Thermodynamic Analysis of Eplerenone in 13 Pure Solvents at Temperatures from 283.15 to 323.15 K.

The solubility of eplerenone (EP) in 13 pure solvents (acetonitrile, N,N-dimethylformamide (DMF), acetone, 2-butanone, 4-methyl-2-pentanone, ethyl formate, methyl acetate, ethyl acetate, propyl acetate, butyl acetate, methyl propionate, ethyl propionate, ethanol, and 1-propanol) was determined by the gravimetric method at atmospheric pressure and various temperatures (from 283.15 to 323.15 K). The results showed that the solubility of EP in the selected solvents was positively correlated with the thermodynamic temperature, and the order of solubility of EP at 298.15 K was acetonitrile > DMF > 2-butanone > methyl acetate > 4-methyl-2-pentanone > methyl propionate > ethyl acetate > propyl acetate > ethyl formate > acetone > butyl acetate > ethanol >1-propanol. The modified Apelblat model, van't Hoff model, λh model, and polynomial empirical model were used for fitting the solubility data, and then the λh model was found to have the highest fitting accuracy with a minimum ARD of 7.0 × 10-3 and a minimum RMSD of 6.1 × 10-6. The solvent effect between the solute and the solvent was analyzed using linear solvation energy relationship (LSER), and the enthalpy of solvation (ΔsolH°), entropy of solvation (ΔsolS°), and Gibbs free energy of solvation (ΔsolG°) of the dissolution process of EP were calculated by the van't Hoff model, which indicated that the dissolution process of EP in the selected solvents was endothermic, nonspontaneous, and entropy-increasing. In this work, the solubility, dissolution characteristics, and thermodynamic parameters of EP were studied, which will provide data support for the production, crystallization, and purification of EP and will provide important guidance for the crystallization optimization of EP in industry.

Structure-activity relationship study of anti-wear additives in rapeseed oil based on machine learning and logistic regression.

Anti-wear performance is a crucial quality of lubricants, and it is important to conduct research into the structure-activity relationship of anti-wear additives in bio-based lubricants. These lubricants are eco-friendly and energy-efficient. A literature review resulted in the construction of a dataset comprising 779 anti-wear properties of 79 anti-wear additives in rapeseed oil, at various loadings and additive levels. The anti-wear additives were classified into six groups, including phosphoric acid, formate esters, borate esters, thiazoles, triazine derivatives, and thiophene. Logistic regression analysis revealed that the quantity and kind of anti-wear agents had significant effects on the anti-wear properties of rapeseed oil, with phosphoric acid being the most effective and thiophene being the least effective. To identify the specific structural data that affect the anti-wear capabilities of additives in bio-based lubricants of rapeseed oil, a random forest classification model was developed. The results showed a 0.964 accuracy (ACC) and a 0.931 Matthews Correlation Coefficient (MCC) on the test set. The ranking of importance and characterization of MACCS descriptors in the model confirms that anti-wear additives with chemical structures containing P, O, N, S and heterocyclic groups, along with more than two methyl groups, improve the anti-wear performance of rapeseed oil. The application of data analysis and machine learning to investigate the classifications and structural characteristics of anti-wear additives in rapeseed oil provides data references and guiding principles for designing anti-wear additives in bio-based lubricants.

IDPpub: Illuminating the Dark Phosphoproteome Through PubMed Mining.

