Black Phosphorus Quantum Dot Loaded Bioinspired Nanoplatform Synergized with aPD-L1 for Multimode Cancer Immunotherapy.

Efforts to prolong the blood circulation time and bypass immune clearance play vital roles in improving the therapeutic efficacy of nanoparticles (NPs). Herein, a multifunctional nanoplatform (BPP@RTL) that precisely targets tumor cells is fabricated by encapsulating ultrasmall phototherapeutic agent black phosphorus quantum dot (BPQD), chemotherapeutic drug paclitaxel (PTX), and immunomodulator PolyMetformin (PM) in hybrid membrane-camouflaged liposomes. Specifically, the hybrid cell membrane coating derived from the fusion of cancer cell membrane and red blood cell membrane displays excellent tumor targeting efficiency and long blood circulation property due to the innate features of both membranes. After collaboration with aPD-L1-based immune checkpoint blockade therapy, a boosted immunotherapeutic effect is obtained due to elevated dendritic cell maturation and T cell activation. Significantly, laser-irradiated BPP@RTL combined with aPD-L1 effectively eliminates primary tumors and inhibits lung metastasis in 4T1 breast tumor model, offering a promising treatment plan to develop personalized antitumor strategy.

A hybrid system to understand the relations between assessments and plans in progress notes.

OBJECTIVE: The paper presents a novel solution to the 2022 National NLP Clinical Challenges (n2c2) Track 3, which aims to predict the relations between assessment and plan subsections in progress notes. METHODS: Our approach goes beyond standard transformer models and incorporates external information such as medical ontology and order information to comprehend the semantics of progress notes. We fine-tuned transformers to understand the textual data and incorporated medical ontology concepts and their relationships to enhance the model's accuracy. We also captured order information that regular transformers cannot by taking into account the position of the assessment and plan subsections in progress notes. RESULTS: Our submission earned third place in the challenge phase with a macro-F1 score of 0.811. After refining our pipeline further, we achieved a macro-F1 of 0.826, outperforming the top-performing system during the challenge phase. CONCLUSION: Our approach, which combines fine-tuned transformers, medical ontology, and order information, outperformed other systems in predicting the relationships between assessment and plan subsections in progress notes. This highlights the importance of incorporating external information beyond textual data in natural language processing (NLP) tasks related to medical documentation. Our work could potentially improve the efficiency and accuracy of progress note analysis.

Fair prediction of 2-year stroke risk in patients with atrial fibrillation.

OBJECTIVE: This study aims to develop machine learning models that provide both accurate and equitable predictions of 2-year stroke risk for patients with atrial fibrillation across diverse racial groups. MATERIALS AND METHODS: Our study utilized structured electronic health records (EHR) data from the All of Us Research Program. Machine learning models (LightGBM) were utilized to capture the relations between stroke risks and the predictors used by the widely recognized CHADS2 and CHA2DS2-VASc scores. We mitigated the racial disparity by creating a representative tuning set, customizing tuning criteria, and setting binary thresholds separately for subgroups. We constructed a hold-out test set that not only supports temporal validation but also includes a larger proportion of Black/African Americans for fairness validation. RESULTS: Compared to the original CHADS2 and CHA2DS2-VASc scores, significant improvements were achieved by modeling their predictors using machine learning models (Area Under the Receiver Operating Characteristic curve from near 0.70 to above 0.80). Furthermore, applying our disparity mitigation strategies can effectively enhance model fairness compared to the conventional cross-validation approach. DISCUSSION: Modeling CHADS2 and CHA2DS2-VASc risk factors with LightGBM and our disparity mitigation strategies achieved decent discriminative performance and excellent fairness performance. In addition, this approach can provide a complete interpretation of each predictor. These highlight its potential utility in clinical practice. CONCLUSIONS: Our research presents a practical example of addressing clinical challenges through the All of Us Research Program data. The disparity mitigation framework we proposed is adaptable across various models and data modalities, demonstrating broad potential in clinical informatics.

Enhancing Adhesion and Reducing Ohmic Contact through Nickel-Silicon Alloy Seed Layer in Electroplating Ni/Cu/Ag.

