Background: Discharge medical notes written by physicians contain important information about the health condition of patients. Many deep learning algorithms have been successfully applied to extract important information from unstructured medical notes data that can entail subsequent actionable results in the medical domain. This study aims to explore the model performance of various deep learning algorithms in text classification tasks on medical notes with respect to different disease class imbalance scenarios.Methods: In this study, we employed seven artificial intelligence models, a CNN (Convolutional Neural Network), a Transformer encoder, a pretrained BERT (Bidirectional Encoder Representations from Transformers), and four typical sequence neural networks models, namely, RNN (Recurrent Neural Network), GRU (Gated Recurrent Unit), LSTM (Long Short-Term Memory), and Bi-LSTM (Bi-directional Long Short-Term Memory) to classify the presence or absence of 16 disease conditions from patients’ discharge summary notes. We analyzed this question as a composition of 16 binary separate classification problems. The model performance of the seven models on each of the 16 datasets with various levels of imbalance between classes were compared in terms of AUC-ROC (Area Under the Curve of the Receiver Operating Characteristic), AUC-PR (Area Under the Curve of Precision and Recall), F1 Score, and Balanced Accuracy as well as the training time. The model performances were also compared in combination with different word embedding approaches (GloVe, BioWordVec, and no pre-trained word embeddings).Results: The analyses of these 16 binary classification problems showed that the Transformer encoder model performs the best in nearly all scenarios. In addition, when the disease prevalence is close to or greater than 50%, the Convolutional Neural Network model achieved a comparable performance to the Transformer encoder, and its training time was 17.6% shorter than the second fastest model, 91.3% shorter than the Transformer encoder, and 94.7% shorter than the pre-trained BERT-Base model. The BioWordVec embeddings slightly improved the performance of the Bi-LSTM model in most disease prevalence scenarios, while the CNN model performed better without pre-trained word embeddings. In addition, the training time was significantly reduced with the GloVe embeddings for all models.Conclusions: For classification tasks on medical notes, Transformer encoders are the best choice if the computation resource is not an issue. Otherwise, when the classes are relatively balanced, CNNs are a leading candidate because of their competitive performance and computational efficiency.

Background: Alzheimer’s disease (AD) is the most common neurodegenerative disease. Studying the effects of drug treatments on multiple health outcomes related to AD could be beneficial in demonstrating which drugs reduce the disease burden and increase survival. Methods: We conducted a comprehensive causal inference study implementing doubly robust estimators and using one of the largest high-quality medical databases, the Oracle Electronic Health Records (EHR) Real-World Data. Our work was focused on the estimation of the effects of the two common Alzheimer’s disease drugs, Donepezil and Memantine, and their combined use on the five-year survival since initial diagnosis of AD patients. Also, we formally tested for the presence of interaction between these drugs. Results: Here, we show that the combined use of Donepezil and Memantine significantly elevates the probability of five-year survival. In particular, their combined use increases the probability of five-year survival by 0.050 (0.021, 0.078) (6.4%), 0.049 (0.012, 0.085), (6.3%), 0.065 (0.035, 0.095) (8.3%) compared to no drug treatment, the Memantine monotherapy, and the Donepezil monotherapy respectively. We also identify a significant beneficial additive drug-drug interaction effect between Donepezil and Memantine of 0.064 (0.030, 0.098). Conclusions: Based on our findings, adopting combined treatment of Memantine and Donepezil could extend the lives of approximately 303,000 people with AD living in the USA to be beyond five-years from diagnosis. If these patients instead have no drug treatment, Memantine monotherapy or Donepezil monotherapy they would be expected to die within five years.

We propose a modification of the well-known Armitage trend test to address the problems associated with hidden population structure and hidden relatedness in genome-wide case-control association studies. The new test adopts beneficial traits from three existing testing strategies: the principal components, mixed model, and genomic control while avoiding some of their disadvantageous characteristics, such as the tendency of the principal components method to over-correct in certain situations or the failure of the genomic control approach to reorder the adjusted tests based on their degree of alignment with the underlying hidden structure. The new procedure is based on Gauss-Markov estimators derived from a straightforward linear model with an imposed variance structure proportional to an empirical relatedness matrix. Lastly, conceptual and analytical similarities to and distinctions from other approaches are emphasized throughout. Our simulations show that the power performance of the proposed test is quite promising compared to the considered competing strategies. The power gains are especially large when small differential differences between cases and controls are present; a likely scenario when public controls are used in multiple studies. The proposed modified approach attains high power more consistently than that of the existing commonly implemented tests. Its performance improvement is most apparent when small but detectable systematic differences between cases and controls exist.

Barth Syndrome (BTHS) is a serious X-linked genetic disorder associated with mutations in the tafazzin gene (TAZ, also called G4.5). The multi-system disorder is primarily characterized by the following pathologies: cardiac and skeletal myopathies, neutropenia, growth delay, and exercise intolerance. Although growth anomalies have been widely reported in BTHS, there is a paucity of research on the role of inflammation and the potential link to alterations in growth factors levels in BTHS patients.

The discovery of novel therapeutic compounds through de novo drug design represents a critical challenge in the field of pharmaceutical research. Traditional drug discovery approaches are often resource intensive and time consuming, leading researchers to explore innovative methods that harness the power of deep learning and reinforcement learning techniques. Here, we introduce a novel drug design approach called drugAI that leverages the Encoder–Decoder Transformer architecture in tandem with Reinforcement Learning via a Monte Carlo Tree Search (RL-MCTS) to expedite the process of drug discovery while ensuring the production of valid small molecules with drug-like characteristics and strong binding affinities towards their targets. We successfully integrated the Encoder–Decoder Transformer architecture, which generates molecular structures (drugs) from scratch with the RL-MCTS, serving as a reinforcement learning framework. The RL-MCTS combines the exploitation and exploration capabilities of a Monte Carlo Tree Search with the machine translation of a transformer-based Encoder–Decoder model. This dynamic approach allows the model to iteratively refine its drug candidate generation process, ensuring that the generated molecules adhere to essential physicochemical and biological constraints and effectively bind to their targets. The results from drugAI showcase the effectiveness of the proposed approach across various benchmark datasets, demonstrating a significant improvement in both the validity and drug-likeness of the generated compounds, compared to two existing benchmark methods. Moreover, drugAI ensures that the generated molecules exhibit strong binding affinities to their respective targets. In summary, this research highlights the real-world applications of drugAI in drug discovery pipelines, potentially accelerating the identification of promising drug candidates for a wide range of diseases.