A fair and interpretable network for clinical risk prediction: a regularized multi-view multi-task learning approach.

In healthcare domain, complication risk profiling which can be seen as multiple clinical risk prediction tasks is challenging due to the complex interaction between heterogeneous clinical entities. With the availability of real-world data, many deep learning methods are proposed for complication risk profiling. However, the existing methods face three open challenges. First, they leverage clinical data from a single view and then lead to suboptimal models. Second, most existing methods lack an effective mechanism to interpret predictions. Third, models learned from clinical data may have inherent pre-existing biases and exhibit discrimination against certain social groups. We then propose a multi-view multi-task network (MuViTaNet) to tackle these issues. MuViTaNet complements patient representation by using a multi-view encoder to exploit more information. Moreover, it uses a multi-task learning to generate more generalized representations using both labeled and unlabeled datasets. Last, a fairness variant (F-MuViTaNet) is proposed to mitigate the unfairness issues and promote healthcare equity. The experiments show that MuViTaNet outperforms existing methods for cardiac complication profiling. Its architecture also provides an effective mechanism for interpreting the predictions, which helps clinicians discover the underlying mechanism triggering the complication onsets. F-MuViTaNet can also effectively mitigate the unfairness with only negligible impact on accuracy.

Marrying Medical Domain Knowledge With Deep Learning on Electronic Health Records: A Deep Visual Analytics Approach.

BACKGROUND: Deep learning models have attracted significant interest from health care researchers during the last few decades. There have been many studies that apply deep learning to medical applications and achieve promising results. However, there are three limitations to the existing models: (1) most clinicians are unable to interpret the results from the existing models, (2) existing models cannot incorporate complicated medical domain knowledge (eg, a disease causes another disease), and (3) most existing models lack visual exploration and interaction. Both the electronic health record (EHR) data set and the deep model results are complex and abstract, which impedes clinicians from exploring and communicating with the model directly. OBJECTIVE: The objective of this study is to develop an interpretable and accurate risk prediction model as well as an interactive clinical prediction system to support EHR data exploration, knowledge graph demonstration, and model interpretation. METHODS: A domain-knowledge-guided recurrent neural network (DG-RNN) model is proposed to predict clinical risks. The model takes medical event sequences as input and incorporates medical domain knowledge by attending to a subgraph of the whole medical knowledge graph. A global pooling operation and a fully connected layer are used to output the clinical outcomes. The middle results and the parameters of the fully connected layer are helpful in identifying which medical events cause clinical risks. DG-Viz is also designed to support EHR data exploration, knowledge graph demonstration, and model interpretation. RESULTS: We conducted both risk prediction experiments and a case study on a real-world data set. A total of 554 patients with heart failure and 1662 control patients without heart failure were selected from the data set. The experimental results show that the proposed DG-RNN outperforms the state-of-the-art approaches by approximately 1.5%. The case study demonstrates how our medical physician collaborator can effectively explore the data and interpret the prediction results using DG-Viz. CONCLUSIONS: In this study, we present DG-Viz, an interactive clinical prediction system, which brings together the power of deep learning (ie, a DG-RNN-based model) and visual analytics to predict clinical risks and visually interpret the EHR prediction results. Experimental results and a case study on heart failure risk prediction tasks demonstrate the effectiveness and usefulness of the DG-Viz system. This study will pave the way for interactive, interpretable, and accurate clinical risk predictions.

An interpretable risk prediction model for healthcare with pattern attention.

