Injectable hydrogels are promising for treatment of bone defects in clinic owing to their minimally invasive procedure. Currently, there is limited emphasis on how to utilize injectable hydrogels to mobilize body's regenerative potential for enhancing bone regeneration. Herein, an injectable bone-mimicking hydrogel (BMH) scaffold assembled from nanocomposite microgel building blocks was developed, in which a highly interconnected microporous structure and an inorganic/organic (methacrylated hydroxyapatite and methacrylated gelatin) interweaved nano structure were well-designed. Compared with hydrogels lacking micro-nano structures or only showing microporous structure, the BMH scaffold enhanced the ingrowth of vessels and promoted the formation of dense cellular networks (including stem cells and M2 macrophages), across the entire scaffold at early stage after subcutaneous implantation. Moreover, the BMH scaffold could not only directly trigger osteogenic differentiation of the infiltrated stem cells, but also provided an instructive osteo-immune microenvironment by inducing macrophages into M2 phenotype. Mechanistically, our results reveal that the nano-rough structure of the BMH plays an essential role in inducing macrophage M2 polarization through activating mechanotransduction related RhoA/ROCK2 pathway. Overall, this work offers an injectable hydrogel with micro-nano structure driven bio-responsive abilities, highlighting harnessing body's inherent regenerative potential to realize bone regeneration.
The TP63 gene is essential for epithelial proliferation, differentiation, and maintenance during embryogenesis. Despite considerable clinical variability, TP63-related symptoms are characterized by ectodermal dysplasia, distal limb malformations, and orofacial clefts. We identified a novel TP63 variant (c.619A > G, p.K207E) in a seven-month-old Chinese patient with orofacial clefts and ectrodactyly but no evident signs of ectodermal dysplasia. This phenotype was rarely reported before. We summarized the presence of the three main TP63-related manifestations in the literature and noted different distributions of CP- and CL/P-related variants regarding p63 structural domains.
Cu-based catalysts are the most intensively studied in the field of electrocatalytic CO2 reduction reaction (CO2RR), demonstrating the capacity to yield diverse C1 and C2+ products albeit with unsatisfactory selectivity. Manipulation of the oxidation state of Cu sites during CO2RR process proves advantageous in modulating the selectivity of productions, but poses a formidable challenge. Here, an oxygen spillover strategy is proposed to enhance the oxidation state of Cu during CO2RR by incorporating the oxygen donor Sb2O4. The Cu-Sb bimetallic oxide catalyst attains a remarkable CO2-to-CO selectivity approaching unity, in stark contrast to the diverse product distribution observed with bare CuO. The exceptional Faradaic efficiency of CO can be maintained across a wide range of potential windows of ≈700 mV in 1 m KOH, and remains independent of the Cu/Sb ratio (ranging from 0.1:1 to 10:1). Correlative calculations and experimental results reveal that oxygen spillover from Sb2O4 to Cu sites maintains the relatively high valence state of Cu during CO2RR, which diminishes the binding strength of *CO, thereby achieving heightened selectivity in CO production. These findings propose the role of oxygen spillover in CO2RR over Cu-based catalysts, and shed light on the rational design of highly selective CO2 reduction catalysts.
BACKGROUND: Standardized and reliable medical photographs are crucial for preoperative and postoperative comparisons and academic communication in the medical field. There is limited research on photographic techniques in patients with cleft lip. Deformities of the lip and nose in patients with cleft lip are not only associated with morphological abnormalities but also with abnormalities of muscle function. METHODS: Considering the morphology and function of the lips and nose in cleft lip patients, the study captured the deformity of cleft lip patients in 6 positions: frontal view, 45 degrees left-right tilted side view, 90 degrees left-right tilted side view, and basal view, and in 5 facial expressions: tightly closed lips, slightly open mouth, smiling, teeth bared, and pout. RESULTS: In 6 different positions and 5 different expressions, we took pictures of lip and nasal deformities covering most of the common deformities in patients with cleft lip, such as white lip scarring, interruption of continuity of vermillion border, lip prolapse, asymmetric corners of the mouth, collapsed ala nasi, loss of the nasal base and deviated nasal septum. CONCLUSIONS: This paper suggests a set of effective, easy-to-follow, and precise photographic protocols to assist cleft lip surgeons in capturing suitable and informative, high-quality 2D digital photographs. LEVEL OF EVIDENCE: Level-V.
