then predict patient responses to different ventilation strategies and suggest personalized ventilation settings for individual patients. OBJECTIVE: In this study, we aimed to design and evaluate an AI solution that could tailor an optimal ventilator strategy for each critically ill patient who requires mechanical ventilation. METHODS: We proposed a reinforcement learning-based AI solution using observational data from multiple ICUs in the US. The primary outcome was hospital mortality. Secondary outcomes were the proportion of optimal oxygen saturation and the proportion of optimal mean arterial blood pressure. We trained our AI agent to recommend low/medium/high levels of three ventilator settings - positive end-expiratory pressure (PEEP), fraction of inspired oxygen (FiO2) and ideal body weight-adjusted tidal volume - according to patients' health conditions. We defined a policy as a set of rules guiding ventilator setting changes given specific clinical scenarios. Off-policy evaluation metrics were applied to evaluate the AI policy. RESULTS: We studied 21,595 and 5,105 patients' ICU stays from the eICU Collaborative Research (eICU) and Medical Information Mart for Intensive Care IV (MIMIC-IV) databases respectively. Using the learnt AI policy, we estimated the hospital mortality rate (eICU 12.1±3.1%; MIMIC-IV 29.1±0.9%), proportion of optimal oxygen saturation (eICU 58.7±4.7%; MIMIC-IV 49.0±1.0%), and proportion of optimal mean arterial blood pressure (eICU 31.1±4.5%; MIMIC-IV 41.2±1.0%). Based on multiple quantitative and qualitative evaluation metrics, our proposed AI solution outperformed observed clinical practice.We studied 21,595 5105 and 5,105 21595 patients' ' ICU stays from the Medical Information Mart for Intensive Care -IV (MIMIC-IV)(1) and eICU Collaborative Research (eICU) and Medical Information Mart for Intensive Care IV (MIMIC-IV) databases respectively. Observed hospital mortality rates were 18.2% (eICU) and 31.1% (MIMIC-IV). UsingFor the learnt AI policy, we estimated the hospital mortality rate (eICU 14.7±0.7%; MIMIC-IV 29.1±0.9%), proportion of optimal oxygen saturation (eICU 57.8±1.0%; MIMIC-IV 49.0±1.0%), and proportion of optimal mean arterial blood pressure (eICU 34.7 ± 1.0%; MIMIC-IV 41.2±1.0%). Based on multiple quantitative and qualitative evaluation metrics, our proposed AI solution has potential to outperformed observed clinical practice. CONCLUSIONS: Our study found that customizing ventilation settings for individual patients led to lower estimated hospital mortality rates compared to actual rates. This highlights the potential effectiveness of using RL methodology to develop AI models that analyze complex clinical data for optimizing treatment parameters. Additionally, our findings suggest the integration of this model into a clinical decision support system for refining ventilation settings, supporting the need for prospective validation trials.

Characteristics of Online Health Care Services From China's Largest Online Medical Platform: Cross-sectional Survey Study.