BACKGROUND: The availability of massive amount of data enables the possibility of clinical predictive tasks. Deep learning methods have achieved promising performance on the tasks. However, most existing methods suffer from three limitations: (1) There are lots of missing value for real value events, many methods impute the missing value and then train their models based on the imputed values, which may introduce imputation bias. The models' performance is highly dependent on the imputation accuracy. (2) Lots of existing studies just take Boolean value medical events (e.g. diagnosis code) as inputs, but ignore real value medical events (e.g., lab tests and vital signs), which are more important for acute disease (e.g., sepsis) and mortality prediction. (3) Existing interpretable models can illustrate which medical events are conducive to the output results, but are not able to give contributions of patterns among medical events. METHODS: In this study, we propose a novel interpretable Pattern Attention model with Value Embedding (PAVE) to predict the risks of certain diseases. PAVE takes the embedding of various medical events, their values and the corresponding occurring time as inputs, leverage self-attention mechanism to attend to meaningful patterns among medical events for risk prediction tasks. Because only the observed values are embedded into vectors, we don't need to impute the missing values and thus avoids the imputations bias. Moreover, the self-attention mechanism is helpful for the model interpretability, which means the proposed model can output which patterns cause high risks. RESULTS: We conduct sepsis onset prediction and mortality prediction experiments on a publicly available dataset MIMIC-III and our proprietary EHR dataset. The experimental results show that PAVE outperforms existing models. Moreover, by analyzing the self-attention weights, our model outputs meaningful medical event patterns related to mortality. CONCLUSIONS: PAVE learns effective medical event representation by incorporating the values and occurring time, which can improve the risk prediction performance. Moreover, the presented self-attention mechanism can not only capture patients' health state information, but also output the contributions of various medical event patterns, which pave the way for interpretable clinical risk predictions. AVAILABILITY: The code for this paper is available at: https://github.com/yinchangchang/PAVE .

Combining structured and unstructured data for predictive models: a deep learning approach.

BACKGROUND: The broad adoption of electronic health records (EHRs) provides great opportunities to conduct health care research and solve various clinical problems in medicine. With recent advances and success, methods based on machine learning and deep learning have become increasingly popular in medical informatics. However, while many research studies utilize temporal structured data on predictive modeling, they typically neglect potentially valuable information in unstructured clinical notes. Integrating heterogeneous data types across EHRs through deep learning techniques may help improve the performance of prediction models. METHODS: In this research, we proposed 2 general-purpose multi-modal neural network architectures to enhance patient representation learning by combining sequential unstructured notes with structured data. The proposed fusion models leverage document embeddings for the representation of long clinical note documents and either convolutional neural network or long short-term memory networks to model the sequential clinical notes and temporal signals, and one-hot encoding for static information representation. The concatenated representation is the final patient representation which is used to make predictions. RESULTS: We evaluate the performance of proposed models on 3 risk prediction tasks (i.e. in-hospital mortality, 30-day hospital readmission, and long length of stay prediction) using derived data from the publicly available Medical Information Mart for Intensive Care III dataset. Our results show that by combining unstructured clinical notes with structured data, the proposed models outperform other models that utilize either unstructured notes or structured data only. CONCLUSIONS: The proposed fusion models learn better patient representation by combining structured and unstructured data. Integrating heterogeneous data types across EHRs helps improve the performance of prediction models and reduce errors.

[FOXO4 maintains senescence in human umbilical cord mesenchymal stem cells by repressing apoptosis].

The purpose of the present study was to investigate the effects of forkhead box O4 (FOXO4) on the senescence of human umbilical cord-derived mesenchymal stem cells (hUC-MSCs). The hUC-MSCs were induced to senescence by natural passage, and FOXO4 expression was inhibited by lentiviral shRNA transfection. The hallmark of cell senescence was analyzed by ß-galactosidase staining, and the cell viability was assayed by CCK-8 method. Flow cytometry was used to investigate the apoptosis of hUC-MSCs. The expression levels of Bcl-2, Bax, FOXO4, interleukin 6 (IL-6) and cleaved Caspase-3 were detected by qPCR and Western blot. Immunofluorescence staining was used to detect FOXO4 expression. The amount of IL-6 secreted by hUC-MSCs was detected by ELISA. The results showed that, compared with the passage 1, senescent hUC-MSCs showed up-regulated expression levels of Bax and FOXO4, down-regulated expression levels of Bcl-2 and cleaved Caspase-3, and increased IL-6 mRNA expression and secretion. FOXO4 inhibition in senescent hUC-MSCs promoted cell apoptosis, reduced cell viability, and inhibited the mRNA expression and secretion of IL-6. These results suggest that FOXO4 maintains viability and function of senescent hUC-MSCs by repressing their apoptosis response, thus accelerating senescence of the whole cell colony.