Global phosphoproteomics experiments quantify tens of thousands of phosphorylation sites. However, data interpretation is hampered by our limited knowledge on functions, biological contexts, or precipitating enzymes of the phosphosites. This study establishes a repository of phosphosites with associated evidence in biomedical abstracts, using deep learning-based natural language processing techniques. Our model for illuminating the dark phosphoproteome through PubMed mining (IDPpub) was generated by fine-tuning BioBERT, a deep learning tool for biomedical text mining. Trained using sentences containing protein substrates and phosphorylation site positions from 3000 abstracts, the IDPpub model was then used to extract phosphorylation sites from all MEDLINE abstracts. The extracted proteins were normalized to gene symbols using the National Center for Biotechnology Information gene query, and sites were mapped to human UniProt sequences using ProtMapper and mouse UniProt sequences by direct match. Precision and recall were calculated using 150 curated abstracts, and utility was assessed by analyzing the CPTAC (Clinical Proteomics Tumor Analysis Consortium) pan-cancer phosphoproteomics datasets and the PhosphoSitePlus database. Using 10-fold cross validation, pairs of correct substrates and phosphosite positions were extracted with an average precision of 0.93 and recall of 0.94. After entity normalization and site mapping to human reference sequences, an independent validation achieved a precision of 0.91 and recall of 0.77. The IDPpub repository contains 18,458 unique human phosphorylation sites with evidence sentences from 58,227 abstracts and 5918 mouse sites in 14,610 abstracts. This included evidence sentences for 1803 sites identified in CPTAC studies that are not covered by manually curated functional information in PhosphoSitePlus. Evaluation results demonstrate the potential of IDPpub as an effective biomedical text mining tool for collecting phosphosites. Moreover, the repository (http://idppub.ptmax.org), which can be automatically updated, can serve as a powerful complement to existing resources.

Fostering temporal crop diversification to reduce pesticide use.

Temporal crop diversification could reduce pesticide use by increasing the proportion of crops with low pesticide use (dilution effects) or enhancing the regulation of pests, weeds and diseases (regulation effects). Here, we use the French National DEPHY Network to compare pesticide use between 16 main crops (dilution effect) and to assess whether temporal crop taxonomic and functional diversification, as implemented in commercial farms specialized in arable field crops, could explain variability in total pesticide use within 16 main crops (regulation effect). The analyses are based on 14,556 crop observations belonging to 1334 contrasted cropping systems spanning the diversity of French climatic regions. We find that cropping systems with high temporal crop diversity generally include crops with low pesticide use. For several crops, total pesticide use is reduced under higher temporal crop functional diversity, temporal crop taxonomic diversity, or both. Higher cover crop frequency increases total pesticide use through an increase in herbicide use. Further studies are required to identify crop sequences that maximize regulation and dilution effects while achieving other facets of cropping system multiperformance.

Identifying underlying patterns in Alzheimer's disease trajectory: a deep learning approach and Mendelian randomization analysis.

Background: Alzheimer's disease (AD) is a heterogeneously progressive neurodegeneration disorder with varied rates of deterioration, either between subjects or within different stages of a certain subject. Estimating the course of AD at early stages has treatment implications. We aimed to analyze disease progression to identify distinct patterns in AD trajectory. Methods: We proposed a deep learning model to identify underlying patterns in the trajectory from cognitively normal (CN) to a state of mild cognitive impairment (MCI) to AD dementia, by jointly predicting time-to-conversion and clustering out distinct subgroups characterized by comprehensive features as well as varied progression rates. We designed and validated our model on the ADNI dataset (1370 participants). Prediction of time-to-conversion in AD trajectory was used to validate the expression of the identified patterns. Causality between patterns and time-to-conversion was further inferred using Mendelian randomization (MR) analysis. External validation was performed on the AIBL dataset (233 participants). Findings: The proposed model clustered out patterns characterized by significantly different biomarkers and varied progression rates. The discovered patterns also showed a strong prediction ability, as indicated by hazard ratio (CN→MCI, HR = 3.51, p < 0.001; MCI→AD, HR = 8.11, p < 0.001), C-Index (CN→MCI, 0.618; MCI→AD, 0.718), and AUC (CN→MCI, 3 years 0.802, 5 years 0.876; MCI→AD, 3 years 0.914, 5 years 0.957). In the external validation cohort, our model demonstrated competitive performance on conversion time prediction (CN→MCI, C-Index = 0.693; MCI→AD, C-Index = 0.752). Moreover, suggestive associations between CN→MCI/MCI→AD patterns with four/three SNPs were mediated and MR analysis indicated a causal link between MCI→AD patterns and time-to-conversion in the first three years. Interpretation: Our proposed model identifies biologically and clinically meaningful patterns from real-world data and provides promising performance on time-to-conversion prediction in AD trajectory, which could promote the understanding of disease progression, facilitate clinical trial design, and provide potential for decision-making. Funding: The National Key Research and Development Program of China, the Key R&D Program of Zhejiang, and the National Nature Science Foundation of China.

Assisting schizophrenia diagnosis using clinical electroencephalography and interpretable graph neural networks: a real-world and cross-site study.

