Real-Time Forecasting of the COVID-19 Outbreak in Chinese Provinces: Machine Learning Approach Using Novel Digital Data and Estimates From Mechanistic Models.

BACKGROUND: The inherent difficulty of identifying and monitoring emerging outbreaks caused by novel pathogens can lead to their rapid spread; and if left unchecked, they may become major public health threats to the planet. The ongoing coronavirus disease (COVID-19) outbreak, which has infected over 2,300,000 individuals and caused over 150,000 deaths, is an example of one of these catastrophic events. OBJECTIVE: We present a timely and novel methodology that combines disease estimates from mechanistic models and digital traces, via interpretable machine learning methodologies, to reliably forecast COVID-19 activity in Chinese provinces in real time. METHODS: Our method uses the following as inputs: (a) official health reports, (b) COVID-19-related internet search activity, (c) news media activity, and (d) daily forecasts of COVID-19 activity from a metapopulation mechanistic model. Our machine learning methodology uses a clustering technique that enables the exploitation of geospatial synchronicities of COVID-19 activity across Chinese provinces and a data augmentation technique to deal with the small number of historical disease observations characteristic of emerging outbreaks. RESULTS: Our model is able to produce stable and accurate forecasts 2 days ahead of the current time and outperforms a collection of baseline models in 27 out of 32 Chinese provinces. CONCLUSIONS: Our methodology could be easily extended to other geographies currently affected by COVID-19 to aid decision makers with monitoring and possibly prevention.

Correction: Real-Time Forecasting of the COVID-19 Outbreak in Chinese Provinces: Machine Learning Approach Using Novel Digital Data and Estimates From Mechanistic Models.

[This corrects the article DOI: 10.2196/20285.].

Current situation and progress toward the 2030 health-related Sustainable Development Goals in China: A systematic analysis.

BACKGROUND: The Sustainable Development Goals (SDGs), adopted by all United Nations (UN) member states in 2015, established a set of bold and ambitious health-related targets to achieve by 2030. Understanding China's progress toward these targets is critical to improving population health for its 1.4 billion people. METHODS AND FINDINGS: We used estimates from the Global Burden of Disease (GBD) Study 2016, national surveys and surveillance data from China, and qualitative data. Twenty-eight of the 37 indicators included in the GBD Study 2016 were analyzed. We developed an attainment index of health-related SDGs, a scale of 0-100 based on the values of indicators. The projection model is adjusted based on the one developed by the GBD Study 2016 SDG collaborators. We found that China has achieved several health-related SDG targets, including decreasing neonatal and under-5 mortality rates and the maternal mortality ratios and reducing wasting and stunting for children. However, China may only achieve 12 out of the 28 health-related SDG targets by 2030. The number of target indicators achieved varies among provinces and municipalities. In 2016, among the seven measured health domains, China performed best in child nutrition and maternal and child health and reproductive health, with the attainment index scores of 93.0 and 91.8, respectively, followed by noncommunicable diseases (NCDs) (69.4), road injuries (63.6), infectious diseases (63.0), environmental health (62.9), and universal health coverage (UHC) (54.4). There are daunting challenges to achieve the targets for child overweight, infectious diseases, NCD risk factors, and environmental exposure factors. China will also have a formidable challenge in achieving UHC, particularly in ensuring access to essential healthcare for all and providing adequate financial protection. The attainment index of child nutrition is projected to drop to 80.5 by 2025 because of worsening child overweight. The index of NCD risk factors is projected to drop to 38.8 by 2025. Regional disparities are substantial, with eastern provinces generally performing better than central and western provinces. Sex disparities are clear, with men at higher risk of excess mortality than women. The primary limitations of this study are the limited data availability and quality for several indicators and the adoption of "business-as-usual" projection methods. CONCLUSION: The study found that China has made good progress in improving population health, but challenges lie ahead. China has substantially improved the health of children and women and will continue to make good progress, although geographic disparities remain a great challenge. Meanwhile, China faced challenges in NCDs, mental health, and some infectious diseases. Poor control of health risk factors and worsening environmental threats have posed difficulties in further health improvement. Meanwhile, an inefficient health system is a barrier to tackling these challenges among such a rapidly aging population. The eastern provinces are predicted to perform better than the central and western provinces, and women are predicted to be more likely than men to achieve these targets by 2030. In order to make good progress, China must take a series of concerted actions, including more investments in public goods and services for health and redressing the intracountry inequities.

Comparative Effectiveness of Second-line Antihyperglycemic Agents for Cardiovascular Outcomes: A Large-scale, Multinational, Federated Analysis of the LEGEND-T2DM Study.