Objective: Immune cells play a key role in tumor microenvironment. The purpose of this study was to investigate the infiltration and clinical indication of immune cells including their combined prognostic value in microenvironment of triple negative breast cancer. Methods: We investigated 100 patients with triple negative breast cancer by Opal/Tyramide Signal Amplification multispectral immunofluorescence between 2003 and 2017 at Zhejiang Provincial people's Hospital. Intratumoral and stromal immune cells of triple negative breast cancer were classified and quantitatively analyzed. Survival outcomes were compared using the Kaplan-Meier method and further analyzed with multivariate analysis. Results: Infiltration level of stromal B lymphocytes, stromal and intratumoral CD8+ T cells, stromal CD4+ T cells, stromal PD-L1 and intratumoral tumor associated macrophages 2 cells were shown as independent factors affecting disease-free survival and overall survival in univariate analysis. Stromal B lymphocytes, T stage, N stage and pathological type were independent predictive factors for both DFS and OS in multivariate analysis. We firstly found that patients with B lymphocytes-enriched subtypes have a better prognosis than those with T lymphocytes-enriched subtypes and tumor-associated macrophage-enriched subtypes. Conclusion: The present study identified a bunch of immune targets and subtypes, which could be exploited in future combined immunotherapy/chemotherapy strategies for triple negative breast cancer patients.
Microenvironment regulation of M-N4 single-atom catalysts (SACs) is a promising way to tune their catalytic properties toward the electrochemical CO2 reduction reaction. However, strategies that can effectively introduce functional groups around the M-N4 sites through strong covalent bonding and under mild reaction conditions are highly desired. Taking the hydrophilic Ni-N4 SAC as a representative, we report herein a [2+1] cycloaddition reaction between Ni-N4 and in-situ generated difluorocarbene (F2C:), and enable the surface fluorocarbonation of Ni-N4, resulting in the formation of a super-hydrophobic Ni-N4-CF2 catalyst. Meanwhile, the mild reaction conditions allow Ni-N4-CF2 to inherit both the electronic and structural configuration of the Ni-N4 sites from Ni-N4. Enhanced electrochemical CO2-to-CO Faradaic efficiency above 98% is achieved in a wide operating potential window from -0.7 V to -1.3 V over Ni-N4-CF2. In-situ spectroelectrochemical studies reveal that a highly hydrophobic microenvironment formed by the -CF2- group repels asymmetric H-bonded water at the electrified interface, inhibiting the hydrogen evolution reaction and promoting CO production. This work highlights the advantages of [2+1] cycloaddition reactions on the covalent modification of N-doped carbon-supported catalysts.
Alzheimer's disease (AD) is a gradually advancing neurodegenerative disorder characterized by a concealed onset. Acetylcholinesterase (AChE) is an efficient hydrolase that catalyzes the hydrolysis of acetylcholine (ACh), which regulates the concentration of ACh at synapses and then terminates ACh-mediated neurotransmission. There are inhibitors to inhibit the activity of AChE currently, but its side effects are inevitable. In various application fields where Al have gained prominence, neural network-based models for molecular design have recently emerged and demonstrate encouraging outcomes. However, in the conditional molecular generation task, most of the current generation models need additional optimization algorithms to generate molecules with intended properties which make molecular generation inefficient. Consequently, we introduce a cognitive-conditional molecular design model, termed PED, which leverages the variational auto-encoder. Its primary function is to adeptly produce a molecular library tailored for specific properties. From this library, we can then identify molecules that inhibit AChE activity without adverse effects. These molecules serve as lead compounds, hastening AD treatment and concurrently enhancing the AI's cognitive abilities. In this study, we aim to fine-tune a VAE model pre-trained on the ZINC database using active compounds of AChE collected from Binding DB. Different from other molecular generation models, the PED can simultaneously perform both property prediction and molecule generation, consequently, it can generate molecules with intended properties without additional optimization process. Experiments of evaluation show that proposed model performs better than other methods benchmarked on the same data sets. The results indicated that the model learns a good representation of potential chemical space, it can well generate molecules with intended properties. Extensive experiments on benchmark datasets confirmed PED's efficiency and efficacy. Furthermore, we also verified the binding ability of molecules to AChE through molecular docking. The results showed that our molecular generation system for AD shows excellent cognitive capacities, the molecules within the molecular library could bind well to AChE and inhibit its activity, thus preventing the hydrolysis of ACh.