BACKGROUND: Internet hospitals in China are in great demand due to limited and unevenly distributed health care resources, lack of family doctors, increased burdens of chronic diseases, and rapid growth of the aged population. The COVID-19 epidemic catalyzed the expansion of online health care services. In recent years, internet hospitals have been rapidly developed. Ping An Good Doctor is the largest, national online medical entry point in China and is a widely used platform providing online health care services. OBJECTIVE: This study aims to give a comprehensive description of the characteristics of the online consultations and inquisitions in Ping An Good Doctor. The analyses tried to answer the following questions: (1) What are the characteristics of the consultations in Ping An Good Doctor in terms of department and disease profiles? (2) Who uses the online health services most frequently? and (3) How is the user experience of the online consultations of Ping An Good Doctor? METHODS: A total of 35.3 million consultations and inquisitions over the course of 1 year were analyzed with respect to the distributions of departments and diseases, user profiles, and consulting behaviors. RESULTS: The geographical distribution of the usage of Ping An Good Doctor showed that Shandong (18.4%), Yunnan (15.6%), Shaanxi (7.2%), and Guangdong (5.5%) were the provinces that used it the most; they accounted for 46.6% of the total consultations and inquisitions. In terms of department distribution, we found that gynecology and obstetrics (19.2%), dermatology (17.0%), and pediatrics (14.4%) were the top three departments in Ping An Good Doctor. The disease distribution analysis showed that, except for nondisease-specific consultations, acute upper respiratory infection (AURI) (4.1%), pregnancy (2.8%), and dermatitis (2.4%) were the most frequently consulted diseases. In terms of user profiles, females (60.4%) from 19 to 35 years of age were most likely to seek consultations online, in general. The user behavior analyses showed that the peak times of day for online consultations occurred at 10 AM, 3 PM, and 9 PM. Regarding user experience, 93.0% of users gave full marks following their consultations. For some disease-related health problems, such as AURI, dermatitis, and eczema, the feedback scores were above average. CONCLUSIONS: The prevalence of internet hospitals, such as Ping An Good Doctor, illustrated the great demand for online health care services that can go beyond geographical limitations. Our analyses showed that nondisease-specific issues and moderate health problems were much more frequently consulted about than severe clinical conditions. This indicated that internet hospitals played the role of the family doctor, which helped to relieve the stress placed on offline hospitals and facilitated people's lives. In addition, good user experiences, especially regarding disease-related inquisitions, suggested that online health services can help solve health problems. With support from the government and acceptance by the public, online health care services could develop at a fast pace and greatly benefit people's daily lives.

Effective Treatment Recommendations for Type 2 Diabetes Management Using Reinforcement Learning: Treatment Recommendation Model Development and Validation.

BACKGROUND: Type 2 diabetes mellitus (T2DM) and its related complications represent a growing economic burden for many countries and health systems. Diabetes complications can be prevented through better disease control, but there is a large gap between the recommended treatment and the treatment that patients actually receive. The treatment of T2DM can be challenging because of different comprehensive therapeutic targets and individual variability of the patients, leading to the need for precise, personalized treatment. OBJECTIVE: The aim of this study was to develop treatment recommendation models for T2DM based on deep reinforcement learning. A retrospective analysis was then performed to evaluate the reliability and effectiveness of the models. METHODS: The data used in our study were collected from the Singapore Health Services Diabetes Registry, encompassing 189,520 patients with T2DM, including 6,407,958 outpatient visits from 2013 to 2018. The treatment recommendation model was built based on 80% of the dataset and its effectiveness was evaluated with the remaining 20% of data. Three treatment recommendation models were developed for antiglycemic, antihypertensive, and lipid-lowering treatments by combining a knowledge-driven model and a data-driven model. The knowledge-driven model, based on clinical guidelines and expert experiences, was first applied to select the candidate medications. The data-driven model, based on deep reinforcement learning, was used to rank the candidates according to the expected clinical outcomes. To evaluate the models, short-term outcomes were compared between the model-concordant treatments and the model-nonconcordant treatments with confounder adjustment by stratification, propensity score weighting, and multivariate regression. For long-term outcomes, model-concordant rates were included as independent variables to evaluate if the combined antiglycemic, antihypertensive, and lipid-lowering treatments had a positive impact on reduction of long-term complication occurrence or death at the patient level via multivariate logistic regression. RESULTS: The test data consisted of 36,993 patients for evaluating the effectiveness of the three treatment recommendation models. In 43.3% of patient visits, the antiglycemic medications recommended by the model were concordant with the actual prescriptions of the physicians. The concordant rates for antihypertensive medications and lipid-lowering medications were 51.3% and 58.9%, respectively. The evaluation results also showed that model-concordant treatments were associated with better glycemic control (odds ratio [OR] 1.73, 95% CI 1.69-1.76), blood pressure control (OR 1.26, 95% CI, 1.23-1.29), and blood lipids control (OR 1.28, 95% CI 1.22-1.35). We also found that patients with more model-concordant treatments were associated with a lower risk of diabetes complications (including 3 macrovascular and 2 microvascular complications) and death, suggesting that the models have the potential of achieving better outcomes in the long term. CONCLUSIONS: Comprehensive management by combining knowledge-driven and data-driven models has good potential to help physicians improve the clinical outcomes of patients with T2DM; achieving good control on blood glucose, blood pressure, and blood lipids; and reducing the risk of diabetes complications in the long term.