Background: SGLT2 inhibitors (SGLT2is) and GLP-1 receptor agonists (GLP1-RAs) reduce major adverse cardiovascular events (MACE) in patients with type 2 diabetes mellitus (T2DM). However, their effectiveness relative to each other and other second-line antihyperglycemic agents is unknown, without any major ongoing head-to-head trials. Methods: Across the LEGEND-T2DM network, we included ten federated international data sources, spanning 1992-2021. We identified 1,492,855 patients with T2DM and established cardiovascular disease (CVD) on metformin monotherapy who initiated one of four second-line agents (SGLT2is, GLP1-RAs, dipeptidyl peptidase 4 inhibitor [DPP4is], sulfonylureas [SUs]). We used large-scale propensity score models to conduct an active comparator, target trial emulation for pairwise comparisons. After evaluating empirical equipoise and population generalizability, we fit on-treatment Cox proportional hazard models for 3-point MACE (myocardial infarction, stroke, death) and 4-point MACE (3-point MACE + heart failure hospitalization) risk, and combined hazard ratio (HR) estimates in a random-effects meta-analysis. Findings: Across cohorts, 16·4%, 8·3%, 27·7%, and 47·6% of individuals with T2DM initiated SGLT2is, GLP1-RAs, DPP4is, and SUs, respectively. Over 5·2 million patient-years of follow-up and 489 million patient-days of time at-risk, there were 25,982 3-point MACE and 41,447 4-point MACE events. SGLT2is and GLP1-RAs were associated with a lower risk for 3-point MACE compared with DPP4is (HR 0·89 [95% CI, 0·79-1·00] and 0·83 [0·70-0·98]), and SUs (HR 0·76 [0·65-0·89] and 0·71 [0·59-0·86]). DPP4is were associated with a lower 3-point MACE risk versus SUs (HR 0·87 [0·79-0·95]). The pattern was consistent for 4-point MACE for the comparisons above. There were no significant differences between SGLT2is and GLP1-RAs for 3-point or 4-point MACE (HR 1·06 [0·96-1·17] and 1·05 [0·97-1·13]). Interpretation: In patients with T2DM and established CVD, we found comparable cardiovascular risk reduction with SGLT2is and GLP1-RAs, with both agents more effective than DPP4is, which in turn were more effective than SUs. These findings suggest that the use of GLP1-RAs and SGLT2is should be prioritized as second-line agents in those with established CVD. Funding: National Institutes of Health, United States Department of Veterans Affairs.

Impact of social determinants of health on improving the LACE index for 30-day unplanned readmission prediction.

Objective: Early and accurate prediction of patients at risk of readmission is key to reducing costs and improving outcomes. LACE is a widely used score to predict 30-day readmissions. We examine whether adding social determinants of health (SDOH) to LACE can improve its predictive performance. Methods: This is a retrospective study that included all inpatient encounters in the state of Maryland in 2019. We constructed predictive models by fitting Logistic Regression (LR) on LACE and different sets of SDOH predictors. We used the area under the curve (AUC) to evaluate discrimination and SHapley Additive exPlanations values to assess feature importance. Results: Our study population included 316 558 patients of whom 35 431 (11.19%) patients were readmitted after 30 days. Readmitted patients had more challenges with individual-level SDOH and were more likely to reside in communities with poor SDOH conditions. Adding a combination of individual and community-level SDOH improved LACE performance from AUC = 0.698 (95% CI [0.695-0.7]; ref) to AUC = 0.708 (95% CI [0.705-0.71]; P < .001). The increase in AUC was highest in black patients (+1.6), patients aged 65 years or older (+1.4), and male patients (+1.4). Discussion: We demonstrated the value of SDOH in improving the LACE index. Further, the additional predictive value of SDOH on readmission risk varies by subpopulations. Vulnerable populations like black patients and the elderly are likely to benefit more from the inclusion of SDOH in readmission prediction. Conclusion: These findings provide potential SDOH factors that health systems and policymakers can target to reduce overall readmissions.

Classifying unstructured electronic consult messages to understand primary care physician specialty information needs.

OBJECTIVE: Electronic consultation (eConsult) content reflects important information about referring clinician needs across an organization, but is challenging to extract. The objective of this work was to develop machine learning models for classifying eConsult questions for question type and question content. Another objective of this work was to investigate the ability to solve this task with constrained expert time resources. MATERIALS AND METHODS: Our data source is the San Francisco Health Network eConsult system, with over 700 000 deidentified questions from the years 2008-2017, from gastroenterology, urology, and neurology specialties. We develop classifiers based on Bidirectional Encoder Representations from Transformers, experimenting with multitask learning to learn when information can be shared across classifiers. We produce learning curves to understand when we may be able to reduce the amount of human labeling required. RESULTS: Multitask learning shows benefits only in the neurology-urology pair where they shared substantial similarities in the distribution of question types. Continued pretraining of models in new domains is highly effective. In the neurology-urology pair, near-peak performance is achieved with only 10% of the urology training data given all of the neurology data. DISCUSSION: Sharing information across classifier types shows little benefit, whereas sharing classifier components across specialties can help if they are similar in the balance of procedural versus cognitive patient care. CONCLUSION: We can accurately classify eConsult content with enough labeled data, but only in special cases do methods for reducing labeling effort apply. Future work should explore new learning paradigms to further reduce labeling effort.