Microbiome and microbial dysbiosis have been proven to be involved in the carcinogenesis and treatment of gynecologic malignancies. However, there is a noticeable gap in the literature, as no comprehensive papers have covered general information, research status, and research frontiers in this field. This study addressed this gap by exploring the relationship between the gut and female reproductive tract (FRT) microbiome and gynecological cancers from a bibliometric perspective. Using VOSviewer 1.6.18, CiteSpace 6.1.R6, and HistCite Pro 2.1 software, we analyzed data retrieved from the Web of Science (WOS) Core Collection (WoSCC) database. Our dataset, consisting of 204 articles published from 2012 to 2022, revealed a consistent and upward publication trend. The United States and the United Kingdom were the primary driving forces, attributed to their prolificacy, high-quality output, and extensive cooperation. The University of Arizona Cancer Center, which is affiliated with the United States, ranked first among the top ten most prolific institutions. Frontiers in Cellular and Infection Microbiology emerged as the leading publisher. Herbst-Kralovetz MM led as the most productive author. Mitra A was the most influential author. Cervical cancer is notably associated with the microbiome, while endometrial and ovarian cancers are receiving increased attention in the last year. Intersections between the gut microbiome and estrogen are of growing importance. Current research focuses on identifying specific microbial species for etiological diagnosis, while frontiers mainly focus on the anticancer potential of microorganisms, such as regulating the effects of immune checkpoint inhibitors. In conclusion, this study sheds light on a novel and burgeoning direction of research, providing a one-stop overview of the microbiome in gynecologic malignancies. Its findings aim to help young researchers to identify research directions and future trends for ongoing investigations.
The molecular generation task stands as a pivotal step in the domains of computational chemistry and drug discovery, aiming to computationally generate molecular structures for specific properties. In contrast to previous models that focused primarily on SMILES strings or molecular graphs, our model placed a special emphasis on the substructure information on molecules, enabling the model to learn richer chemical rules and structure features from fragments and chemical reaction information on molecules. To accomplish this, we fragmented the molecules to construct heterogeneous graph representations based on atom and fragment information. Then our model mapped the heterogeneous graph data into a latent vector space by using an encoder and employed a self-regressive generative model as a decoder for molecular generation. Additionally, we performed transfer learning on the model using a small set of ligand molecules known to be active against the target protein to generate molecules that bind better to the target protein. Experimental results demonstrate that our model is highly competitive with state-of-the-art models. It can generate valid and diverse molecules with favorable physicochemical properties and drug-likeness. Importantly, they produce novel molecules with high docking scores against the target proteins.
Proteins , Proteins/chemistry , Proteins/metabolism , Ligands , Models, Molecular , Drug Discovery/methods , Molecular Docking Simulation
Some noncoding RNAs (ncRNAs) carry open reading frames (ORFs) that can be translated into micropeptides, although noncoding RNAs (ncRNAs) have been previously assumed to constitute a class of RNA transcripts without coding capacity. Furthermore, recent studies have revealed that ncRNA-derived micropeptides exhibit regulatory functions in the development of many tumours. Although some of these micropeptides inhibit tumour growth, others promote it. Understanding the role of ncRNA-encoded micropeptides in cancer poses new challenges for cancer research, but also offers promising prospects for cancer therapy. In this review, we summarize the types of ncRNAs that can encode micropeptides, highlighting recent technical developments that have made it easier to research micropeptides, such as ribosome analysis, mass spectrometry, bioinformatics methods, and CRISPR/Cas9. Furthermore, based on the distribution of micropeptides in different subcellular locations, we explain the biological functions of micropeptides in different human cancers and discuss their underestimated potential as diagnostic biomarkers and anticancer therapeutic targets in clinical applications, information that may contribute to the discovery and development of new micropeptide-based tools for early diagnosis and anticancer drug development.
Etomidate is a nonbarbiturate sedative derived from imidazole. Prolonged and excessive use of etomidate can lead to the suppression of adrenocortical function, myoclonus, and even death. This report describes a rare case of a 47-year-old man who died from acute intoxication after oral ingestion of liquid containing etomidate. The cause of death was conclusively attributed to etomidate based on a comprehensive investigation, including autopsy, histopathological examination, toxicological analysis, and biochemical analysis. This is the first reported case of a fatality solely resulting from the oral ingestion of etomidate, which can provide valuable insights for future forensic investigations involving etomidate poisoning. Therefore, it is imperative to share this case with the scientific community.
