Avoid non-diagnostic EUS-FNA: a DNN model as a possible gatekeeper to distinguish pancreatic lesions prone to inconclusive biopsy.

OBJECTIVE: This work aimed to explore the utility of CT radiomics with machine learning for distinguishing the pancreatic lesions prone to non-diagnostic ultrasound-guided fine-needle aspiration (EUS-FNA). METHODS: 498 patients with pancreatic EUS-FNA were retrospectively reviewed [Development cohort: 147 pancreatic ductal adenocarcinoma (PDAC); Validation cohort: 37 PDAC]. Pancreatic lesions not PDAC were also tested exploratively. Radiomics extracted from contrast-enhanced CT was integrated with deep neural networks (DNN) after dimension reduction. The receiver operating characteristic (ROC) curve, and decision curve analysis (DCA) were performed for model evaluation. And, the explainability of the DNN model was analyzed by integrated gradients. RESULTS: The DNN model was effective in distinguishing PDAC lesions prone to non-diagnostic EUS-FNA (Development cohort: AUC = 0.821, 95% CI: 0.742-0.900; Validation cohort: AUC = 0.745, 95% CI: 0.534-0.956). In all cohorts, the DNN model showed better utility than the logistic model based on traditional lesion characteristics with NRI >0 (p < 0.05). And, the DNN model had net benefits of 21.6% at the risk threshold of 0.60 in the validation cohort. As for the model explainability, gray-level co-occurrence matrix (GLCM) features contributed the most averagely and the first-order features were the most important in the sum attribution. CONCLUSION: The CT radiomics-based DNN model can be a useful auxiliary tool for distinguishing the pancreatic lesions prone to nondiagnostic EUS-FNA and provide alerts for endoscopists preoperatively to reduce unnecessary EUS-FNA. ADVANCES IN KNOWLEDGE: This is the first investigation into the utility of CT radiomics-based machine learning in avoiding non-diagnostic EUS-FNA for patients with pancreatic masses and providing potential pre-operative assistance for endoscopists.

Deep Learning Identifies Intelligible Predictors of Poor Prognosis in Chronic Kidney Disease.

Early diagnosis and prediction of chronic kidney disease (CKD) progress within a given duration are critical to ensure personalized treatment, which could improve patients' quality of life and prolong survival time. In this study, we explore the intelligibility of machine-learning and deep-learning models on end-stage renal disease (ESRD) prediction, based on readily-accessible clinical and laboratory features of patients suffering from CKD. Eight machine learning models were used to predict whether a patient suffering from CKD would progress to ESRD within three years based on demographics, clinical,and comorbidity information. LASSO, random forest, and XGBoost were used to identify the most significant markers. In addition, we introduced four advanced attribution methods to the deep learning model to enhance model intelligibility. The deep learning model achieved an AUC-ROC of 0.8991, which was significantly higher than that of baseline models. The interpretation generated by deep learning with attribution methods, random forest, and XGBoost was consistent with clinical knowledge, whereas LASSO-based interpretation was inconsistent. Hematuria, proteinuria, potassium, urine albumin to creatinine ratio were positively associated with the progression of CKD, while eGFR and urine creatinine were negatively associated. In conclusion, deep learning with attribution algorithms could identify intelligible features of CKD progression. Our model identified a number of critical, but under-reported features, which may be novel markers for CKD progression. This study provides physicians with solid data-driven evidence for using machine learning for CKD clinical management and treatment.

Network-based prediction of the disclosure of ideation about self-harm and suicide in online counseling sessions.

BACKGROUND: In psychological services, the transition to the disclosure of ideation about self-harm and suicide (ISS) is a critical point warranting attention. This study developed and tested a succinct descriptor to predict such transitions in an online synchronous text-based counseling service. METHOD: We analyzed two years' worth of counseling sessions (N = 49,770) from Open Up, a 24/7 service in Hong Kong. Sessions from Year 1 (N = 20,618) were used to construct a word affinity network (WAN), which depicts the semantic relationships between words. Sessions from Year 2 (N = 29,152), including 1168 with explicit ISS, were used to train and test the downstream ISS prediction model. We divided and classified these sessions into ISS blocks (ISSBs), blocks prior to ISSBs (PISSBs), and non-ISS blocks (NISSBs). To detect PISSB, we adopted complex network approaches to examine the distance among different types of blocks in WAN. RESULTS: Our analyses find that words within a block tend to form a module in WAN and that network-based distance between modules is a reliable indicator of PISSB. The proposed model yields a c-statistic of 0.79 in identifying PISSB. CONCLUSIONS: This simple yet robust network-based model could accurately predict the transition point of suicidal ideation prior to its explicit disclosure. It can potentially improve the preparedness and efficiency of help-providers in text-based counseling services for mitigating self-harm and suicide.