Reinforcement Learning for Clinical Decision Support in Critical Care: Comprehensive Review.

BACKGROUND: Decision support systems based on reinforcement learning (RL) have been implemented to facilitate the delivery of personalized care. This paper aimed to provide a comprehensive review of RL applications in the critical care setting. OBJECTIVE: This review aimed to survey the literature on RL applications for clinical decision support in critical care and to provide insight into the challenges of applying various RL models. METHODS: We performed an extensive search of the following databases: PubMed, Google Scholar, Institute of Electrical and Electronics Engineers (IEEE), ScienceDirect, Web of Science, Medical Literature Analysis and Retrieval System Online (MEDLINE), and Excerpta Medica Database (EMBASE). Studies published over the past 10 years (2010-2019) that have applied RL for critical care were included. RESULTS: We included 21 papers and found that RL has been used to optimize the choice of medications, drug dosing, and timing of interventions and to target personalized laboratory values. We further compared and contrasted the design of the RL models and the evaluation metrics for each application. CONCLUSIONS: RL has great potential for enhancing decision making in critical care. Challenges regarding RL system design, evaluation metrics, and model choice exist. More importantly, further work is required to validate RL in authentic clinical environments.

Hyperedge Representations with Hypergraph Wavelets: Applications to Spatial Transcriptomics.

In many data-driven applications, higher-order relationships among multiple objects are essential in capturing complex interactions. Hypergraphs, which generalize graphs by allowing edges to connect any number of nodes, provide a flexible and powerful framework for modeling such higher-order relationships. In this work, we introduce hypergraph diffusion wavelets and describe their favorable spectral and spatial properties. We demonstrate their utility for biomedical discovery in spatially resolved transcriptomics by applying the method to represent disease-relevant cellular niches for Alzheimer's disease.

The Beijing angle closure progression study: design and methodology.

Purpose: The purpose of this study is to summarize the design and methodology of a large-scale trial in northern China, the Beijing Angle Closure Progression Study (BAPS). This trial is designed to explore the 5-year incidence of primary angle-closure suspect (PACS) progressing to primary angle-closure (PAC) or primary angle-closure glaucoma (PACG) and to determine the possible risk factors of disease progression. Methods/design: The BAPS is a clinic-based, multicenter, noninterventional trial conducted on a sample of urban Chinese adults. Consecutive eligible patients who meet PACS diagnostic criteria will be recruited from eight participating centers, with the trial commencing on August 4, 2022. The target sample size is set at 825 subjects, with follow up planned for a minimum period of 5 years. Baseline examination will include presenting visual acuity, best corrected visual acuity, intraocular pressure (IOP), undilated slit-lamp biomicroscopy, stereoscopic evaluation of the optic disc, visual field test, optical coherence tomography evaluation of retinal nerve fiber layer, ultrasound biomicroscopy and IOLMaster. Questionnaires will also be used to collect detailed personal history. Patients are scheduled to visit the glaucoma clinic every 12 months and may visit the emergency room in case of acute attack of angle closure. Study endpoints include acute PAC episodes, elevated IOP, peripheral anterior synechiae, glaucomatous visual field defect, or glaucomatous abnormality of optic nerve. Discussion: The BAPS will provide data on the 5-year incidence of PACS progressing to PAC or PACG and determine the risk factors for disease progression. This study will also help redefine high-risk patients with PACS.

A clinical research analytics toolkit for cohort study.

This paper presents a clinical informatics toolkit that can assist physicians to conduct cohort studies effectively and efficiently. The toolkit has three key features: 1) support of procedures defined in epidemiology, 2) recommendation of statistical methods in data analysis, and 3) automatic generation of research reports. On one hand, our system can help physicians control research quality by leveraging the integrated knowledge of epidemiology and medical statistics; on the other hand, it can improve productivity by reducing the complexities for physicians during their cohort studies.

Benchmarking automated cell type annotation tools for single-cell ATAC-seq data.

