DrugDoctor: enhancing drug recommendation in cold-start scenario via visit-level representation learning and training.

Medication recommendation is a crucial application of artificial intelligence in healthcare. Current methodologies mostly depend on patient-level longitudinal representation, which utilizes the entirety of historical electronic health records for making predictions. However, they tend to overlook a few key elements: (1) The need to analyze the impact of past medications on previous conditions. (2) Similarity in patient visits is more common than similarity in the complete medical histories of patients. (3) It is difficult to accurately represent patient-level longitudinal data due to the varying numbers of visits. To our knowledge, current models face difficulties in dealing with initial patient visits (i.e. in cold-start scenarios) which are common in clinical practice. This paper introduces DrugDoctor, an innovative drug recommendation model crafted to emulate the decision-making mechanics of human doctors. Unlike previous methods, DrugDoctor explores the visit-level relationship between prescriptions and diseases while considering the impact of past prescriptions on the patient's condition to provide more accurate recommendations. We design a plug-and-play block to effectively capture drug substructure-aware disease information and effectiveness-aware medication information, employing cross-attention and multi-head self-attention mechanisms. Furthermore, DrugDoctor adopts a fundamentally new visit-level training strategy, aligning more closely with the practices of doctors. Extensive experiments conducted on the MIMIC-III and MIMIC-IV datasets demonstrate that DrugDoctor outperforms 10 other state-of-the-art methods in terms of Jaccard, F1-score, and PRAUC. Moreover, DrugDoctor exhibits strong robustness in handling patients with varying numbers of visits and effectively tackles "cold-start" issues in medication combination recommendations.

A patient information mining network for drug recommendation.

As an important task of natural language processing, medication recommendation aims to recommend medication combinations according to the electronic health record, which can also be regarded as a multi-label classification task. But patients often have multiple diseases simultaneously, and the model must consider drug-drug interactions (DDI) of medication combinations when recommending medications, making medication recommendation more difficult. There is little existing work to explore the changes in patient conditions. However, these changes may point to future trends in patient conditions that are critical for reducing DDI rates in recommended drug combinations. In this paper, we proposed the Patient Information Mining Network (PIMNet), which models the current core medications of patient by mining the temporal and spatial changes of patient medication order and patient condition vector, and allocates some auxiliary medications as the currently recommended medication combination. The experimental results show that the proposed model greatly reduces the recommended DDI of medications while achieving results no lower than the state-of-the-art results.

ACDNet: Attention-guided Collaborative Decision Network for effective medication recommendation.

Medication recommendation using Electronic Health Records (EHR) is challenging due to complex medical data. Current approaches extract longitudinal information from patient EHR to personalize recommendations. However, existing models often lack sufficient patient representation and overlook the importance of considering the similarity between a patient's medication records and specific medicines. Therefore, an Attention-guided Collaborative Decision Network (ACDNet) for medication recommendation is proposed in this paper. Specifically, ACDNet utilizes attention mechanism and Transformer to effectively capture patient health conditions and medication records by modeling their historical visits at both global and local levels. ACDNet also employs a collaborative decision framework, utilizing the similarity between medication records and medicine representation to facilitate the recommendation process. The experimental results on two extensive medical datasets, MIMIC-III and MIMIC-IV, clearly demonstrate that ACDNet outperforms state-of-the-art models in terms of Jaccard, PR-AUC, and F1 score, reaffirming its superiority. Moreover, the ablation experiments provide solid evidence of the effectiveness of each module in ACDNet, validating their contribution to the overall performance. Furthermore, a detailed case study reinforces the effectiveness of ACDNet in medication recommendation based on EHR data, showcasing its practical value in real-world healthcare scenarios.

Concordance of provider chart notation and guideline-based classification of asthma severity.

OBJECTIVE: To evaluate concordance of asthma severity classification via physician chart notation compared with guideline-based criteria in adolescents with diagnosed asthma. METHODS: Of 284 urban primary care and subspecialty clinic patients aged 13-18 years approached through convenience sampling, 203 surveys were completed (RR = 71.5%). We assessed concordance with sensitivity, specificity, and positive predictive values; overall agreement was evaluated with weighted kappa coefficients and McNemar's test. RESULTS: When considering prescribed treatment according to NAEPP guidelines as a gold standard, the sensitivity for chart notation was very good for intermittent (95%) and less for non-intermittent severity ratings (51%, 58%, and 67% for moderate, severe, and mild persistent asthma, respectively). Overall agreement between chart notation and guideline-based asthma criteria ranged from fair-to-good for mild- (k = 0.36), moderate- (k = 0.44), and severe-persistent severity (k = 0.66). Although the agreement for intermittent severity was highest (k = 0.88), it did not significantly differ by between the two classifications (p ≥ 0.05). CONCLUSIONS: Concordance for all non-intermittent asthma severity classifications varied between physician and medication-driven 2007 NAEPP guideline classifications in an ethnically diverse urban adolescent patient sample. Physicians should remain aware of the potential for this discordance and refer to the guidelines to classify and treat adolescents with asthma.