In online counseling, the help-provider can often be engaging with several service users simultaneously. Therefore, new tools that could help to alert and assist the help-provider and increase their preparedness for getting further help for service users could be useful. In this study, we developed and tested a new tool that is designed to alert help-providers to the disclosure of self-harm and suicidal thoughts, based on the words that the service user has been typing. The tool is developed on the basis that word usage may have a specific pattern when suicidal thoughts are more likely to occur. We tested our tool using two years' worth of online counseling conversations and we show that our approach can help to predict the confession of suicidal thoughts. As such, we are taking a step forward in helping to improve these counseling services.

Deep learning identifies explainable reasoning paths of mechanism of action for drug repurposing from multilayer biological network.

The discovery and repurposing of drugs require a deep understanding of the mechanism of drug action (MODA). Existing computational methods mainly model MODA with the protein-protein interaction (PPI) network. However, the molecular interactions of drugs in the human body are far beyond PPIs. Additionally, the lack of interpretability of these models hinders their practicability. We propose an interpretable deep learning-based path-reasoning framework (iDPath) for drug discovery and repurposing by capturing MODA on by far the most comprehensive multilayer biological network consisting of the complex high-dimensional molecular interactions between genes, proteins and chemicals. Experiments show that iDPath outperforms state-of-the-art machine learning methods on a general drug repurposing task. Further investigations demonstrate that iDPath can identify explicit critical paths that are consistent with clinical evidence. To demonstrate the practical value of iDPath, we apply it to the identification of potential drugs for treating prostate cancer and hypertension. Results show that iDPath can discover new FDA-approved drugs. This research provides a novel interpretable artificial intelligence perspective on drug discovery.

Ureteral calculi lithotripsy for single ureteral calculi: can DNN-assisted model help preoperatively predict risk factors for sepsis?

OBJECTIVES: To explore the utility of radiomics and deep learning model in assessing the risk factors for sepsis after flexible ureteroscopy lithotripsy (FURL) or percutaneous nephrolithotomy (PCNL) in patients with ureteral calculi. METHODS: This retrospective analysis included 847 patients with treatment-naive proximal ureteral calculi who received FURL or PCNL. All participants were preoperatively conducted non-contrast computed tomography scans, and relevant clinical information was meanwhile collected. After propensity score matching, the radiomics model was established to predict the onset of sepsis. A deep learning model was also adapted to further improve the prediction accuracy. Performance of these trained models was verified in another independent external validation set including 40 cases of ureteral calculi patients. RESULTS: The overall incidence of sepsis after FURL or PCNL was 5.9%. The least absolute shrinkage and selection operator (LASSO) regression analysis revealed 26 predictive variables, with an overall AUC of 0.881 (95% CI, 0.813-0.931) and an AUC of 0.783 (95% CI, 0.766-0.801) in external validation cohort. Judicious adaption of a deep neural network (DNN) model to our dataset improved the AUC to 0.920 (95% CI, 0.906-0.933) in the internal validation. To eliminate the overfitting, external validation was carried out for DNN model (AUC = 0.874 (95% CI, 0.858-0.891)). CONCLUSIONS: The DNN was more effective than the LASSO model in revealing risk factors for sepsis after FURL or PCNL in single ureteral calculi patients, and females are more susceptible to sepsis than males. Deep learning models have the potential to act as gatekeepers to facilitate patient stratification. KEY POINTS: • Both the least absolute shrinkage and selection operator (LASSO) and deep neural network (DNN) models were shown to be effective in sepsis prediction. • The DNN model achieved superior prediction capability, with an AUC of 0.920 (95% CI, 0.906-0.933). • DNN-assisted model has potential to serve as a gatekeeper to facilitate patient stratification.

An online advertising intervention to increase adherence to stay-at-home-orders during the COVID-19 pandemic: An efficacy trial monitoring individual-level mobility data.