Schizophrenia (SCZ) is a chronic and serious mental disorder with a high mortality rate. At present, there is a lack of objective, cost-effective and widely disseminated diagnosis tools to address this mental health crisis globally. Clinical electroencephalogram (EEG) is a noninvasive technique to measure brain activity with high temporal resolution, and accumulating evidence demonstrates that clinical EEG is capable of capturing abnormal SCZ neuropathology. Although EEG-based automated diagnostic tools have obtained impressive performance on individual datasets, the transportability of potential EEG biomarkers in cross-site real-world application is still an open question. To address the challenges of small sample sizes and population heterogeneity, we develop an advanced interpretable deep learning model using multimodal clinical EEG features and demographic information as inputs to graph neural networks, and further propose different transfer learning strategies to adapt to different clinical scenarios. Taking the disease discrimination of health control (HC) and SCZ with 1030 participants as a use case, our model is trained on a small clinical dataset (N = 188, Chinese) and enhanced using a large-scale public dataset (N = 508, American) of adult participants. Cross-site validation from an independent dataset of adult participants (N = 157, Chinese) produced stable performance, with AUCs of 0.793-0.852 and accuracies of 0.786-0.858 for different SCZ prevalence, respectively. In addition, cross-site validation from another dataset of adolescent boys (N = 84, Russian) yielded an AUC of 0.702 and an accuracy of 0.690. Moreover, feature visualization further revealed that the ranking of feature importance varied significantly among different datasets, and that EEG theta and alpha band power appeared to be the most significant and translational biomarkers of SCZ pathology. Overall, our promising results demonstrate the feasibility of SCZ discrimination using EEG biomarkers in multiple clinical settings.

Randomized Trial of Modified Chest Tube Placement vs Routine Placement After Lung Resection.

BACKGROUND: Chest tube placement after pulmonary resection is usually considered a mandatory procedure. However, peritubular leakage of pleural fluid and intrathoracic air is frequent after surgery. Therefore, we separated the chest tube from the intercostal space as a modified placement strategy. METHODS: Patients undergoing robotic and video-assisted lung resection were enrolled in this study at our medical center between February 2021 and August 2021. All patients were randomly divided into either the modified group (n = 98) or the routine group (n = 101). The incidence of peritubular leakage of pleural fluid and peritubular air leaking or entering after surgery were the primary end points of the study. RESULTS: A total of 199 patients were randomized. Patients in the modified group had lower incidence of peritubular leakage of pleural fluid (after surgery, 39.6% vs 18.4% [P = .001]; after chest tube removal, 26.7% vs 11.2% [P = .005]), lower incidence of peritubular air leaking or entering (14.9% vs 5.1% [P = .022]), and fewer dressing changes (5.02 ± 2.30 vs 3.48 ± 0.94 [P < .001]). In patients undergoing lobectomy and segmentectomy, the type of chest tube placement was associated with the severity of peritubular pleural fluid leakage (P < .05). CONCLUSIONS: The modified chest tube placement was safe and had better clinical efficacy than the routine type. The reduction of postoperative peritubular leakage of pleural fluid resulted in better wound recovery. This modified strategy should be popularized, especially in patients undergoing pulmonary lobectomy or segmentectomy.

Comparative Effectiveness of Digital Cognitive Behavioral Therapy vs Medication Therapy Among Patients With Insomnia.