DGCL: Distance-wise and Graph Contrastive Learning for medication recommendation.

Medicine recommendation aims to provide a combination of medicine based on the patient's electronic health record (EHR), which is an essential task in healthcare. Existing methods either base recommendations on EHRs or provide models with knowledge of drug-drug interactions (DDIs) to achieve DDI reduction. However, the former models the patient's health history but ignores undesirable DDIs, while the latter lacks mining of patient health records and gets low recommendation accuracy. Therefore, this study contributes to research on personalized medication recommendations that consider drug interaction effects and models the patient's past medical history. In this paper, the Distance-wise and Graph Contrastive Learning (DGCL) framework is proposed. Specifically, we develop a two-stage neural network module for clinical record learning. We propose the distance detection loss to model the difference between the output distribution of current cases and historical records. In the DDI recognition and control task, DGCL proposes a graph contrastive learning method to jointly train the DDI knowledge graph and the electronic record graph, thereby effectively controlling the level of DDI for recommended medications. By comparing the performance on the MIMIC-III dataset with several baselines, DGCL outperforms other models in terms of efficacy and safety.

MR-KPA: medication recommendation by combining knowledge-enhanced pre-training with a deep adversarial network.

BACKGROUND: Medication recommendation based on electronic medical record (EMR) is a research hot spot in smart healthcare. For developing computational medication recommendation methods based on EMR, an important challenge is the lack of a large number of longitudinal EMR data with time correlation. Faced with this challenge, this paper proposes a new EMR-based medication recommendation model called MR-KPA, which combines knowledge-enhanced pre-training with the deep adversarial network to improve medication recommendation from both feature representation and the fine-tuning process. Firstly, a knowledge-enhanced pre-training visit model is proposed to realize domain knowledge-based external feature fusion and pre-training-based internal feature mining for improving the feature representation. Secondly, a medication recommendation model based on the deep adversarial network is developed to optimize the fine-tuning process of pre-training visit model and alleviate over-fitting of model caused by the task gap between pre-training and recommendation. RESULT: The experimental results on EMRs from medical and health institutions in Hainan Province, China show that the proposed MR-KPA model can effectively improve the accuracy of medication recommendation on small-scale longitudinal EMR data compared with existing representative methods. CONCLUSION: The advantages of the proposed MR-KPA are mainly attributed to knowledge enhancement based on ontology embedding, the pre-training visit model and adversarial training. Each of these three optimizations is very effective for improving the capability of medication recommendation on small-scale longitudinal EMR data, and the pre-training visit model has the most significant improvement effect. These three optimizations are also complementary, and their integration makes the proposed MR-KPA model achieve the best recommendation effect.

TAHDNet: Time-aware hierarchical dependency network for medication recommendation.

Medication recommendation is a hot topic in the research of applying neural networks to the healthcare area. Although extensive progressions have been made, current researches still face the following challenges: (i). Existing methods are poor at efficiently capturing and leveraging local and global dependency information from patient visit records. (ii). Current time-aware models based on irregularly interval medical records tend to ignore periodic variability in patient conditions, which limits the representational learning capability of these models. Therefore, we propose a Dynamic Time-aware Hierarchical Dependency Network (TAHDNet) for the medication recommendation task to address these challenges. Firstly, we use a Transformer-based model to learn the global information of the whole patient record through a self-supervised pre-training process. Secondly, a 1D-CNN model is used to learn the local dependencies on visitation level. Thirdly, we propose a dynamic time-aware module with a fused temporal decay function to assign different weights among different time intervals dynamically through a key-value attention mechanism. Experimental results on real-world datasets demonstrate the effectiveness of the model proposed in this paper.

MedGCN: Medication recommendation and lab test imputation via graph convolutional networks.