As single-cell chromatin accessibility profiling methods advance, scATAC-seq has become ever more important in the study of candidate regulatory genomic regions and their roles underlying developmental, evolutionary, and disease processes. At the same time, cell type annotation is critical in understanding the cellular composition of complex tissues and identifying potential novel cell types. However, most existing methods that can perform automated cell type annotation are designed to transfer labels from an annotated scRNA-seq data set to another scRNA-seq data set, and it is not clear whether these methods are adaptable to annotate scATAC-seq data. Several methods have been recently proposed for label transfer from scRNA-seq data to scATAC-seq data, but there is a lack of benchmarking study on the performance of these methods. Here, we evaluated the performance of five scATAC-seq annotation methods on both their classification accuracy and scalability using publicly available single-cell datasets from mouse and human tissues including brain, lung, kidney, PBMC, and BMMC. Using the BMMC data as basis, we further investigated the performance of these methods across different data sizes, mislabeling rates, sequencing depths and the number of cell types unique to scATAC-seq. Bridge integration, which is the only method that requires additional multimodal data and does not need gene activity calculation, was overall the best method and robust to changes in data size, mislabeling rate and sequencing depth. Conos was the most time and memory efficient method but performed the worst in terms of prediction accuracy. scJoint tended to assign cells to similar cell types and performed relatively poorly for complex datasets with deep annotations but performed better for datasets only with major label annotations. The performance of scGCN and Seurat v3 was moderate, but scGCN was the most time-consuming method and had the most similar performance to random classifiers for cell types unique to scATAC-seq.

Abnormality classification from electrocardiograms with various lead combinations.

Objective. As cardiovascular diseases are a leading cause of death, early and accurate diagnosis of cardiac abnormalities for a lower cost becomes particularly important. Given electrocardiogram (ECG) datasets from multiple sources, there exist many challenges to the development of generalized models that can identify multiple types of cardiac abnormalities from both 12-lead ECG signals and reduced-lead ECG signals. In this study, our objective is to build robust models that can accurately classify 30 types of abnormalities from various lead combinations of ECG signals.Approach. Given the challenges of this problem, we propose a framework for building robust models for ECG signal classification. Firstly, a preprocessing workflow is adopted for each ECG dataset to mitigate the problem of data divergence. Secondly, to capture the lead-wise relations, we use a squeeze-and-excitation deep residual network as our base model. Thirdly, we propose a cross-relabeling strategy and apply the sign-augmented loss function to tackle the corrupted labels in the data. Furthermore, we utilize a pos-if-any-pos ensemble strategy and a dataset-wise cross-evaluation strategy to handle the uncertainty of the data distribution in the application.Main results. In the Physionet/Computing in Cardiology Challenge 2021, our approach achieved the challenge metric scores of 0.57, 0.59, 0.59, 0.58, 0.57 on 12-, 6-, 4-, 3- and 2-lead versions and an averaged challenge metric score of 0.58 over all the lead versions.Significance. Using the proposed framework, we have developed the models from several large datasets with sufficiently labeled abnormalities. Our models are able to identify 30 ECG abnormalities accurately based on various lead combinations of ECG signals. The performance on hidden test data demonstrates the effectiveness of the proposed approaches.

Ontology-based knowledge management for personalized adverse drug events detection.

Since Adverse Drug Event (ADE) has become a leading cause of death around the world, there arises high demand for helping clinicians or patients to identify possible hazards from drug effects. Motivated by this, we present a personalized ADE detection system, with the focus on applying ontology-based knowledge management techniques to enhance ADE detection services. The development of electronic health records makes it possible to automate the personalized ADE detection, i.e., to take patient clinical conditions into account during ADE detection. Specifically, we define the ADE ontology to uniformly manage the ADE knowledge from multiple sources. We take advantage of the rich semantics from the terminology SNOMED-CT and apply it to ADE detection via the semantic query and reasoning.

Construction of a Non-Mutually Exclusive Decision Tree for Medication Recommendation of Chronic Heart Failure.