17ß-estradiol protects nucleus pulposus cells from serum deprivation-induced apoptosis and regulates expression of MMP-3 and MMP-13 through promotion of autophagy.

Serum deprivation is a likely contributor to intervertebral disc (IVD) degeneration (IVDD).17ß-estradiol (E2) have been noted to protect nucleus pulposus cells (NPCs) against apoptosis. Autophagy and apoptosis play a paramount role in maintaining the homeostasis of IVD. So far, little research has been published on whether autophagy plays a role for the E2 mediated protection of NPCs. The aim of this study is to understand whether autophagy is involved in the protective effect of E2 against serum deprivation-induced cell apoptosis and expression of matrix metalloproteinase (MMP)-3 and MMP-13. mCherry-GFP-LC3-adenovirus transfection is used to monitor autophagy detection. The expression levels of autophagy-related proteins were measured by Western blotting, Apoptosis and MMPs were detected by flow cytometry and Western blotting. Accordingly, Autophagy and apoptosis was detected in NP cells under serum deprivation conditions, the autophagy incidence began to reached a peak value at 48 h, the apoptosis and MMPs incidence began reached a minimum value treat with E2 (10-7 M). Whereas the combined use of E2 and 3-MA led to a dramatic decrease in autophagy, while aberrantly elevated expression levels of apoptotic and MMPs. These data suggest that serum deprivation-induced apoptosis and MMP-3, MMP-13, which was efficiently suppressed by the E2 through promoting autophagy in rat NPCs.

[Effect of Total Ravonoids of Herba Epimedium on BMP-2/RunX2/OSX Signaling Pathway during Osteogenic Differentiation of Bone Marrow Mesenchymal Stem Cells].

OBJECTIVE: To explore the effect of total flavonoids of Herba Epimedium (FHE) on BMP-2/RunX2/OSX signaling pathway in promoting osteogenic differentiation of bone marrow mesenchymal stem cells (BMSCs). METHODS: Passage 3 BMSCs were randomly divided into the control group, the experimental group, and the inhibitor group. BMSCs in the control group were cultured in 0.2% dimethyl sulfoxide + Osteogenuxic Supplement (OS) fluid + DMEM/F12 culture media. BMSCs in the experimental group were intervened by 20 microg/mL FHE. BMSCs in the inhibitor group were intervened by 20 microg/mL FHE and 1 microg/mL NOGGIN recombinant protein. At day 9 alkaline phosphatase (ALP) activity was measured. Calcium nodules were stained by alizarin red staining and the density was observed. The transcription expression of osteogenic differentiation-related proteins (type I collagen, osteocalcin, and osteopontin) and related factors of BMP-2/RunX2/OSX signaling pathway was assayed by RT-PCR. RESULTS: Compared with the control group, ALP activities were enhanced and the density of calcium nodules significantly increased; type I collagen, osteocalcin, and osteopontin expression levels were increased in the experimental group. The expression of osteogenesis-related transcription factor was also increased in the experimental group. Noggin recombinant protein inhibited FHE promoting BMSCs osteogenesis in the inhibitor group. Compared with the experimental group, ALP activity decreased (P < 0.05), the density of calcium nodules was lowered, expression levels of type I collagen, osteocalcin, osteopontin significantly decreased (P < 0.05) in the inhibitor group. CONCLUSION: 20 microg/mL FHE promoted osteogenic differentiation process of BMSCs by BMP-2/RunX2/OSX signaling pathway.

[Icaritin promotes chondrogenic differentiation of BMSCs by Wnt/ß-catenin signaling pathway].