Importance: Although digital cognitive behavioral therapy for insomnia (dCBT-I) has been studied in many randomized clinical trials and is recommended as a first-line treatment option, few studies have systematically examined its effectiveness, engagement, durability, and adaptability in clinical settings. Objective: To evaluate the clinical effectiveness, engagement, durability, and adaptability of dCBT-I. Design, Setting, and Participants: This retrospective cohort study was conducted using longitudinal data collected via a mobile app named Good Sleep 365 between November 14, 2018, and February 28, 2022. Three therapeutic modes (ie, dCBT-I, medication, and their combination) were compared at month 1, month 3, and month 6 (primary). Inverse probability of treatment weighting (IPTW) using propensity scores was applied to enable homogeneous comparisons between the 3 groups. Exposures: Treatment with dCBT-I, medication therapy, or combination therapy according to prescriptions. Main Outcomes and Measures: The Pittsburgh Sleep Quality Index (PSQI) score and its essential subitems were used as the primary outcomes. Effectiveness on comorbid somnolence, anxiety, depression, and somatic symptoms were used as secondary outcomes. Cohen d effect size, P value, and standardized mean difference (SMD) were used to measure differences in treatment outcomes. Changes in outcomes and response rates (≥3 points change in PSQI score) were also reported. Results: A total of 4052 patients (mean [SD] age, 44.29 [12.01] years; 3028 [74.7%] female participants) were selected for dCBT-I (n = 418), medication (n = 862), and their combination (n = 2772). Compared with the change in PSQI score at 6 months for participants receiving medication alone (from a mean [SD] of 12.85 [3.49] to 8.92 [4.03]), both dCBT-I (from a mean [SD] of 13.51 [3.03] to 7.15 [3.25]; Cohen d, -0.50; 95% CI, -0.62 to -0.38; P < .001; SMD = 0.484) and combination therapy (from a mean [SD] of 12.92 [3.49] to 6.98 [3.43]; Cohen d, 0.50; 95% CI, 0.42 to 0.58; P < .001; SMD = 0.518) were associated with significant reductions; dCBT-I had a comparable effect as combination therapy (Cohen d, 0.05; 95% CI, -0.05 to 0.15; P = .66; SMD = 0.05), but showed unstable durability. Outcomes of dCBT-I improved steadily and rapidly during the first 3 months, and then fluctuated. The response rates with dCBT-I and combination therapy were higher than with medication. Changes in secondary outcomes indicated statistically significant benefits from dCBT-I and combination therapy. The results of subgroup analysis were consistent with the main findings, demonstrating the superiority of dCBT-I vs medication therapy in various subpopulations. Conclusions and Relevance: In this study, clinical evidence suggested that combination therapy was optimal, and dCBT-I was more effective than medication therapy, with long-term benefits for insomnia. Future studies are needed to analyze its clinical effectiveness and reliability in distinct subpopulations.

Factors Affecting the Breastfeeding Duration of Infants and Young Children in China: A Cross-Sectional Study.

OBJECTIVE: To investigate the factors affecting the duration of continuous breastfeeding of infants within 2 years of age, and to explore intervention strategies that may promote breastfeeding duration in China. METHOD: A self-made electronic questionnaire was used to investigate the breastfeeding duration of infants, and the influencing factors were collected from three levels of individual, family, and social support. The Kruskal-Wallis rank sum test and the multivariable ordinal logistic regression model were used for data analysis. Subgroup analysis was carried out according to region and parity. RESULTS: A total of 1001 valid samples from 26 provinces across the country were obtained. Among them, 9.9% breastfed for less than 6 months, 38.6% for 6 to 12 months, 31.8% for 12 to 18 months, 6.7% for 18 to 24 months, and 13.1% for more than 24 months. Barriers to sustained breastfeeding included the mother's age at birth being over 31, education level below junior high, cesarean delivery, and the baby's first nipple sucking at 2 to 24 h after birth. Factors that promote continued breastfeeding included freelancer or full-time mother, high breastfeeding knowledge score, supporting breastfeeding, baby with low birth weight, first bottle feeding at 4 months and later, first supplementary food at over 6 months old, high family income, the mother's family and friends supporting breastfeeding, breastfeeding support conditions after returning to work, etc. Conclusion: The breastfeeding duration in China is generally short, and the proportion of mothers breastfeeding until the age of 2 years and above, recommended by WHO, is very low. Multiple factors at the individual, family, and social support levels influence the duration of breastfeeding. It is suggested to improve the current situation by strengthening health education, improving system security, and enhancing social support.

Optimizing multi-domain hematologic biomarkers and clinical features for the differential diagnosis of unipolar depression and bipolar depression.