MOTIVATION: Protein-protein interaction sites (PPIS) are crucial for deciphering protein action mechanisms and related medical research, which is the key issue in protein action research. Recent studies have shown that graph neural networks have achieved outstanding performance in predicting PPIS. However, these studies often neglect the modeling of information at different scales in the graph and the symmetry of protein molecules within three-dimensional space. RESULTS: In response to this gap, this paper proposes the MEG-PPIS approach, a PPIS prediction method based on multi-scale graph information and E(n) equivariant graph neural network (EGNN). There are two channels in MEG-PPIS: the original graph and the subgraph obtained by graph pooling. The model can iteratively update the features of the original graph and subgraph through the weight-sharing EGNN. Subsequently, the max-pooling operation aggregates the updated features of the original graph and subgraph. Ultimately, the model feeds node features into the prediction layer to obtain prediction results. Comparative assessments against other methods on benchmark datasets reveal that MEG-PPIS achieves optimal performance across all evaluation metrics and gets the fastest runtime. Furthermore, specific case studies demonstrate that our method can predict more true positive and true negative sites than the current best method, proving that our model achieves better performance in the PPIS prediction task. AVAILABILITY AND IMPLEMENTATION: The data and code are available at https://github.com/dhz234/MEG-PPIS.git.
By observation of Sprague-Dawley male rats with different ejaculatory behaviors, we have identified distinct behavioral characteristics in rapid ejaculator rats. To validate these differential behaviors, we conducted multifaceted behavioral experiments on rapid ejaculator rats and normal rats. Through mating experiments, 42 male rats were categorized into 5 rapid ejaculator rats, 29 normal ejaculator rats, and 8 sluggish ejaculator rats according to their ejaculation frequency. We selected 5 rats exhibiting rapid ejaculation and 5 rats with normal ejaculation for participation in the Morris water maze, open-field test, and balance beam experiments. The open-field tests revealed that rapid ejaculator rats spent shorter time in the center region (1.23 ± 1.21 vs. 6.56 ± 2.40 s, P = 0.0041), less entered the center region (0.80 ± 0.75 vs. 3.40 ± 1.50, time, P = 0.0145), traveled shorter distances (17,003.77 ± 3339.42 vs. 25,037.90 ± 5499.94 mm, P = 0.0371), and had a lower average speed compared with normal rats (66.09 ± 62.36 vs. 195.56 ± 83.41 mm/s, P = 0.0377). However, no significant differences were observed in the Morris water maze and balance beam experiments (0.25 ± 0.05 vs. 0.26 ± 0.07, P = 0.7506;16.40 ± 3.77 vs. 16.25 ± 2.05, P = 0.9515). These behavioral results indicated that the rapid ejaculator rats were more prone to anxiety. To further substantiate this claim, we examined Brain-derived neurotrophic factor expression levels in the hippocampus of rat brains using immunohistochemistry and western blotting. The results demonstrate lower Brain-derived neurotrophic factor expression in the hippocampus of rapid ejaculator rats compared with that in normal rats (P = 0.0093). Thus, our experiments indicate that rapid ejaculator rats exhibit a higher propensity for anxiety, potentially linked to their abnormal neurophysiologic state. It is concluded that rapid ejaculator rats may be more susceptible to anxiety on a pathophysiological basis.
To properly treat and care for hepatic cystic echinococcosis (HCE), it is essential to make an accurate diagnosis before treatment. OBJECTIVE: The objective of this study was to assess the diagnostic accuracy of computer-aided diagnosis techniques in classifying HCE ultrasound images into five subtypes. METHODS: A total of 1820 HCE ultrasound images collected from 967 patients were included in the study. A multi-kernel learning method was developed to learn the texture and depth features of the ultrasound images. Combined kernel functions were built-in Support Vector Machine (MK-SVM) for the classification work. The experimental results were evaluated using five-fold cross-validation. Finally, our approach was compared with three other machine learning algorithms: the decision tree classifier, random forest, and gradient boosting decision tree. RESULTS: Among all the methods used in the study, the MK-SVM achieved the highest accuracy of 96.6% on the fused feature set. CONCLUSION: The multi-kernel learning method effectively learns different image features from ultrasound images by utilizing various kernels. The MK-SVM method, which combines the learning of texture features and depth features separately, has significant application value in HCE classification tasks.