To investigate the effect of icaritin (ICT) combined with GDF-5 on chondrogenic differentiation of bone marrow stromal cells (BMSCs), and discuss the action of Wnt signaling pathway, full bone marrow adherent method was used to isolate and culture SD rats BMSCs, and the cells at P3 generation were taken and divided into 6 groups： BMSCs group, ICT group, GDF-5 group, GDF-5+ICT group, GDF-5+ICT+SB216763 group, and GDF-5+ICT+ XAV-939 group. The cells were induced and cultured for 14 days. The morphology change was observed by inverted microscope. Alcian blue staining method was used to detect the changes of proteoglycans. RT-PCR was used to detect the mRNA expressions of aggrecan, Col2, Sox9, Dvl1, Gsk3ß, and ß-catenin. The protein expressions of collagen 2 (COL2) and ß-catenin were detected by Western blot. The results indicated that, compared with the BMSCs group, gradual increase was present in proteoglycan Alcian blue staining; mRNA expressions of cartilage differentiation marker genes aggrecan, COL2, Sox9 and the protein expression of COL2, as well as mRNA and protein expressions of Wnt signaling pathway-related gene ß-catenin, but with gradual decrease in Gsk3ß mRNA expressions in GDF-5 group, GDF-5+ICT group and GDF-5+ICT+SB216763 group. On the contrary, compared with GDF-5+ICT group, there was a decrease in expressions of Dvl1, and ß-catenin related to chondrogenic differentiation and Wnt signaling pathway, a increase in Gsk3ß mRNA expression, and also a decrease in protein expressions of COL2 and ß-catenin in GDF-5+ICT+XAV-939 group, with statistically significant difference between two groups. GDF-5 in combination with icaritin can induce chondrogenic differentiation of BMSCs in rats, and icaritin (ICT) can promote the chondrogenic differentiation. ICT can promote the chondrogenic differentiation of BMSCs in vitro probably by activating the Wnt/ß-catenin signaling pathway.

[Mechanism of chlorogenic acid on apoptosis of rat nucleus pulposus cells induced by oxidative stress].

OBJECTIVE: To investigate the mechanism of chlorogenic acid (CGA) on H2O2-induced apoptosis in the rat nucleus pulposus cells (NPCs). METHODS: NPCs were isolated from SD rats and cultured in vitro. Cultured cells (P3) were randomly divided into normal control group, H2O2 group, CGA + H2O2 group, CGA group and LY294002 pretreatment group. The apoptosis and ROS production of rNPCs was detected by flow cytometry. The expressions of p-Akt, BCL-2 and Akt were analyzed by Western blot. RESULTS: Compared with normal control group, in the H2O2 group, the production of ROS and the apoptosis rate significantly increased in rNPCs; CGA treatment inhibited ROS production and cell apoptosis, while increased the expression of p-Akt and BCL-2; LY294002, a PI3Kinse inhibitor, not only decreased the expression of p-Akt and BCL-2, but also obviously increased ROS production and cell apoptosis. CONCLUSION: Chlorogenic acid can protect NPCs against apoptosis by oxidative stress through decreasing reactive oxygen species production and increasing anti-apoptotic protein BCL-2 expression in NPCs by activation of PI3K-Akt signaling pathways.

Multimodal risk prediction with physiological signals, medical images and clinical notes.

The broad adoption of electronic health record (EHR) systems brings us a tremendous amount of clinical data and thus provides opportunities to conduct data-based healthcare research to solve various clinical problems in the medical domain. Machine learning and deep learning methods are widely used in the medical informatics and healthcare domain due to their power to mine insights from raw data. When adapting deep learning models for EHR data, it is essential to consider its heterogeneous nature: EHR contains patient records from various sources including medical tests (e.g. blood test, microbiology test), medical imaging, diagnosis, medications, procedures, clinical notes, etc. Those modalities together provide a holistic view of patient health status and complement each other. Therefore, combining data from multiple modalities that are intrinsically different is challenging but intuitively promising in deep learning for EHR. To assess the expectations of multimodal data, we introduce a comprehensive fusion framework designed to integrate temporal variables, medical images, and clinical notes in EHR for enhanced performance in clinical risk prediction. Early, joint, and late fusion strategies are employed to combine data from various modalities effectively. We test the model with three predictive tasks: in-hospital mortality, long length of stay, and 30-day readmission. Experimental results show that multimodal models outperform uni-modal models in the tasks involved. Additionally, by training models with different input modality combinations, we calculate the Shapley value for each modality to quantify their contribution to multimodal performance. It is shown that temporal variables tend to be more helpful than CXR images and clinical notes in the three explored predictive tasks.