There is a lack of objective features for the differential diagnosis of unipolar and bipolar depression, especially those that are readily available in practical settings. We investigated whether clinical features of disease course, biomarkers from complete blood count, and blood biochemical markers could accurately classify unipolar and bipolar depression using machine learning methods. This retrospective study included 1160 eligible patients (918 with unipolar depression and 242 with bipolar depression). Patient data were randomly split into training (85%) and open test (15%) sets 1000 times, and the average performance was reported. XGBoost achieved the optimal open-test performance using selected biomarkers and clinical features-AUC 0.889, sensitivity 0.831, specificity 0.839, and accuracy 0.863. The importance of features for differential diagnosis was measured using SHapley Additive exPlanations (SHAP) values. The most informative features include (1) clinical features of disease duration and age of onset, (2) biochemical markers of albumin, low density lipoprotein (LDL), and potassium, and (3) complete blood count-derived biomarkers of white blood cell count (WBC), platelet-to-lymphocyte ratio (PLR), and monocytes (MONO). Overall, onset features and hematologic biomarkers appear to be reliable information that can be readily obtained in clinical settings to facilitate the differential diagnosis of unipolar and bipolar depression.

Characterization of titanium dioxide nanoparticles in confectionary products and estimation of dietary exposure level among the Chinese population.

Titanium dioxide (TiO2) is widely used in the food industry. Recently, European Commission has banned TiO2 as a food additive, raising public concern about its health risk, especially the nanoparticles (NPs) contained therein. This study aimed to reveal the existence of TiO2 NPs in food and further estimate the dietary exposure level among Chinese population by characterizing particle size distribution, determining Ti content and micro-distribution in food products, and calculating food consumption from the China Health and Nutrition Survey (CHNS). The results showed that TiO2 particle size in food additives and chewing gums was 53.5-230.3 nm and 56.8-267.7 nm respectively, where NPs accounted for 34.7% and 55.6% respectively. TiO2 was firstly in situ presented on the surface of confectionary products with hard shells. The content of TiO2 ranged from 3.2 to 3409.3 µg/g product. Besides, the mean dietary intake was 71.31 µg/kgbw/day for TiO2 and 7.75 µg/kgbw/day for TiO2 NPs among Chinese population, affected by people's dietary habits of different regions. Children's exposure levels was the highest due to their love of sweets. More attention should be paid to risk assessment and management of TiO2 NPs for children in China.

Disentangled representation for sequential treatment effect estimation.

BACKGROUND AND OBJECTIVE: Treatment effect estimation, as a fundamental problem in causal inference, focuses on estimating the outcome difference between different treatments. However, in clinical observational data, some patient covariates (such as gender, age) not only affect the outcomes but also affect the treatment assignment. Such covariates, named as confounders, produce distribution discrepancies between different treatment groups, thereby introducing the selection bias for the estimation of treatment effects. The situation is even more complicated in longitudinal data, because the confounders are time-varying that are subject to patient history and meanwhile affect the future outcomes and treatment assignments. Existing methods mainly work on cross-sectional data obtained at a specific time point, but cannot process the time-varying confounders hidden in the longitudinal data. METHODS: In this study, we address this problem for the first time by disentangled representation learning, which considers the observational data as consisting of three components, including outcome-specific factors, treatment-specific factors, and time-varying confounders. Based on this, the proposed approach adopts a recurrent neural network-based framework to process sequential information and learn the disentangled representations of the components from longitudinal observational sequences, captures the posterior distributions of latent factors by multi-task learning strategy. Moreover, mutual information-based regularization is adopted to eliminate the time-varying confounders. In this way, the association between patient history and treatment assignment is removed and the estimation can be effectively conducted. RESULTS: We evaluate our model in a realistic set-up using a model of tumor growth. The proposed model achieves the best performance over benchmark models for both one-step ahead prediction (0.70% vs 0.74% for the-state-of-the-art model, when γ = 3. Measured by normalized root mean square error, the lower the better) and five-step ahead prediction (1.47% vs 1.83%) in most cases. By increasing the effect of confounders, our proposed model always shows superiority against the state-of-the-art model. In addition, we adopted T-SNE to visualize the disentangled representations and present the effectiveness of disentanglement explicitly and intuitively. CONCLUSIONS: The experimental results indicate the powerful capacity of our model in learning disentangled representations from longitudinal observational data and dealing with the time-varying confounders, and demonstrate the surpassing performance achieved by our proposed model on dynamic treatment effect estimation.

Cross-Language Terminology Mapping Between ICD-10-CN and SNOMED-CT.