Objective: Although guidelines have recommended standardized drug treatment for heart failure (HF), there are still many challenges in making the correct clinical decisions due to the complicated clinical situations of HF patients. Each patient would satisfy several recommendations, meaning the decision tree of HF treatment should be nonmutually exclusive, and the same patient would be allocated to several leaf nodes in the decision tree. In the current study, we aim to propose a way to ensemble a nonmutually exclusive decision tree for recommendation system for complicated diseases, such as HF. Methods: The nonmutually exclusive decision tree was constructed via knowledge rules summarized from the HF clinical guidelines. Then similar patients were defined as those who followed the same pattern of leaf node allocation according to the decision tree. The frequent medication patterns for each similar patient were mined using the Apriori algorithms, and we also carried out the outcome prognosis analyses to show the capability for the evidence-based medication recommendations of our nonmutually exclusive decision tree. Results: Based on a large database that included 29,689 patients with 84,705 admissions, we tested the framework for HF treatment recommendation. In the constructed decision tree, the HF treatment recommendations were grouped into two independent parts. The first part was recommendations for new cases, and the second part was recommendations when patients had different historical medication. There are 14 leaf nodes in our decision tree, and most of the leaf nodes had a guideline adherence of around 90%. We reported the top 10 popular similar patients, which accounted for 32.84% of the whole population. In addition, the multiple outcome prognosis analyses were carried out to assess the medications for one of the subgroups of similar patients. Our results showed even for the subgroup of the same similar patients that no one medication pattern would benefit all outcomes. Conclusion: In the present study, the methodology to construct a nonmutually exclusive decision tree for medication recommendations for HF and its application in CDSS was proposed. Our framework is universal for most diseases and could be generally applied in developing the CDSS for treatment.

Identification of 27 abnormalities from multi-lead ECG signals: an ensembled SE_ResNet framework with Sign Loss function.

Objective. Cardiovascular disease is a major threat to health and one of the primary causes of death globally. The 12-lead ECG is a cheap and commonly accessible tool to identify cardiac abnormalities. Early and accurate diagnosis will allow early treatment and intervention to prevent severe complications of cardiovascular disease. Our objective is to develop an algorithm that automatically identifies 27 ECG abnormalities from 12-lead ECG databases.Approach. Firstly, a series of pre-processing methods were proposed and applied on various data sources in order to mitigate the problem of data divergence. Secondly, we ensembled two SE_ResNet models and one rule-based model to enhance the performance of various ECG abnormalities' classification. Thirdly, we introduce a Sign Loss to tackle the problem of class imbalance, and thus improve the model's generalizability.Main results. In the PhysioNet/Computing in Cardiology Challenge (2020), our proposed approach achieved a challenge validation score of 0.682, and a full test score of 0.514, placed us 3rd out of 40 in the official ranking.Significance. We proposed an accurate and robust predictive framework that combines deep neural networks and clinical knowledge to automatically classify multiple ECG abnormalities. Our framework is able to identify 27 ECG abnormalities from multi-lead ECG signals regardless of discrepancies in data sources and the imbalance of data labeling. We trained our framework on five datasets and validated it on six datasets from various countries. The outstanding performance demonstrate the effectiveness of our proposed framework.

A clinical diagnostic model based on an eXtreme Gradient Boosting algorithm to distinguish type 1 diabetes.