Rethinking Human-AI Collaboration in Complex Medical Decision Making: A Case Study in Sepsis Diagnosis.

Today's AI systems for medical decision support often succeed on benchmark datasets in research papers but fail in real-world deployment. This work focuses on the decision making of sepsis, an acute life-threatening systematic infection that requires an early diagnosis with high uncertainty from the clinician. Our aim is to explore the design requirements for AI systems that can support clinical experts in making better decisions for the early diagnosis of sepsis. The study begins with a formative study investigating why clinical experts abandon an existing AI-powered Sepsis predictive module in their electrical health record (EHR) system. We argue that a human-centered AI system needs to support human experts in the intermediate stages of a medical decision-making process (e.g., generating hypotheses or gathering data), instead of focusing only on the final decision. Therefore, we build SepsisLab based on a state-of-the-art AI algorithm and extend it to predict the future projection of sepsis development, visualize the prediction uncertainty, and propose actionable suggestions (i.e., which additional laboratory tests can be collected) to reduce such uncertainty. Through heuristic evaluation with six clinicians using our prototype system, we demonstrate that SepsisLab enables a promising human-AI collaboration paradigm for the future of AI-assisted sepsis diagnosis and other high-stakes medical decision making.

[Effects of total flavones of Chrysanthemum indicum on proliferation and apoptosis of human osteosarcoma Saos-2 cells].

OBJECTIVE: To study the effects of total flavones of Chrysanthemum indicum on proliferation and apoptosis of human osteosarcoma Saos-2 cells and its mechanism. METHODS: The effect of the total flavones of Chrysanthemum indicum on the proliferation of human osteosarcoma Saos-2 cells was detected by CCK assay, and the morphological changes of cells treated with total flavones of Chrysanthemum indicum were observed using contrast microscope. Flow cytomerty was performed to analyze the apoptotic rate of the cells, and the gene expression levels of Caspase-3, BCL-2, BAX were detected by RT-PCR. RESULTS: The total flavones of Chrysanthemum indicum suppressed the proliferation of osteosarcoma cells in a dose-and time-dependent manner. Under a microscope observation of cell morphology, the volume became smaller ,the number of internal particles was increased. Cell apoptosis rate was positively related to the drug concentration. After treated for 48 hours, Caspase-3 and BAX expression were up-regulated, BCL-2 and BCL-2/BAX were decreased. CONCLUSION: The total flavones of Chrysanthemum indicum can inhibit the proliferation of osteosarcoma cell line Saos-2 by inducing cell apoptosis,the mechanism of which might be related with reducing BCL-2/BAX and activating Caspase-3.

Multimodal Risk Prediction with Physiological Signals, Medical Images and Clinical Notes.

The broad adoption of electronic health records (EHRs) provides great opportunities to conduct healthcare research and solve various clinical problems in medicine. With recent advances and success, methods based on machine learning and deep learning have become increasingly popular in medical informatics. Combining data from multiple modalities may help in predictive tasks. To assess the expectations of multimodal data, we introduce a comprehensive fusion framework designed to integrate temporal variables, medical images, and clinical notes in Electronic Health Record (EHR) for enhanced performance in downstream predictive tasks. Early, joint, and late fusion strategies were employed to effectively combine data from various modalities. Model performance and contribution scores show that multimodal models outperform uni-modal models in various tasks. Additionally, temporal signs contain more information than CXR images and clinical notes in three explored predictive tasks. Therefore, models integrating different data modalities can work better in predictive tasks.

Stable clinical risk prediction against distribution shift in electronic health records.

The availability of large-scale electronic health record datasets has led to the development of artificial intelligence (AI) methods for clinical risk prediction that help improve patient care. However, existing studies have shown that AI models suffer from severe performance decay after several years of deployment, which might be caused by various temporal dataset shifts. When the shift occurs, we have access to large-scale pre-shift data and small-scale post-shift data that are not enough to train new models in the post-shift environment. In this study, we propose a new method to address the issue. We reweight patients from the pre-shift environment to mitigate the distribution shift between pre- and post-shift environments. Moreover, we adopt a Kullback-Leibler divergence loss to force the models to learn similar patient representations in pre- and post-shift environments. Our experimental results show that our model efficiently mitigates temporal shifts, improving prediction performance.