Laboratory testing and medication prescription are two of the most important routines in daily clinical practice. Developing an artificial intelligence system that can automatically make lab test imputations and medication recommendations can save costs on potentially redundant lab tests and inform physicians of a more effective prescription. We present an intelligent medical system (named MedGCN) that can automatically recommend the patients' medications based on their incomplete lab tests, and can even accurately estimate the lab values that have not been taken. In our system, we integrate the complex relations between multiple types of medical entities with their inherent features in a heterogeneous graph. Then we model the graph to learn a distributed representation for each entity in the graph based on graph convolutional networks (GCN). By the propagation of graph convolutional networks, the entity representations can incorporate multiple types of medical information that can benefit multiple medical tasks. Moreover, we introduce a cross regularization strategy to reduce overfitting for multi-task training by the interaction between the multiple tasks. In this study, we construct a graph to associate 4 types of medical entities, i.e., patients, encounters, lab tests, and medications, and applied a graph neural network to learn node embeddings for medication recommendation and lab test imputation. we validate our MedGCN model on two real-world datasets: NMEDW and MIMIC-III. The experimental results on both datasets demonstrate that our model can outperform the state-of-the-art in both tasks. We believe that our innovative system can provide a promising and reliable way to assist physicians to make medication prescriptions and to save costs on potentially redundant lab tests.

Recommendations service for chronic disease patient in multimodel sensors home environment.

With advanced technologies in hand, there exist potential applications and services built around monitoring activities of daily living (ADL) of elderly people at nursing homes. Most of the elderly people in these facilities are suffering from different chronic diseases such as dementia. Existing technologies are mainly focusing on non-medication interventions and monitoring of ADL for addressing loss of autonomy or well-being. Monitoring and managing ADL related to cognitive behaviors for non-medication intervention are very effective in improving dementia patients' conditions. However, cognitive functions of patients can be improved if appropriate recommendations of medications are delivered at a particular time. Previously we developed the Secured Wireless Sensor Network Integrated Cloud Computing for Ubiquitous-Life Care (SC(3)). SC(3) services were limited to monitoring ADL of elderly people with Alzheimer's disease and providing non-medication recommendations to the patient. In this article, we propose a system called the Smart Clinical Decision Support System (CDSS) as an integral part of the SC(3) platform. Using the Smart CDSS, patients are provided with access to medication recommendations of expert physicians. Physicians are provided with an interface to create clinical knowledge for medication recommendations and to observe the patient's condition. The clinical knowledge created by physicians as the knowledge base of the Smart CDSS produces recommendations to the caregiver for medications based on each patient's symptoms.

CEHMR: Curriculum learning enhanced hierarchical multi-label classification for medication recommendation.

The medication recommendation (MR) or medication combination prediction task aims to predict effective prescriptions given accurate patient representations derived from electronic health records (EHRs), which contributes to improving the quality of clinical decision-making, especially for patients with multi-morbidity. Although in recent years deep learning technology has achieved great success in MR, the performance of current multi-label based MR solutions is unsatisfactory. They mainly focus on improving the patient representation module and modeling the medication label dependencies such as drug-drug interaction (DDI) correlation and co-occurrence relationship. However, the hierarchical dependency among medication labels and diversity of difficulty among MR training examples lack sufficient consideration. In this paper, we propose a framework of Curriculum learning Enhanced Hierarchical multi-label classification for MR (CEHMR). Motivated by the category hierarchy of medications which organizes standard medication codes in a hierarchical structure, we utilize it to provide more trustworthy prior knowledge for modeling label dependency. Specifically, we design a hierarchical multi-label classifier with a learnable gate fusion layer, to simultaneously capture the level-independent (local) and level-dependent (global) hierarchical information in the medication hierarchy. In addition, to overcome the diversity of training example difficulties, and progressively achieve a smoother training process, we introduce a bootstrap-based curriculum learning strategy. Hence, the example difficulty can be measured based on the predictive performance of the MR model, and then all training examples would be retrained from easy to hard under the guidance of a predefined training scheduler. Experiments on the real-world medical MIMIC-III database demonstrate that the proposed framework can achieve state-of-the-art performance compared with seven representative baselines, and extensive ablation studies validate the effectiveness of each component of CEHMR.

A-GSTCN: An Augmented Graph Structural-Temporal Convolution Network for Medication Recommendation Based on Electronic Health Records.

Medication recommendation based on electronic health records (EHRs) is a significant research direction in the biomedical field, which aims to provide a reasonable prescription for patients according to their historical and current health conditions. However, the existing recommended methods have many limitations in dealing with the structural and temporal characteristics of EHRs. These methods either only consider the current state while ignoring the historical situation, or fail to adequately assess the structural correlations among various medical events. These factors result in poor recommendation quality. To solve this problem, we propose an augmented graph structural-temporal convolutional network (A-GSTCN). Firstly, an augmented graph attention network is used to model the structural features among medical events of patients' EHRs. Next, the dilated convolution combined with residual connection is applied in the proposed model, which can improve the temporal prediction capability and further reduce the complexity. Moreover, the cache memory module further enhances the model's learning of the history of EHRs. Finally, the A-GSTCN model is compared with the baselines through experiments, and the efficiency of the A-GSTCN model is verified by Jaccard, F1 and PRAUC. Not only that, the proposed model also reduces the training parameters by an order of magnitude.