BACKGROUND: Accurate classification of type 1 diabetes (T1DM) and type 2 diabetes (T2DM) in the early phase is crucial for individual precision treatment. This study aimed to develop a classification model having fewer and easier to access clinical variables to distinguish T1DM in newly diagnosed diabetes in adults. METHODS: Clinical and laboratory data were collected from 15,206 adults with newly diagnosed diabetes in this cross-sectional study. This cohort represented 20 provinces and 4 municipalities in China. Types of diabetes were determined based on postprandial C-peptide (PCP) level and glutamic acid decarboxylase autoantibody (GADA) titer. We developed multivariable clinical diagnostic models using the eXtreme Gradient Boosting (XGBoost) algorithm. Classification variables included in the final model were based on their scores of importance. Model performance was evaluated by area under the receiver operating characteristic curve (ROC AUC), sensitivity, and specificity. The performance of models with different variable combinations was compared. Calibration intercept and slope were evaluated for the final model. RESULTS: Among the newly diagnosed diabetes cohort, 1,465 (9.63%) persons had T1DM and 13,741 (90.37%) had T2DM. Body mass index (BMI) contributed the most to the model, followed by age of onset and hemoglobin A1c (HbA1c). Compared with models with other clinical variable combinations, a final model that integrated age of onset, BMI and HbA1c had relatively higher performance. The ROC AUC, sensitivity, and specificity for this model were 0.83 (95% CI, 0.80 to 0.85), 0.77, and 0.76, respectively. The calibration intercept and slope were 0.02 (95% CI, -0.03 to 0.06) and 0.90 (95% CI, 0.79 to 1.02), respectively, which suggested a good calibration performance. CONCLUSIONS: Our classification model that integrated age of onset, BMI, and HbA1c could distinguish T1DM from T2DM, which provides a useful tool in assisting physicians in subtyping and precising treatment in diabetes.

A Guideline-Based Decision Tree Achieves Better Glucose Control with Less Hypoglycemia at 3 Months in Chinese Diabetic Patients.

INTRODUCTION: China has the world's largest diabetes epidemic and has been facing a serious shortage of primary care providers for chronic diseases including diabetes. To help primary care physicians follow guidelines and mitigate the workload in primary care communities in China, we developed a guideline-based decision tree. This study aimed to validate it at 3 months with real-world data. METHODS: The decision tree was developed based on the 2017 Chinese Type 2 Diabetes (T2DM) guideline and 2018 guideline for primary care. It was validated with the data from two registry studies: the NEW2D and ORBIT studies. Patients' data were divided into two groups: the compliance and non-compliance group, depending on whether the physician's prescription was consistent with the decision tree or not. The primary outcome was the difference of change in HbA1c from baseline to 3 months between the two groups. The secondary outcomes included the difference in the proportion of patients achieving HbA1c < 7% at 3 months between the two groups, the incidence of self-reported hypoglycemia at 3 months, and the proportion of patients (baseline HbA1c ≥ 7%) with a HbA1c reduction ≥ 0.3%. The statistical analysis was performed using linear or logistic regression with inverse probability of treatment weighting with adjustments of confounding factors. RESULTS: There was a 0.9% reduction of HbA1c in the compliance group and a 0.8% reduction in the non-compliance group (P < 0.001); 61.1% of the participants in the compliance group and 44.3% of the participants in the non-compliance group achieved a HbA1c level < 7% at 3 months (P < 0.001). The hypoglycemic events occurred in 7.1% of patients in the compliance group vs. 9.4% in the non-compliance group (P < 0.001). CONCLUSION: The decision tree can help physicians to treat their patients so that they achieve their glycemic targets with fewer hypoglycemic risks. ( http://www.clinicaltrials.gov NCT01525693 & NCT01859598).

Construction of Guideline-Based Decision Tree for Medication Recommendation.

Clinical decision support system (CDSS) plays an essential role nowadays and CDSS for treatment provides clinicians with the clinical evidence of candidate prescriptions to assist them in making patient-specific decisions. Therefore, it is essential to find a partition of patients such that patients with similar clinical conditions are grouped together and the preferred prescriptions for different groups are diverged. A comprehensive clinical guideline often provides information of patient partition. However, for most diseases, the guideline is not so detailed that only limited circumstances are covered. This makes it challenging to group patients properly. Here we proposed an approach that combines clinical guidelines with medical data to construct a nested decision tree for patient partitioning and treatment recommendation. Compared with pure data-driven decision tree, the recommendations generated by our model have better guideline adherence and interpretability. The approach was successfully applied in a real-world case study of patients with hyperthyroidism.

Influence of guideline adherence and parameter control on the clinical outcomes in patients with diabetic nephropathy.