Deconfounding Actor-Critic Network with Policy Adaptation for Dynamic Treatment Regimes.

Despite intense efforts in basic and clinical research, an individualized ventilation strategy for critically ill patients remains a major challenge. Recently, dynamic treatment regime (DTR) with reinforcement learning (RL) on electronic health records (EHR) has attracted interest from both the healthcare industry and machine learning research community. However, most learned DTR policies might be biased due to the existence of confounders. Although some treatment actions non-survivors received may be helpful, if confounders cause the mortality, the training of RL models guided by long-term outcomes (e.g., 90-day mortality) would punish those treatment actions causing the learned DTR policies to be suboptimal. In this study, we develop a new deconfounding actor-critic network (DAC) to learn optimal DTR policies for patients. To alleviate confounding issues, we incorporate a patient resampling module and a confounding balance module into our actor-critic framework. To avoid punishing the effective treatment actions non-survivors received, we design a short-term reward to capture patients' immediate health state changes. Combining short-term with long-term rewards could further improve the model performance. Moreover, we introduce a policy adaptation method to successfully transfer the learned model to new-source small-scale datasets. The experimental results on one semi-synthetic and two different real-world datasets show the proposed model outperforms the state-of-the-art models. The proposed model provides individualized treatment decisions for mechanical ventilation that could improve patient outcomes.

Predicting Age-Related Macular Degeneration Progression with Contrastive Attention and Time-Aware LSTM.

Age-related macular degeneration (AMD) is the leading cause of irreversible blindness in developed countries. Identifying patients at high risk of progression to late AMD, the sight-threatening stage, is critical for clinical actions, including medical interventions and timely monitoring. Recently, deep-learning-based models have been developed and achieved superior performance for late AMD prediction. However, most existing methods are limited to the color fundus photography (CFP) from the last ophthalmic visit and do not include the longitudinal CFP history and AMD progression during the previous years' visits. Patients in different AMD subphenotypes might have various speeds of progression in different stages of AMD disease. Capturing the progression information during the previous years' visits might be useful for the prediction of AMD progression. In this work, we propose a Contrastive-Attention-based Time-aware Long Short-Term Memory network (CAT-LSTM) to predict AMD progression. First, we adopt a convolutional neural network (CNN) model with a contrastive attention module (CA) to extract abnormal features from CFPs. Then we utilize a time-aware LSTM (T-LSTM) to model the patients' history and consider the AMD progression information. The combination of disease progression, genotype information, demographics, and CFP features are sent to T-LSTM. Moreover, we leverage an auto-encoder to represent temporal CFP sequences as fixed-size vectors and adopt k-means to cluster them into subphenotypes. We evaluate the proposed model based on real-world datasets, and the results show that the proposed model could achieve 0.925 on area under the receiver operating characteristic (AUROC) for 5-year late-AMD prediction and outperforms the state-of-the-art methods by more than 3%, which demonstrates the effectiveness of the proposed CAT-LSTM. After analyzing patient representation learned by an auto-encoder, we identify 3 novel subphenotypes of AMD patients with different characteristics and progression rates to late AMD, paving the way for improved personalization of AMD management. The code of CAT-LSTM can be found at GitHub.

Brain Atlas Guided Attention U-Net for White Matter Hyperintensity Segmentation.

White Matter Hyperintensities (WMH) are the most common manifestation of cerebral small vessel disease (cSVD) on the brain MRI. Accurate WMH segmentation algorithms are important to determine cSVD burden and its clinical con-sequences. Most of existing WMH segmentation algorithms require both fluid attenuated inversion recovery (FLAIR) images and T1-weighted images as inputs. However, T1-weighted images are typically not part of standard clinical scans which are acquired for patients with acute stroke. In this paper, we propose a novel brain atlas guided attention U-Net (BAGAU-Net) that leverages only FLAIR images with a spatially-registered white matter (WM) brain atlas to yield competitive WMH segmentation performance. Specifically, we designed a dual-path segmentation model with two novel connecting mechanisms, namely multi-input attention module (MAM) and attention fusion module (AFM) to fuse the information from two paths for accurate results. Experiments on two publicly available datasets show the effectiveness of the proposed BAGAU-Net. With only FLAIR images and WM brain atlas, BAGAU-Net outperforms the state-of-the-art method with T1-weighted images, paving the way for effective development of WMH segmentation. Availability: https://github.com/Ericzhang1/BAGAU-Net.