The COVID-19 pandemic has led public health departments to issue several orders and recommendations to reduce COVID-19-related morbidity and mortality. However, for various reasons, including lack of ability to sufficiently monitor and influence behavior change, adherence to these health orders and recommendations has been suboptimal. Starting April 29, 2020, during the initial stay-at-home orders issued by various state governors, we conducted an intervention that sent online website and mobile application advertisements to people's mobile phones to encourage them to adhere to stay-at-home orders. Adherence to stay-at-home orders was monitored using individual-level cell phone mobility data, from April 29, 2020 through May 10, 2020. Mobile devices across 5 regions in the United States were randomly-assigned to either receive advertisements from our research team advising them to stay at home to stay safe (intervention group) or standard advertisements from other advertisers (control group). Compared to control group devices that received only standard corporate advertisements (i.e., did not receive public health advertisements to stay at home), the (intervention group) devices that received public health advertisements to stay at home demonstrated objectively-measured increased adherence to stay at home (i.e., smaller radius of gyration, average travel distance, and larger stay-at-home ratios). Results suggest that 1) it is feasible to use mobility data to assess efficacy of an online advertising intervention, and 2) online advertisements are a potentially effective method for increasing adherence to government/public health stay-at-home orders.

GraphSynergy: a network-inspired deep learning model for anticancer drug combination prediction.

OBJECTIVE: To develop an end-to-end deep learning framework based on a protein-protein interaction (PPI) network to make synergistic anticancer drug combination predictions. MATERIALS AND METHODS: We propose a deep learning framework named Graph Convolutional Network for Drug Synergy (GraphSynergy). GraphSynergy adapts a spatial-based Graph Convolutional Network component to encode the high-order topological relationships in the PPI network of protein modules targeted by a pair of drugs, as well as the protein modules associated with a specific cancer cell line. The pharmacological effects of drug combinations are explicitly evaluated by their therapy and toxicity scores. An attention component is also introduced in GraphSynergy, which aims to capture the pivotal proteins that play a part in both PPI network and biomolecular interactions between drug combinations and cancer cell lines. RESULTS: GraphSynergy outperforms the classic and state-of-the-art models in predicting synergistic drug combinations on the 2 latest drug combination datasets. Specifically, GraphSynergy achieves accuracy values of 0.7553 (11.94% improvement compared to DeepSynergy, the latest published drug combination prediction algorithm) and 0.7557 (10.95% improvement compared to DeepSynergy) on DrugCombDB and Oncology-Screen datasets, respectively. Furthermore, the proteins allocated with high contribution weights during the training of GraphSynergy are proved to play a role in view of molecular functions and biological processes, such as transcription and transcription regulation. CONCLUSION: The introduction of topological relations between drug combination and cell line within the PPI network can significantly improve the capability of synergistic drug combination identification.

Demand-driven spreading patterns of African swine fever in China.

African swine fever (ASF) is a highly contagious hemorrhagic viral disease of domestic and wild pigs. ASF has led to major economic losses and adverse impacts on livelihoods of stakeholders involved in the pork food system in many European and Asian countries. While the epidemiology of ASF virus (ASFV) is fairly well understood, there is neither any effective treatment nor vaccine. In this paper, we propose a novel method to model the spread of ASFV in China by integrating the data of pork import/export, transportation networks, and pork distribution centers. We first empirically analyze the overall spatiotemporal patterns of ASFV spread and conduct extensive experiments to evaluate the efficacy of a number of geographic distance measures. These empirical analyses of ASFV spread within China indicate that the first occurrence of ASFV has not been purely dependent on the geographical distance from existing infected regions. Instead, the pork supply-demand patterns have played an important role. Predictions based on a new distance measure achieve better performance in predicting ASFV spread among Chinese provinces and thus have the potential to enable the design of more effective control interventions.

Risk of suicide after a self-poisoning episode: a self-controlled case series study.

PURPOSE: The risk of death from suicide after self-poisoning has been known to be significantly higher as compared to the general population. Nevertheless, the change in suicide risk before and after self-poisoning is still unclear. METHODS: The database of territory-wide medical records collected by the Hospital Authority of Hong Kong was used to identify inpatients who have survived the first-ever self-poisoning but died by suicide between January 1, 2001, and December 31, 2010. A self-controlled case series ("SCCS") design controlling for time-invariant patient confounders was used to explore the temporal change in suicide risk after the first self-poisoning episode. RESULTS: During the study period, 227 people in the database died from suicide after surviving one episode of self-poisoning. A significant increase of the risk of suicide in the first 12 months after the first lifetime self-poisoning-Risk Ratio ("RR") 2.88 (95% CI 1.74-4.76)-was detected. The RR gradually returned to baseline levels after the second post-poisoning period. CONCLUSION: By within-person comparison, the net increase of the suicide risk caused by the first self-poisoning was quantitatively modeled, demonstrating that the first lifetime self-poisoning event itself is a modifiable risk factor of subsequent suicide death.

The impact of non-pharmaceutical interventions on the prevention and control of COVID-19 in New York City.