Assessing the Racial and Socioeconomic Disparities in Postpartum Depression Using Population-Level Hospital Discharge Data: Longitudinal Retrospective Study.

BACKGROUND: In the United States, >3.6 million deliveries occur annually. Among them, up to 20% (approximately 700,000) of women experience postpartum depression (PPD) according to the Centers for Disease Control and Prevention. Absence of accurate reporting and diagnosis has made phenotyping of patients with PPD difficult. Existing literature has shown that factors such as race, socioeconomic status, and history of substance abuse are associated with the differential risks of PPD. However, limited research has considered differential temporal associations with the outcome. OBJECTIVE: This study aimed to estimate the disparities in the risk of PPD and time to diagnosis for patients of different racial and socioeconomic backgrounds. METHODS: This is a longitudinal retrospective study using the statewide hospital discharge data from Maryland. We identified 160,066 individuals who had a hospital delivery from 2017 to 2019. We applied logistic regression and Cox regression to study the risk of PPD across racial and socioeconomic strata. Multinomial regression was used to estimate the risk of PPD at different postpartum stages. RESULTS: The cumulative incidence of PPD diagnosis was highest for White patients (8779/65,028, 13.5%) and lowest for Asian and Pacific Islander patients (248/10,760, 2.3%). Compared with White patients, PPD diagnosis was less likely to occur for Black patients (odds ratio [OR] 0.31, 95% CI 0.30-0.33), Asian or Pacific Islander patients (OR 0.17, 95% CI 0.15-0.19), and Hispanic patients (OR 0.21, 95% CI 0.19-0.22). Similar findings were observed from the Cox regression analysis. Multinomial regression showed that compared with White patients, Black patients (relative risk 2.12, 95% CI 1.73-2.60) and Asian and Pacific Islander patients (relative risk 2.48, 95% CI 1.46-4.21) were more likely to be diagnosed with PPD after 8 weeks of delivery. CONCLUSIONS: Compared with White patients, PPD diagnosis is less likely to occur in individuals of other races. We found disparate timing in PPD diagnosis across different racial groups and socioeconomic backgrounds. Our findings serve to enhance intervention strategies and policies for phenotyping patients at the highest risk of PPD and to highlight needs in data quality to support future work on racial disparities in PPD.

Incorporating Risk Factor Embeddings in Pre-trained Transformers Improves Sentiment Prediction in Psychiatric Discharge Summaries.

Reducing rates of early hospital readmission has been recognized and identified as a key to improve quality of care and reduce costs. There are a number of risk factors that have been hypothesized to be important for understanding re-admission risk, including such factors as problems with substance abuse, ability to maintain work, relations with family. In this work, we develop RoBERTa-based models to predict the sentiment of sentences describing readmission risk factors in discharge summaries of patients with psychosis. We improve substantially on previous results by a scheme that shares information across risk factors while also allowing the model to learn risk factor-specific information.

Classifying Electronic Consults for Triage Status and Question Type.

Electronic consult (eConsult) systems allow specialists more flexibility to respond to referrals more efficiently, thereby increasing access in under-resourced healthcare settings like safety net systems. Understanding the usage patterns of eConsult system is an important part of improving specialist efficiency. In this work, we develop and apply classifiers to a dataset of eConsult questions from primary care providers to specialists, classifying the messages for how they were triaged by the specialist office, and the underlying type of clinical question posed by the primary care provider. We show that pre-trained transformer models are strong baselines, with improving performance from domain-specific training and shared representations.

A machine learning methodology for real-time forecasting of the 2019-2020 COVID-19 outbreak using Internet searches, news alerts, and estimates from mechanistic models.

We present a timely and novel methodology that combines disease estimates from mechanistic models with digital traces, via interpretable machine-learning methodologies, to reliably forecast COVID-19 activity in Chinese provinces in real-time. Specifically, our method is able to produce stable and accurate forecasts 2 days ahead of current time, and uses as inputs (a) official health reports from Chinese Center Disease for Control and Prevention (China CDC), (b) COVID-19-related internet search activity from Baidu, (c) news media activity reported by Media Cloud, and (d) daily forecasts of COVID-19 activity from GLEAM, an agent-based mechanistic model. Our machine-learning methodology uses a clustering technique that enables the exploitation of geo-spatial synchronicities of COVID-19 activity across Chinese provinces, and a data augmentation technique to deal with the small number of historical disease activity observations, characteristic of emerging outbreaks. Our model's predictive power outperforms a collection of baseline models in 27 out of the 32 Chinese provinces, and could be easily extended to other geographies currently affected by the COVID-19 outbreak to help decision makers.