The objective of this study was to develop a hybrid method and perform an initial evaluation of mappings from the International Statistical Classification of Diseases, 10th revision, Chinese version (ICD-10-CN) to the Systematized Nomenclature of Medicine - Clinical Terms (SNOMED-CT). The methods used to perform mapping include reusing existing mappings, term similarity modeling for automatic mapping and manual review. We evaluated the results of automatic mapping and the coverage of the maps between two terminologies. Experimental results demonstrated that fine-tuning the pre-trained biomedical language model of PubmedBERT obtained the optimal performance, with a precision of 0.859, a recall of 0.773, and a F1 of 0.814. 100% 4-digit code ICD-10-CN terms were mapped to SNOMED-CT terms through exsit code mappings. Around 42.41% randomly selected 6-digit code ICD-10-CN terms had exact matches to corresponding SNOMED-CT terms, and we did not find appropriate SNOMED-CT terms for ICD grouping terms.

Novel Wearable Pyrothermoelectric Hybrid Generator for Solar Energy Harvesting.

Recently, wearable energy harvesting systems have been attracting great attention. As thermal energy is abundant in nature, developing wearable energy harvesters based on thermal energy conversion processes has been of particular interest. By integration of a high-efficient solar absorber, a pyroelectric film, and thermoelectric yarns, herein, we design a novel wearable solar-energy-driven pyrothermoelectric hybrid generator (PTEG). In contrast to those wearable pyroelectric generators and thermoelectric generators reported in previous works, our PTEG can enable effective energy harvesting from both dynamic temperature fluctuations and static temperature gradients. Under an illumination intensity of 1500 W/m2 (1.5 sun), the PTEG successfully charges two commercial capacitors to a sum voltage of 3.7 V in only 800 s, and the total energy is able to light up 73 LED light bulbs. The volumetric energy density over the two capacitors is calculated to be 67.8 µJ/cm3. The practical energy harvesting performance of the PTEG is further evaluated in the outdoor environment. The PTEG reported in this work not only demonstrates a rational structural design of high-efficient wearable energy harvesters but also paves a new pathway to integrate multiple energy conversion technologies for solar energy collection.

COVID-19 SignSym: a fast adaptation of a general clinical NLP tool to identify and normalize COVID-19 signs and symptoms to OMOP common data model.

The COVID-19 pandemic swept across the world rapidly, infecting millions of people. An efficient tool that can accurately recognize important clinical concepts of COVID-19 from free text in electronic health records (EHRs) will be valuable to accelerate COVID-19 clinical research. To this end, this study aims at adapting the existing CLAMP natural language processing tool to quickly build COVID-19 SignSym, which can extract COVID-19 signs/symptoms and their 8 attributes (body location, severity, temporal expression, subject, condition, uncertainty, negation, and course) from clinical text. The extracted information is also mapped to standard concepts in the Observational Medical Outcomes Partnership common data model. A hybrid approach of combining deep learning-based models, curated lexicons, and pattern-based rules was applied to quickly build the COVID-19 SignSym from CLAMP, with optimized performance. Our extensive evaluation using 3 external sites with clinical notes of COVID-19 patients, as well as the online medical dialogues of COVID-19, shows COVID-19 SignSym can achieve high performance across data sources. The workflow used for this study can be generalized to other use cases, where existing clinical natural language processing tools need to be customized for specific information needs within a short time. COVID-19 SignSym is freely accessible to the research community as a downloadable package (https://clamp.uth.edu/covid/nlp.php) and has been used by 16 healthcare organizations to support clinical research of COVID-19.

From Tokenization to Self-Supervision: Building a High-Performance Information Extraction System for Chemical Reactions in Patents.

Chemical reactions and experimental conditions are fundamental information for chemical research and pharmaceutical applications. However, the latest information of chemical reactions is usually embedded in the free text of patents. The rapidly accumulating chemical patents urge automatic tools based on natural language processing (NLP) techniques for efficient and accurate information extraction. This work describes the participation of the Melax Tech team in the CLEF 2020-ChEMU Task of Chemical Reaction Extraction from Patent. The task consisted of two subtasks: (1) named entity recognition to identify compounds and different semantic roles in the chemical reaction and (2) event extraction to identify event triggers of chemical reaction and their relations with the semantic roles recognized in subtask 1. To build an end-to-end system with high performance, multiple strategies tailored to chemical patents were applied and evaluated, ranging from optimizing the tokenization, pre-training patent language models based on self-supervision, to domain knowledge-based rules. Our hybrid approaches combining different strategies achieved state-of-the-art results in both subtasks, with the top-ranked F1 of 0.957 for entity recognition and the top-ranked F1 of 0.9536 for event extraction, indicating that the proposed approaches are promising.