Due to the lower cost compared to screen-printed silver contacts, the Ni/Cu/Ag contacts formed by plating have been continuously studied as a potential metallization technology for solar cells. To address the adhesion issue of backside grid lines in electroplated n-Tunnel Oxide Passivating Contacts (n-TOPCon) solar cells and reduce ohmic contact, we propose a novel approach of adding a Ni/Si alloy seed layer between the Ni and Si layers. The metal nickel layer is deposited on the backside of the solar cells using electron beam evaporation, and excess nickel is removed by H2SO4:H2O2 etchant under annealing conditions of 300-425 °C to form a seed layer. The adhesion strength increased by more than 0.5 N mm-1 and the contact resistance dropped by 0.5 mΩ cm2 in comparison to the traditional direct plating Ni/Cu/Ag method. This is because the resulting Ni/Si alloy has outstanding electrical conductivity, and the produced Ni/Si alloy has higher adhesion over direct contact between the nickel-silicon interface, as well as enhanced surface roughness. The results showed that at an annealing temperature of 375 °C, the main compound formed was NiSi, with a contact resistance of 1 mΩ cm-2 and a maximum gate line adhesion of 2.7 N mm-1. This method proposes a new technical solution for cost reduction and efficiency improvement of n-TOPCon solar cells.

Blood-Brain Barrier-Penetrating and Lesion-Targeting Nanoplatforms Inspired by the Pathophysiological Features for Synergistic Ischemic Stroke Therapy.

Ischemic stroke is a dreadful vascular disorder that poses enormous threats to the public health. Due to its complicated pathophysiological features, current treatment options after ischemic stroke attack remains unsatisfactory. Insufficient drug delivery to ischemic lesions impeded by the blood-brain barrier (BBB) largely limits the therapeutic efficacy of most anti-stroke agents. Herein, inspired by the rapid BBB penetrability of 4T1 tumor cells upon their brain metastasis and natural roles of platelet in targeting injured vasculatures, a bio-derived nanojacket is developed by fusing 4T1 tumor cell membrane with platelet membrane, which further clothes on the surface of paeonol and polymetformin-loaded liposome to obtain biomimetic nanoplatforms (PP@PCL) for ischemic stroke treatment. The designed PP@PCL could remarkably alleviate ischemia-reperfusion injury by efficiently targeting ischemic lesion, preventing neuroinflammation, scavenging excess reactive oxygen species (ROS), reprogramming microglia phenotypes, and promoting angiogenesis due to the synergistic therapeutic mechanisms that anchor the pathophysiological characteristics of ischemic stroke. As a result, PP@PCL exerts desirable therapeutic efficacy in injured PC12 neuronal cells and rat model of ischemic stroke, which significantly attenuates neuronal apoptosis, reduces infarct volume, and recovers neurological functions, bringing new insights into exploiting promising treatment strategies for cerebral ischemic stroke management.

Reducing Perovskite/C60 Interface Losses via Sequential Interface Engineering for Efficient Perovskite/Silicon Tandem Solar Cell.

Wide-bandgap (WBG) perovskite solar cells hold tremendous potential for realizing efficient tandem solar cells. However, nonradiative recombination and carrier transport losses occurring at the perovskite/electron-selective contact (e.g. C60 ) interface present significant obstacles in approaching their theoretical efficiency limit. To address this, a sequential interface engineering (SIE) strategy that involves the deposition of ethylenediamine diiodide (EDAI2 ) followed by sequential deposition of 4-Fluoro-Phenethylammonium chloride (4F-PEACl) is implemented. The SIE technique synergistically narrows the conduction band offset and reduces recombination velocity at the perovskite/C60 interface. The best-performing WBG perovskite solar cell (1.67 eV) delivers a power conversion efficiency (PCE) of 21.8% and an impressive open-circuit voltage of 1.262 V. Moreover, through integration with double-textured silicon featuring submicrometer pyramid structures, a stabilized PCE of 29.6% is attained for a 1 cm2 monolithic perovskite/silicon tandem cell (certified PCE of 29.0%).

Automated stratification of trauma injury severity across multiple body regions using multi-modal, multi-class machine learning models.