Objective: Viral encephalitis is an infectious disease severely affecting human health. It is caused by a wide variety of viral pathogens, including herpes viruses, flaviviruses, enteroviruses, and other viruses. The laboratory diagnosis of viral encephalitis is a worldwide challenge. Recently, high-throughput sequencing technology has provided new tools for diagnosing central nervous system infections. Thus, In this study, we established a multipathogen detection platform for viral encephalitis based on amplicon sequencing. Methods: We designed nine pairs of specific polymerase chain reaction (PCR) primers for the 12 viruses by reviewing the relevant literature. The detection ability of the primers was verified by software simulation and the detection of known positive samples. Amplicon sequencing was used to validate the samples, and consistency was compared with Sanger sequencing. Results: The results showed that the target sequences of various pathogens were obtained at a coverage depth level greater than 20×, and the sequence lengths were consistent with the sizes of the predicted amplicons. The sequences were verified using the National Center for Biotechnology Information BLAST, and all results were consistent with the results of Sanger sequencing. Conclusion: Amplicon-based high-throughput sequencing technology is feasible as a supplementary method for the pathogenic detection of viral encephalitis. It is also a useful tool for the high-volume screening of clinical samples.
Encephalitis, Viral , Viruses , Humans , Encephalitis, Viral/diagnosis , Viruses/genetics , High-Throughput Nucleotide Sequencing/methods , Polymerase Chain Reaction , DNA, Viral
Microorganisms are highly sensitive to toxic metal pollution and play an important role in the material cycling and energy flow of the water ecosystem. Herein, 13 sediment samples from Junchong Reservoir (Guangxi Province, China) were collected in December 2021. The spatial distribution of pollution levels for toxic metals and the effects of toxic metals on the composition, functional characteristics, and metabolism of microorganisms were investigated. The results demonstrated that the area is a proximate area to industrial zones with severity of toxic metal pollution. Their mean concentrations of As, Cu, Zn, and Pb were up to 128.79 mg/kg, 57.62 mg/kg, 594.77 mg/kg, and 97.12 mg/kg respectively. There was a strong correlation between As, Cu, Zn, and Pb, with the highest correlation coefficient reaching 0.94. As the level of toxic metal pollution increases, the diversity and abundance of microorganisms gradually decrease. Compared to those with lower pollution levels, the Shannon index in regions with higher pollution levels decreases by up to 0.373, and the Chao index decreases by up to 143.507. However, the relative abundance of Bacteroidota, Patescibacteria, and Chloroflexi increased by 23%, 20%, and 5%, respectively, indicating their higher adaptability to toxic metals. Furthermore, microbial carbon and nitrogen metabolism were also affected by the presence of toxic metals. FAPROTAX analysis demonstrated an abundant reduction of ecologically functional groups associated with carbon and nitrogen transformations under high toxic metal pollution levels. KEGG pathway analysis indicated that carbon fixation and nitrogen metabolism pathways were inhibited with increasing toxic metal concentrations. These findings would contribute to a better understanding of the effects of toxic metal pollution on sediment microbial communities and function, shedding light on the ecological consequences of toxic metal contamination.
Carbon , Geologic Sediments , Nitrogen , Geologic Sediments/chemistry , China , Water Pollutants, Chemical/toxicity , Microbiota/drug effects , Environmental Monitoring , Metals, Heavy
Thyroid cancer (THCA) is the most common endocrine malignancy worldwide and has been rising at the fastest rate in recent years. Long-stranded non-coding RNAs (lncRNAs) and N6-methyladenosine (m6A) have been associated with immunotherapy efficacy and cancer prognosis. However, how m6A-associated lncRNAs (mrlncRNAs) affect the prognosis of patients with thyroid cancer is unclear. Therefore, this study utilized The Cancer Genome Atlas (TCGA) database to provide thyroid cancer-related transcriptomic data and related clinical data. The R program was used to identify m6A-related lncRNAs, and a risk model consisting of two lncRNAs (LINC02471 and DOCK9-DT) was obtained using least absolute shrinkage and selection operator (LASSO) Cox regression analysis. Kaplan-Meier survival analysis and transient subject operating characteristics (ROC) were used for analysis. The results showed a substantial association between immune cell infiltration and risk scores. Independent analyses confirmed that the expression of LINC02471 and DOCK9-DT was significantly higher in thyroid cancer tissues than in normal tissues, suggesting that they may be useful biomarkers for thyroid cancer.