INTRODUCTION: We assessed the association between guideline adherence and outcomes of clinical parameter control and end-stage kidney disease (ESKD), and further studied the effect of parameter control on ESKD for Chinese patients with diabetic nephropathy (DN). RESEARCH DESIGN AND METHODS: In this retrospective study, 1128 patients with DN (15,374 patient-visit samples) diagnosed by renal biopsy were enrolled. Samples were classified as adherence and nonadherence based on whether prescribed drugs conformed to medication regimen and drug contraindication recommended by guidelines, including American Diabetes Association (ADA) and Chinese guidelines. Guideline adherence rate was calculated on all samples for antihyperglycemic, antihypertensive and lipid-lowering treatments. Clinical parameter control was compared after 3-6 months' therapy between two groups by generalized estimating equation models. Time-dependent Cox models were applied to evaluate the influence of guideline adherence on ESKD. Latent class mixed model was used to identify distinct trajectories for parameters and their ESKD risks were compared using Cox proportional-hazards models. RESULTS: Guideline adherence rate of antihyperglycemic therapy was the highest, with 72.87% and 68.15% of samples meeting ADA and Chinese guidelines, respectively. Adherence was more likely to have good glycated hemoglobin A1c (HbA1c) control (ADA: OR 1.46, 95% CI 1.12 to 1.88; Chinese guideline: OR 1.42, 95% CI 1.09 to 1.85) and good blood pressure control (ADA: OR 1.35, 95% CI 1.03 to 1.78; Chinese guideline: OR 1.39, 95% CI 1.08 to 1.79) compared with nonadherence. The improvement of patient's adherence showed the potential to reduce ESKD risk. For proteinuria, low-density lipoprotein cholesterol (LDL-C), systolic blood pressure and uric acid, patients in higher-value trajectory group had higher ESKD risk. Proteinuria and LDL-C trajectories were most closely related to ESKD risk, while the risk was not significantly different in HbA1c trajectories. CONCLUSIONS: Guideline adherence and good control of proteinuria and LDL-C in clinical practice are important and in need for improving clinical outcomes in patients with DN.

Improving Anticoagulant Treatment Strategies of Atrial Fibrillation Using Reinforcement Learning.

In this paper, we developed a personalized anticoagulant treatment recommendation model for atrial fibrillation (AF) patients based on reinforcement learning (RL) and evaluated the effectiveness of the model in terms of short-term and long-term outcomes. The data used in our work were baseline and follow-up data of 8,540 AF patients with high risk of stroke, enrolled in the Chinese Atrial Fibrillation Registry (CAFR) study during 2011 to 2018. We found that in 64.98% of patient visits, the anticoagulant treatment recommended by the RL model were concordant with the actual prescriptions of the clinicians. Model-concordant treatments were associated with less ischemic stroke and systemic embolism (SSE) event compared with non-concordant ones, but no significant difference on the occurrence rate of major bleeding. We also found that higher proportion of model-concordant treatments were associated with lower risk of death. Our approach identified several high-confidence rules, which were interpreted by clinical experts.

An Approach of Integrating Domain Knowledge into Data-Driven Diagnostic Model.

A diagnostic model of general diseases could help general practitioners to decrease misdiagnoses and reduce workload. In this paper, we developed a neural network model that can classify potential diagnoses among 100 selected common diseases based on ambulatory health care data. We propose a novel approach to integrate domain knowledge into neural network training. The evaluation results show our model outperforming the baseline model in terms of knowledge consistency and model generalization.

Integrating Clinical Knowledge and Real-World Evidence for Type 2 Diabetes Treatment.

Clinical decision support system (CDSS) plays a significant role nowadays and it assists physicians in making decisions for treatment. Generally based on clinical guideline, the principles of the recommendation are provided and may suggest several candidate medications for similar patient group with certain clinical conditions. However, it is challenging to prioritize these candidates and even refine the guideline to a finer level for patient-specific recommendation. Here we propose a method and system to integrate the clinical knowledge and real-world evidence (RWE) for type 2 diabetes treatment, to enable both standardized and personalized medication recommendation. The RWE is generated by medication effectiveness analysis and subgroup analysis. The knowledge model has been verified by clinical experts from the advanced hospitals. The data verification results show that the medications that are consistent with the method recommendation can lead to better clinical outcome in terms of glycemic control, compared to those inconsistent.