OBJECTIVE: The timely stratification of trauma injury severity can enhance the quality of trauma care but it requires intense manual annotation from certified trauma coders. The objective of this study is to develop machine learning models for the stratification of trauma injury severity across various body regions using clinical text and structured electronic health records (EHRs) data. MATERIALS AND METHODS: Our study utilized clinical documents and structured EHR variables linked with the trauma registry data to create 2 machine learning models with different approaches to representing text. The first one fuses concept unique identifiers (CUIs) extracted from free text with structured EHR variables, while the second one integrates free text with structured EHR variables. Temporal validation was undertaken to ensure the models' temporal generalizability. Additionally, analyses to assess the variable importance were conducted. RESULTS: Both models demonstrated impressive performance in categorizing leg injuries, achieving high accuracy with macro-F1 scores of over 0.8. Additionally, they showed considerable accuracy, with macro-F1 scores exceeding or near 0.7, in assessing injuries in the areas of the chest and head. We showed in our variable importance analysis that the most important features in the model have strong face validity in determining clinically relevant trauma injuries. DISCUSSION: The CUI-based model achieves comparable performance, if not higher, compared to the free-text-based model, with reduced complexity. Furthermore, integrating structured EHR data improves performance, particularly when the text modalities are insufficiently indicative. CONCLUSIONS: Our multi-modal, multiclass models can provide accurate stratification of trauma injury severity and clinically relevant interpretations.

Solvent engineering for scalable fabrication of perovskite/silicon tandem solar cells in air.

Perovskite/silicon tandem solar cells hold great promise for realizing high power conversion efficiency at low cost. However, achieving scalable fabrication of wide-bandgap perovskite (~1.68 eV) in air, without the protective environment of an inert atmosphere, remains challenging due to moisture-induced degradation of perovskite films. Herein, this study reveals that the extent of moisture interference is significantly influenced by the properties of solvent. We further demonstrate that n-Butanol (nBA), with its low polarity and moderate volatilization rate, not only mitigates the detrimental effects of moisture in air during scalable fabrication but also enhances the uniformity of perovskite films. This approach enables us to achieve an impressive efficiency of 29.4% (certified 28.7%) for double-sided textured perovskite/silicon tandem cells featuring large-size pyramids (2-3 µm) and 26.3% over an aperture area of 16 cm2. This advance provides a route for large-scale production of perovskite/silicon tandem solar cells, marking a significant stride toward their commercial viability.

Microbiome preterm birth DREAM challenge: Crowdsourcing machine learning approaches to advance preterm birth research.

Every year, 11% of infants are born preterm with significant health consequences, with the vaginal microbiome a risk factor for preterm birth. We crowdsource models to predict (1) preterm birth (PTB; <37 weeks) or (2) early preterm birth (ePTB; <32 weeks) from 9 vaginal microbiome studies representing 3,578 samples from 1,268 pregnant individuals, aggregated from public raw data via phylogenetic harmonization. The predictive models are validated on two independent unpublished datasets representing 331 samples from 148 pregnant individuals. The top-performing models (among 148 and 121 submissions from 318 teams) achieve area under the receiver operator characteristic (AUROC) curve scores of 0.69 and 0.87 predicting PTB and ePTB, respectively. Alpha diversity, VALENCIA community state types, and composition are important features in the top-performing models, most of which are tree-based methods. This work is a model for translation of microbiome data into clinically relevant predictive models and to better understand preterm birth.

Evaluation of crowdsourced mortality prediction models as a framework for assessing artificial intelligence in medicine.

OBJECTIVE: Applications of machine learning in healthcare are of high interest and have the potential to improve patient care. Yet, the real-world accuracy of these models in clinical practice and on different patient subpopulations remains unclear. To address these important questions, we hosted a community challenge to evaluate methods that predict healthcare outcomes. We focused on the prediction of all-cause mortality as the community challenge question. MATERIALS AND METHODS: Using a Model-to-Data framework, 345 registered participants, coalescing into 25 independent teams, spread over 3 continents and 10 countries, generated 25 accurate models all trained on a dataset of over 1.1 million patients and evaluated on patients prospectively collected over a 1-year observation of a large health system. RESULTS: The top performing team achieved a final area under the receiver operator curve of 0.947 (95% CI, 0.942-0.951) and an area under the precision-recall curve of 0.487 (95% CI, 0.458-0.499) on a prospectively collected patient cohort. DISCUSSION: Post hoc analysis after the challenge revealed that models differ in accuracy on subpopulations, delineated by race or gender, even when they are trained on the same data. CONCLUSION: This is the largest community challenge focused on the evaluation of state-of-the-art machine learning methods in a healthcare system performed to date, revealing both opportunities and pitfalls of clinical AI.

A framework for future national pediatric pandemic respiratory disease severity triage: The HHS pediatric COVID-19 data challenge.