A survival model generalized to regression learning algorithms.

Survival prediction is an important problem that is encountered widely in industry and medicine. Despite the explosion of artificial intelligence technologies, no uniformed method allows the application of any type of regression learning algorithm to a survival prediction problem. Here, we present a statistical modeling method that is generalized to all types of regression learning algorithm, including deep learning. We present its empirical advantage when it is applied to traditional survival problems. We demonstrate its expanded applications in different types of regression learning algorithm, such as gradient boosted trees, convolutional neural networks and recurrent neural networks. Additionally, we demonstrate its application in clinical informatic data, pathological images and the hardware industry. We expect that this algorithm will be widely applicable for diverse types of survival data, including discrete data types and those suitable for deep learning such as those with time or spatial continuity.

An interpretable deep-learning model for early prediction of sepsis in the emergency department.

Sepsis is a life-threatening condition with high mortality rates and expensive treatment costs. Early prediction of sepsis improves survival in septic patients. In this paper, we report our top-performing method in the 2019 DII National Data Science Challenge to predict onset of sepsis 4 h before its diagnosis on electronic health records of over 100,000 unique patients in emergency departments. A long short-term memory (LSTM)-based model with event embedding and time encoding is leveraged to model clinical time series and boost prediction performance. Attention mechanism and global max pooling techniques are utilized to enable interpretation for the deep-learning model. Our model achieved an average area under the curve of 0.892 and was selected as one of the winners of the challenge for both prediction accuracy and clinical interpretability. This study paves the way for future intelligent clinical decision support, helping to deliver early, life-saving care to the bedside of septic patients.

LncRNA Malat-1 From MSCs-Derived Extracellular Vesicles Suppresses Inflammation and Cartilage Degradation in Osteoarthritis.

Purpose: Extracellular Vesicles (EVs) derived from hMSCs, have the potential to alleviate cartilage damage and inflammation. We aimed to explore the effects of EVs derived from lncRNA malat-1-overexpressing human mesenchymal stem cells (hMSCs) on chondrocytes. Material and Methods: hMSCs-derived Extracellular Vesicles (hMSCs-EVs) were identified by transmission electron microscopy and western blot. We used a Sprague-Dawley (SD) rat model of CollagenaseⅡ-induced osteoarthritis (OA) as well as IL-1ß-induced OA chondrocytes. Lentiviral vectors were used to overexpress lncRNA malat-1 in hMSCs. Chondrocyte proliferation, inflammation, extracellular matrix degradation, and cell migration were measured by Edu staining, ELISA, western blot analysis, and transwell assay. Chondrocyte apoptosis was evaluated by flow cytometry, Hoechst 33342/PI Staining, and western blot. Safranine O-fast green (S-O) staining and HE staining were used to assess morphologic alterations of the rat knee joint. Results: hMSCsmalat-1-EVs decreased MMP-13, IL-6, and Caspase-3 expression in IL-1ß-induced OA chondrocytes. Moreover, hMSCsmalat-1-EVs promoted chondrocyte proliferation and migration, suppressed apoptosis, and attenuated IL-1ß-induced chondrocyte injury. Our animal experiments suggested that hMSCsmalat-1-EVs were sufficient to prevent cartilage degeneration. Conclusion: Our findings show that lncRNA malat-1from hMSCs-delivered EVs can promote chondrocyte proliferation, alleviate chondrocyte inflammation and cartilage degeneration, and enhance chondrocyte repair. Overall, hMSCsmalat-1-EVs might be a new potential therapeutic option for patients with OA.