Adenosine , Biomarkers, Tumor , RNA, Long Noncoding , Thyroid Neoplasms , Humans , RNA, Long Noncoding/genetics , RNA, Long Noncoding/metabolism , Biomarkers, Tumor/genetics , Thyroid Neoplasms/genetics , Thyroid Neoplasms/immunology , Adenosine/analogs & derivatives , Adenosine/metabolism , Gene Expression Regulation, Neoplastic , Prognosis , Male , Female , GTPase-Activating Proteins/genetics , GTPase-Activating Proteins/metabolism , Middle Aged
OBJECTIVE: To explore the feasibility of identifying epidermal growth factor receptor (EGFR) mutation molecular subtypes in primary lesions based on the radiomics features of lung adenocarcinoma brain metastases using magnetic resonance imaging (MRI). METHODS: We retrospectively analyzed clinical, imaging, and genetic testing data of patients with lung adenocarcinoma with EGFR gene mutations who had brain metastases. Three-dimensional radiomics features were extracted from contrast-enhanced T1-weighted images. The volume of interest was delineated and normalized using Z-score, dimensionality reduction was performed using principal component analysis, feature selection using Relief, and radiomics model construction using adaptive boosting as a classifier. Data were randomly divided into training and testing datasets at an 8:2 ratio. Five-fold cross-validation was conducted in the training set to select the optimal radiomics features and establish a predictive model for distinguishing between exon 19 deletion (19Del) and exon 21 L858R point mutation (21L858R), the two most common EGFR gene mutations. The testing set was used for external validation of the models. Model performance was evaluated using receiver operating characteristic curve and decision curve analyses. RESULTS: Overall, 86 patients with 228 brain metastases were included. Patient age was identified as an independent predictor for distinguishing between 19Del and 21L858R. The area under the curve (AUC) values of the radiomics model in the training and testing datasets were 0.895 (95% confidence interval [CI]: 0.850-0.939) and 0.759 (95% CI: 0.0.614-0.903), respectively. The AUC for diagnosis of all cases using a combined model of age and radiomics was 0.888 (95% CI: 0.846-0.930), slightly higher than that of the radiomics model alone (0.866, 95% CI: 0.820-0.913), but without statistical significance (p=0.1626). In the decision curve analysis, both models demonstrated clinical net benefits. CONCLUSIONS: The radiomics model based on MRI of lung adenocarcinoma brain metastases could distinguish between EGFR 19Del and 21L858R mutations in the primary lesion.
Adenocarcinoma of Lung , Brain Neoplasms , ErbB Receptors , Lung Neoplasms , Magnetic Resonance Imaging , Mutation , Humans , Brain Neoplasms/genetics , Brain Neoplasms/diagnostic imaging , Brain Neoplasms/secondary , Male , Female , Middle Aged , ErbB Receptors/genetics , Magnetic Resonance Imaging/methods , Lung Neoplasms/genetics , Lung Neoplasms/diagnostic imaging , Lung Neoplasms/pathology , Adenocarcinoma of Lung/genetics , Adenocarcinoma of Lung/diagnostic imaging , Adenocarcinoma of Lung/pathology , Aged , Retrospective Studies , Adult , Radiomics
The present study aims to assess the treatment outcome of patients with diabetes and tuberculosis (TB-DM) at an early stage using machine learning (ML) based on electronic medical records (EMRs). A total of 429 patients were included at Chongqing Public Health Medical Center. The random-forest-based Boruta algorithm was employed to select the essential variables, and four models with a fivefold cross-validation scheme were used for modeling and model evaluation. Furthermore, we adopted SHapley additive explanations to interpret results from the tree-based model. 9 features out of 69 candidate features were chosen as predictors. Among these predictors, the type of resistance was the most important feature, followed by activated partial throm-boplastic time (APTT), thrombin time (TT), platelet distribution width (PDW), and prothrombin time (PT). All the models we established performed above an AUC 0.7 with good predictive performance. XGBoost, the optimal performing model, predicts the risk of treatment failure in the test set with an AUC 0.9281. This study suggests that machine learning approach (XGBoost) presented in this study identifies patients with TB-DM at higher risk of treatment failure at an early stage based on EMRs. The application of a convenient and economy EMRs based on machine learning provides new insight into TB-DM treatment strategies in low and middle-income countries.
Diabetes Mellitus , Humans , Comorbidity , Treatment Failure , Electronic Health Records , Machine Learning