Introduction: With persistent incidence, incomplete vaccination rates, confounding respiratory illnesses, and few therapeutic interventions available, COVID-19 continues to be a burden on the pediatric population. During a surge, it is difficult for hospitals to direct limited healthcare resources effectively. While the overwhelming majority of pediatric infections are mild, there have been life-threatening exceptions that illuminated the need to proactively identify pediatric patients at risk of severe COVID-19 and other respiratory infectious diseases. However, a nationwide capability for developing validated computational tools to identify pediatric patients at risk using real-world data does not exist. Methods: HHS ASPR BARDA sought, through the power of competition in a challenge, to create computational models to address two clinically important questions using the National COVID Cohort Collaborative: (1) Of pediatric patients who test positive for COVID-19 in an outpatient setting, who are at risk for hospitalization? (2) Of pediatric patients who test positive for COVID-19 and are hospitalized, who are at risk for needing mechanical ventilation or cardiovascular interventions? Results: This challenge was the first, multi-agency, coordinated computational challenge carried out by the federal government as a response to a public health emergency. Fifty-five computational models were evaluated across both tasks and two winners and three honorable mentions were selected. Conclusion: This challenge serves as a framework for how the government, research communities, and large data repositories can be brought together to source solutions when resources are strapped during a pandemic.

Microbiome Preterm Birth DREAM Challenge: Crowdsourcing Machine Learning Approaches to Advance Preterm Birth Research.

Globally, every year about 11% of infants are born preterm, defined as a birth prior to 37 weeks of gestation, with significant and lingering health consequences. Multiple studies have related the vaginal microbiome to preterm birth. We present a crowdsourcing approach to predict: (a) preterm or (b) early preterm birth from 9 publicly available vaginal microbiome studies representing 3,578 samples from 1,268 pregnant individuals, aggregated from raw sequences via an open-source tool, MaLiAmPi. We validated the crowdsourced models on novel datasets representing 331 samples from 148 pregnant individuals. From 318 DREAM challenge participants we received 148 and 121 submissions for our two separate prediction sub-challenges with top-ranking submissions achieving bootstrapped AUROC scores of 0.69 and 0.87, respectively. Alpha diversity, VALENCIA community state types, and composition (via phylotype relative abundance) were important features in the top performing models, most of which were tree based methods. This work serves as the foundation for subsequent efforts to translate predictive tests into clinical practice, and to better understand and prevent preterm birth.

More Generalizable Models For Sepsis Detection Under Covariate Shift.

Sepsis is a major cause of mortality in the intensive care units (ICUs). Early intervention of sepsis can improve clinical outcomes for sepsis patients1,2,3. Machine learning models have been developed for clinical recognition of sepsis4,5,6. A common assumption of supervised machine learning models is that the covariates in the testing data follow the same distributions as those in the training data. When this assumption is violated (e.g., there is covariate shift), models that performed well for training data could perform badly for testing data. Covariate shift happens when the relationships between covariates and the outcome stay the same, but the marginal distributions of the covariates differ among training and testing data. Covariate shift could make clinical risk prediction model nongeneralizable. In this study, we applied covariate shift corrections onto common machine learning models and have observed that these corrections can help the models be more generalizable under the occurrence of covariate shift when detecting the onset of sepsis.

A Continuously Benchmarked and Crowdsourced Challenge for Rapid Development and Evaluation of Models to Predict COVID-19 Diagnosis and Hospitalization.