The emergence of coronavirus disease 2019 (COVID-19) has infected more than 62 million people worldwide. Control responses varied across countries with different outcomes in terms of epidemic size and social disruption. This study presents an age-specific susceptible-exposed-infected-recovery-death model that considers the unique characteristics of COVID-19 to examine the effectiveness of various non-pharmaceutical interventions (NPIs) in New York City (NYC). Numerical experiments from our model show that the control policies implemented in NYC reduced the number of infections by 72% [interquartile range (IQR) 53-95] and the number of deceased cases by 76% (IQR 58-96) by the end of 2020. Among all the NPIs, social distancing for the entire population and protection for the elderly in public facilities is the most effective control measure in reducing severe infections and deceased cases. School closure policy may not work as effectively as one might expect in terms of reducing the number of deceased cases. Our simulation results provide novel insights into the city-specific implementation of NPIs with minimal social disruption considering the locations and population characteristics.

Understanding the Association Between Antidepressants and the Risk of Being Diagnosed with Dementia in Older People: A Self-Controlled Case Series Study.

BACKGROUND: Given concerns about adverse outcomes for older people taking antidepressants in the literature, we investigated whether taking antidepressants elevates the risk of dementia. OBJECTIVE: This study aims to investigate the putative association of antidepressants with the risk of dementia. METHODS: We conducted a population-based self-controlled case series analysis of older people with dementia and taking antidepressants, using territory-wide medical records of 194,507 older patients collected by the Hospital Authority of Hong Kong, to investigate the association between antidepressant treatment and the risk of developing dementia in older people. RESULTS: There was a significantly higher risk of being diagnosed with dementia during the pre-drug-exposed period (incidence rate ratio (IRR) 20.42 (95% CI: 18.66-22.34)) compared to the non-drug-exposed baseline period. The IRR remained high during the drug-exposed period (IRR 8.86 (7.80-10.06)) before returning to a baseline level after washout (IRR 1.12 (0.77-1.36)). CONCLUSION: The higher risk of dementia before antidepressant treatment may be related to emerging psychiatric symptoms co-occurring with dementia, which trigger medical consultations that result in a decision to begin antidepressants. Our findings do not support a causal relationship between antidepressant treatment and the risk of dementia.

Preferential catalytic ozonation of p-nitrophenol by molecularly imprinted Fe3O4/SiO2 core-shell magnetic composites.

Molecularly imprinted Fe(3)O(4)/SiO(2) core-shell magnetic composites (Fe(3)O(4)/SiO(2)-MIP) were successfully prepared via anchoring p-nitrophenol (p-NP) imprinted functional polymers on the surface of amino-modified Fe(3)O(4)/SiO(2) core-shell particles. Synthesized magnetic Fe(3)O(4)/SiO(2)-MIP composites were characterized by X-ray diffraction, scanning electronic microscopy, transmission electron microscopy, Fourier transform infrared spectroscopy, and magnetic property measurement. The preferential catalytic ozonation of p-nitrophenol was evaluated in comparison with the competitive reaction in the presence of coexistent phenol. The results showed that the prepared Fe(3)O(4)/SiO(2)-MIP composites exhibit strong adsorption ability due to the strong bonding between p-NP and the molecularly imprinted layer. The Fe(3)O(4)/SiO(2)-MIP demonstrated a preferential catalytic ozonation of p-NP by the recognition ability of the molecularly imprinted layer to the target p-NP. The enhanced catalytic activity using Fe(3)O(4)/SiO(2)-MIP composites could be attributed to the excellent recognition absorption of the MIP layer on the surface of Fe(3)O(4)/SiO(2)-MIP to p-NP.

T-2 toxin is hydroxylated by chicken CYP3A37.

T-2 toxin (T-2) is an acute toxic trichothecene mycotoxin produced mainly by Fusarium species, detected in many crops including oats, wheat and barley, in animal feed and food. It is important to know the metabolic pathway and kinetics of T-2 in food animals given that T-2 can cause serious adverse effects on human health. In this study, we investigated the metabolic capacity of chicken CYP3A37 in the metabolism of T-2 using reconstituted bacteria produced enzymes. Our results showed that chicken CYP3A37 is able to convert T-2 to 3'-OH T-2 with an apparent Km of 15.29 µM, and T-2 hydroxylation activity of CYP3A37 is strongly inhibited by ketoconazole (IC50=0.11 µM). We also observed that chicken CYP3A37 can catalyze erythromycin N-demethylation, another CYP3A-specific activity. These findings imply that chicken CYP3A37 may have a broad substrate spectrum, similar to its human homologue CYP3A4.

Hydroxylation of quinocetone and carbadox is mediated by CYP1As in the chicken (Gallus gallus).