Artificial-Intelligence-Driven Algorithms for Predicting Response to Corticosteroid Treatment in Patients with Post-Acute COVID-19.

Pulmonary fibrosis is one of the most severe long-term consequences of COVID-19. Corticosteroid treatment increases the chances of recovery; unfortunately, it can also have side effects. Therefore, we aimed to develop prediction models for a personalized selection of patients benefiting from corticotherapy. The experiment utilized various algorithms, including Logistic Regression, k-NN, Decision Tree, XGBoost, Random Forest, SVM, MLP, AdaBoost, and LGBM. In addition easily human-interpretable model is presented. All algorithms were trained on a dataset consisting of a total of 281 patients. Every patient conducted an examination at the start and three months after the post-COVID treatment. The examination comprised a physical examination, blood tests, functional lung tests, and an assessment of health state based on X-ray and HRCT. The Decision tree algorithm achieved balanced accuracy (BA) of 73.52%, ROC-AUC of 74.69%, and 71.70% F1 score. Other algorithms achieving high accuracy included Random Forest (BA 70.00%, ROC-AUC 70.62%, 67.92% F1 score) and AdaBoost (BA 70.37%, ROC-AUC 63.58%, 70.18% F1 score). The experiments prove that information obtained during the initiation of the post-COVID-19 treatment can be used to predict whether the patient will benefit from corticotherapy. The presented predictive models can be used by clinicians to make personalized treatment decisions.

On-ward participation of clinical pharmacists in a Chinese intensive care unit for patients with COVID-19: A retrospective, observational study.

BACKGROUND: The practical experiences of active pharmacists involved in managing critically ill patients with coronavirus disease 2019 (COVID-19) have been rarely reported. OBJECTIVE: This work aimed to share professional experiences on medication optimization and provide a feasible reference for the pharmaceutical care of critically ill patients with COVID-19. METHODS: This study was conducted in a COVID-19-designated hospital in China. A group of dedicated clinical pharmacists participated in multidisciplinary rounds to optimize the treatments for critically ill patients with COVID-19. Consensus on medication recommendations was reached by a multidisciplinary team through bi-daily discussion. Related drug, classification, cause, and adjustment content for recommendations were recorded and reviewed. RESULTS: A total of 111 medication recommendations were supplied for 22 out of 33 (56.7%) critically ill patients from 1 February 2020 to 18 March 2020, and 106 (95.5%) of these were accepted. Among these recommendations, 64 (67.7%), 32 (28.8%), and 15 (13.5%) were related to antibiotics and antifungals, antiviral agents, and other drugs, respectively. Recommendation types significantly differed for different anti-infectives (p < 0.05). For antibiotics and antifungals, treatment effectiveness accounted for 60.9% of recommendation types, with 15 (38.5%) cases related to untreated infections. For antiviral agents, adverse drug events were the most common recommendation types (84.4%), with 20 (74.1%) cases related to liver function dysfunction. Discontinuation of suspected antiviral agents (66.7%) was usually recommended after the occurrence of adverse events that may progress and bring poor outcomes. CONCLUSION: Forceful and extensive on-ward participation is recommended for clinical pharmacists in managing critically ill patients. Our experiences highlight the need for special attention toward untreated infections and adverse events related to antiviral agents.

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.

A smart medication recommendation model for the electronic prescription.

BACKGROUND: The report from the Institute of Medicine, To Err Is Human: Building a Safer Health System in 1999 drew a special attention towards preventable medical errors and patient safety. The American Reinvestment and Recovery Act of 2009 and federal criteria of 'Meaningful use' stage 1 mandated e-prescribing to be used by eligible providers in order to access Medicaid and Medicare incentive payments. Inappropriate prescribing has been identified as a preventable cause of at least 20% of drug-related adverse events. A few studies reported system-related errors and have offered targeted recommendations on improving and enhancing e-prescribing system. OBJECTIVE: This study aims to enhance efficiency of the e-prescribing system by shortening the medication list, reducing the risk of inappropriate selection of medication, as well as in reducing the prescribing time of physicians. METHOD: 103.48 million prescriptions from Taiwan's national health insurance claim data were used to compute Diagnosis-Medication association. Furthermore, 100,000 prescriptions were randomly selected to develop a smart medication recommendation model by using association rules of data mining. RESULTS AND CONCLUSION: The important contribution of this model is to introduce a new concept called Mean Prescription Rank (MPR) of prescriptions and Coverage Rate (CR) of prescriptions. A proactive medication list (PML) was computed using MPR and CR. With this model the medication drop-down menu is significantly shortened, thereby reducing medication selection errors and prescription times. The physicians will still select relevant medications even in the case of inappropriate (unintentional) selection.