Importance: Machine learning could be used to predict the likelihood of diagnosis and severity of illness. Lack of COVID-19 patient data has hindered the data science community in developing models to aid in the response to the pandemic. Objectives: To describe the rapid development and evaluation of clinical algorithms to predict COVID-19 diagnosis and hospitalization using patient data by citizen scientists, provide an unbiased assessment of model performance, and benchmark model performance on subgroups. Design, Setting, and Participants: This diagnostic and prognostic study operated a continuous, crowdsourced challenge using a model-to-data approach to securely enable the use of regularly updated COVID-19 patient data from the University of Washington by participants from May 6 to December 23, 2020. A postchallenge analysis was conducted from December 24, 2020, to April 7, 2021, to assess the generalizability of models on the cumulative data set as well as subgroups stratified by age, sex, race, and time of COVID-19 test. By December 23, 2020, this challenge engaged 482 participants from 90 teams and 7 countries. Main Outcomes and Measures: Machine learning algorithms used patient data and output a score that represented the probability of patients receiving a positive COVID-19 test result or being hospitalized within 21 days after receiving a positive COVID-19 test result. Algorithms were evaluated using area under the receiver operating characteristic curve (AUROC) and area under the precision recall curve (AUPRC) scores. Ensemble models aggregating models from the top challenge teams were developed and evaluated. Results: In the analysis using the cumulative data set, the best performance for COVID-19 diagnosis prediction was an AUROC of 0.776 (95% CI, 0.775-0.777) and an AUPRC of 0.297, and for hospitalization prediction, an AUROC of 0.796 (95% CI, 0.794-0.798) and an AUPRC of 0.188. Analysis on top models submitting to the challenge showed consistently better model performance on the female group than the male group. Among all age groups, the best performance was obtained for the 25- to 49-year age group, and the worst performance was obtained for the group aged 17 years or younger. Conclusions and Relevance: In this diagnostic and prognostic study, models submitted by citizen scientists achieved high performance for the prediction of COVID-19 testing and hospitalization outcomes. Evaluation of challenge models on demographic subgroups and prospective data revealed performance discrepancies, providing insights into the potential bias and limitations in the models.

[Effects of three-dimensional culture on cell phenotype and hematopoietic cytokine expression of umbilical cord mesenchymal stem cells].

This study was aimed to investigate the change of cell phenotype and the expression of hematopoiesis associated cytokines in umbilical cord mesenchymal stem cells (UC-MSC) in three-dimensional (3-D) system. MSC were isolated from umbilical cord, and then cultured in 2-D and 3-D system respectively. The phenotype of MSC was detected by flow cytometry; the angiogenic capability of MSC cultured in 2-D and 3-D syitem was assessed using in vitro capillary formation assay. The cytokine expression of MSC in two kinds of culture conditions was measured by real-time PCR. The results showed that MSC were successfully isolated from umbilical cord. Flow cytometry showed that the percentage of CD31, CD133 and CD271 expressed in endothelial cells, endothelial progenitor cells and primitive mesenchymal stem cells increased significantly in 3-D culture conditions, as compared to 2-D system. Capillary formation assay showed that the angiogenic capability of UC-MSC was greatly enhanced. Quantitative PCR showed that the expression of ß-actin was upregulated in 3-D system. The expression of some cytokines associated with hematopoiesis, such as G-CSF, LIF, SCF, IL-1α, IL-1ß, IL-3, IL-7 and IL-11, increased, especially for LIF, IL-3, IL-7. The expression of IL-10 associated with immune regulation also increased. The expression of SDF-1, IL-6 slightly decreased, but without significant difference. It is concluded that expression of CD31, CD133 and CD271 increases in 3-D system, the angiogenic capability of UC-MSC enhances and the expression of hematopoiesis-associated cytokines in UC-MSC increases in 3-D system.

A novel functional TagSNP Rs7560488 in the DNMT3A1 promoter is associated with susceptibility to gastric cancer by modulating promoter activity.

DNA-methyltransferase (DNMT)-3A which contains DNMT3A1 and DNMT3A2 isoforms have been suggested to play a crucial role in carcinogenesis and showed aberrant expression in most cancers. Accumulated evidences also indicated that single nucleotide polymorphisms (SNP) in DNMT genes were associated with susceptibility to different tumors. We hypothesized that genetic variants in DNMT3A1 promoter region are associated with gastric cancer risk. We selected the tagSNPs from the HapMap database for the Chinese and genotyped in a case-control study to evaluate the association with gastric cancer (GC) in a Chinese population. We identified that the functional tagSNP rs7560488 T>C associated with a significantly increased risk of GC. In vitro functional analysis by luciferase reporter assay and EMSA indicated that the tagSNP rs7560488 T>C substantially altered transcriptional activity of DNMT3A1 gene via influencing the binding of some transcriptional factors, although a definite transcriptional factor remains to be established. Compared with TT homozygotes, subjects who were TC heterozygotes and CC homozygotes exhibited a reduced expression of DNMT3A1. Furthermore, stratified analysis showed that individuals who harbor TC or CC genotypes less than 60 years old were more susceptible to GC. Our results suggest that the genetic variations in the DNMT3A1 promoter contribute to the susceptibility to GC and also provide an insight that tagSNP rs7560488 T>C may be a promising biomarker for predicting GC genetic susceptibility and a valuable information in GC pathogenesis.