COVID-19 SignSym: a fast adaptation of a general clinical NLP tool to identify and normalize COVID-19 signs and symptoms to OMOP common data model.

The COVID-19 pandemic swept across the world rapidly, infecting millions of people. An efficient tool that can accurately recognize important clinical concepts of COVID-19 from free text in electronic health records (EHRs) will be valuable to accelerate COVID-19 clinical research. To this end, this study aims at adapting the existing CLAMP natural language processing tool to quickly build COVID-19 SignSym, which can extract COVID-19 signs/symptoms and their 8 attributes (body location, severity, temporal expression, subject, condition, uncertainty, negation, and course) from clinical text. The extracted information is also mapped to standard concepts in the Observational Medical Outcomes Partnership common data model. A hybrid approach of combining deep learning-based models, curated lexicons, and pattern-based rules was applied to quickly build the COVID-19 SignSym from CLAMP, with optimized performance. Our extensive evaluation using 3 external sites with clinical notes of COVID-19 patients, as well as the online medical dialogues of COVID-19, shows COVID-19 SignSym can achieve high performance across data sources. The workflow used for this study can be generalized to other use cases, where existing clinical natural language processing tools need to be customized for specific information needs within a short time. COVID-19 SignSym is freely accessible to the research community as a downloadable package (https://clamp.uth.edu/covid/nlp.php) and has been used by 16 healthcare organizations to support clinical research of COVID-19.

Asthma Exacerbation Prediction and Risk Factor Analysis Based on a Time-Sensitive, Attentive Neural Network: Retrospective Cohort Study.

BACKGROUND: Asthma exacerbation is an acute or subacute episode of progressive worsening of asthma symptoms and can have a significant impact on patients' quality of life. However, efficient methods that can help identify personalized risk factors and make early predictions are lacking. OBJECTIVE: This study aims to use advanced deep learning models to better predict the risk of asthma exacerbations and to explore potential risk factors involved in progressive asthma. METHODS: We proposed a novel time-sensitive, attentive neural network to predict asthma exacerbation using clinical variables from large electronic health records. The clinical variables were collected from the Cerner Health Facts database between 1992 and 2015, including 31,433 adult patients with asthma. Interpretations on both patient and cohort levels were investigated based on the model parameters. RESULTS: The proposed model obtained an area under the curve value of 0.7003 through a five-fold cross-validation, which outperformed the baseline methods. The results also demonstrated that the addition of elapsed time embeddings considerably improved the prediction performance. Further analysis observed diverse distributions of contributing factors across patients as well as some possible cohort-level risk factors, which could be found supporting evidence from peer-reviewed literature such as respiratory diseases and esophageal reflux. CONCLUSIONS: The proposed neural network model performed better than previous methods for the prediction of asthma exacerbation. We believe that personalized risk scores and analyses of contributing factors can help clinicians better assess the individual's level of disease progression and afford the opportunity to adjust treatment, prevent exacerbation, and improve outcomes.

Recognizing software names in biomedical literature using machine learning.

Software tools now are essential to research and applications in the biomedical domain. However, existing software repositories are mainly built using manual curation, which is time-consuming and unscalable. This study took the initiative to manually annotate software names in 1,120 MEDLINE abstracts and titles and used this corpus to develop and evaluate machine learning-based named entity recognition systems for biomedical software. Specifically, two strategies were proposed for feature engineering: (1) domain knowledge features and (2) unsupervised word representation features of clustered and binarized word embeddings. Our best system achieved an F-measure of 91.79% for recognizing software from titles and an F-measure of 86.35% for recognizing software from both titles and abstracts using inexact matching criteria. We then created a biomedical software catalog with 19,557 entries using the developed system. This study demonstrates the feasibility of using natural language processing methods to automatically build a high-quality software index from biomedical literature.