Molecular bases of unexpressed RHD alleles in Chinese D- persons.

BACKGROUND: The aim of this study was to use a systematic survey to analyze RHD alleles in Chinese D- donors who do not express D antigen or who lack functional RhD protein. STUDY DESIGN AND METHODS: A total of 733 D-Chinese donors, not including Del phenotypes, were investigated by RHD polymorphism­specific polymerase chain reaction (PCR), Rhesus box PCR-PstI digestion, and RHD sequencing. The frequencies of identified alleles were calculated. RESULTS: Three genetic mechanisms and eight alleles were found associated with the Chinese D- phenotype. One new RHD/CE hybrid allele and one novel mutation were also found. The rates of total deletion and the most frequent hybrid allele RHD(1)-CE(2-9)-D(10) were similar to those found in previous studies. A previously reported mutation RHD(711delC) was found to be the predominant cause of aberrant RHD alleles. CONCLUSION: Informative population-based data for improving molecular diagnostic strategies for Chinese D- persons are suggested by this study. This type of systematic knowledge is important for the development of typing and transfusion strategies for the Chinese population.

Rapid mussel-inspired synthesis of PDA-Zn-Ag nanofilms on TiO2 nanotubes for optimizing the antibacterial activity and biocompatibility by doping polydopamine with zinc at a higher temperature.

Mussel-inspired deposition of polydopamine (PDA) is a green chemical method that has been used to load silver nanoparticles on titanium oxide nanotubes (TiO2 NTs) to kill bacteria. However, a long reaction time is required for both the polymerization of dopamine and the reaction between PDA and silver nitrate. In addition, the deposition of silver nanoparticles is difficult to control, which may increase the risk of cytotoxicity. In this study, a rapid polymerization of dopamine was achieved by performing the reaction in a water bath at 90 °C (PDA-H). Furthermore, the reduction of Ag+ ions was markedly accelerated by the PDA-Zn film that was formed on the surface of TiO2 NTs from a solution of dopamine and zinc nitrate under the same heating conditions. The reaction between the PDA-Zn film and silver nitrate was dramatically reduced to 10 min, and the silver nanoparticles deposited on the PDA-Zn film were more uniform than those by PDA-H film. This PDA-Zn-Ag-TiO2 NTs material exhibited good antibacterial activity, as evidenced by the inhibition zone. The WST-1 assay indicated that the PDA-Zn-Ag film possessed a lower cell cytotoxicity and better biocompatibility than other Ag containing PDA films.

Synthesis of Surface-Enhanced Raman Scattering-Active Gold Nanoflowers by 5-Hydroxytryptophan in Acidic Solution.

We demonstrated a one-step synthesis of gold nanoflowers by 5-hydroxytryptophan (5-HTP) in acidic solutions at room temperature. The synthesized nanoflowers are 400 nm in dimension consisting of a solid core and many small petal-like nanoparticles (30-50 nm) in various directions. The shape, size and surface morphology of the gold nanostructure could be tuned by controlling the molar ratio of 5-HTP to HAuCl4 and HCl concentration. Examination of the nanoparticles at different reaction stages with transmission electron microscopy (TEM) reveals the shape evolutionary process of the nanoflowers to get a better understanding on their possible formation mechanism. Additionally, these gold nanoflowers exhibit a high SERS performance because of textured surface which is expected to provide many active sites.

Peptide derived from Pvfp-1 as bioadhesive on bio-inert surface.

Surface property is one important characteristic of materials, especially for ones that are bio-inert but designed for bio-medical application. In this study, we designed a series of peptides and compared their capacities as bioadhesive to improve the surface bioactivity of bio-inert material. The peptides were designed according to the sequence of Perna viridis foot protein 1 (Pvfp-1), one of the Mfp-1s (mussel foot protein 1) which play key roles in wet adhesion of mussel byssus. And the Teflon (PTFE) was chosen as a model of bio-inert material. With adsorption, adhesion and coating analysis, it was found that peptide C2 (M) (derived from the non-repeating region of Pvfp-1, contains modified DOPA) has superior coating and adhesion abilities especially on the bio-inert surface of PTFE. After coating with peptide C2 (M), the cell adhesion and spreading of osteoblast MC3T3-E1 cells on PTFE were significantly improved compared with those on non-coated surface, and the peptide-coating did not show any cell toxicity. Therefore, peptide C2 (M) is effective for improving the bioactivity of bio-inert PTFE, and could be potentially used as a bioadhesive on other bio-inert materials for biomedical application. Moreover, this study also provided new insights in designing other peptide-based bioadhesive materials.