Quinoxaline derivatives (quinoxalines) comprise a class of drugs that have been widely used as animal antimicrobial agents and feed additives. Although the metabolism of quinoxaline drugs has been mostly studied using chicken liver microsomes, the biochemical mechanism of biotransformation of these chemicals in the chicken has yet to be characterized. In this study, using bacteria produced enzymes, we demonstrated that both CYP1A4 and CYP1A5 participate in the oxidative metabolism of quinoxalines. For CYP1A5, three hydroxylated metabolites of quinocetone were generated. In addition, CYP1A5 is able to hydroxylate carbadox. For CYP1A4, only one hydroxylated product of quinocetone on the phenyl ring was identified. Neither CYP1A5 nor CYP1A4 showed hydroxylation activity towards mequindox and cyadox. Our results suggest that CYP1A4 and CYP1A5 have different and somewhat overlapping substrate specificity in quinoxaline metabolism, and CYP1A5 represents a crucial enzyme in hydroxylation of both quinocetone and carbadox.

Separation and determination of degradation products of acid orange 7 by capillary electrophoresis/capacitively coupled contactless conductivity detector.

Capillary electrophoresis (CE) with capacitively coupled contactless conductivity detector (C(4)D) was developed to separate azo-dyestuff acid orange 7 (AO7) and its six degradation products. The analyzed products were sulfamic acid, oxalic acid, benzenesulfonic acid, 4-hydroxybenzene sulfonic acid, phthalic acid, and 4-aminobenzene sulfonic acid. In developing the method, types and concentrations of running buffers, injecting voltage and time, and applied voltage were tested to obtain optimum conditions to analyze target compounds. The separation was successfully achieved within 10 min using a fused-silica capillary under the following conditions: 20 mmol L(-1) acetate acid buffer, electrokinetic injection of -12 kV × 10 s, and applied voltage of -13 kV. The developed method was applied to analyze degradation products in situ during the reaction of AO7 with Fenton reagent (Fe(II)+H2O2 at pH 4.0).

Characterization of chicken cytochrome P450 1A4 and 1A5: inter-paralog comparisons of substrate preference and inhibitor selectivity.

The chicken (Gallus gallus) is one of the most economically important domestic animals and also an avian model species. Chickens have two CYP1A genes (CYP1A4 and CYP1A5) which are orthologous to mammalian CYP1A1 and CYP1A2. Although the importance of chicken CYP1As in metabolism of endogenous compounds and xenobiotics is well recognized, their enzymatic properties, substrate preference and inhibitor selectivity remain poorly understood. In this study, functional enzymes of chicken CYP1A4 and CYP1A5 were successfully produced in Escherichia coli (E. coli). The substrate preference and inhibitor specificity of the two chicken CYP1As were compared. Kinetic results showed that the enzymatic parameters (K(m), V(max), V(max)/K(m)) for ethoxyresorufin O-deethylase (EROD) and benzyloxyresorufin O-debenzylase (BROD) differed between CYP1A4 and CYP1A5, while no significant difference was observed for methoxyresorufin O-demethylase (MROD). Lower K(m) of CYP1A4 for BROD suggests that CYP1A4 has a greater binding affinity to benzyloxyresorufin than either ethoxyresorufin or methoxyresorufin. The highest V(max)/K(m) ratio was seen in BROD activity for CYP1A4 and in MROD for CYP1A5 respectively. These results indicate that substrate preference of chicken CYP1As is more notably distinguished by BROD activity and CYP1A5 prefers shorter alkoxyresorufins resembling its mammalian ortholog CYP1A2. Differential patterns of MROD inhibition were observed between CYP1As and among the five CYP inhibitors (α-naphthoflavone, furafylline, piperonyl butoxide, erythromycin and ketoconazole). α-Naphthoflavone was determined to be a potent MROD inhibitor of both CYP1A4 and CYP1A5. In contrast, no or only a trace inhibitory effect (<15%) was observed by erythromycin at a concentration of 500 µM. Stronger inhibition of MROD activity was found in CYP1A5 than CYP1A4 by relatively small molecules α-naphthoflavone, piperonyl butoxide and furafylline. AROD kinetics and inhibition profiles between chicken CYP1A4 and CYP1A5 demonstrate that the two paralogous members of the CYP1A subfamily have distinct enzymatic properties, reflecting differences in the active site geometry between CYP1A4 and CYP1A5. These findings suggest that CYP1A4 and CYP1A5 play partially overlapping but distinctly different physiological and toxicological roles in the chicken.

Disease-causing mutation in PKR2 receptor reveals a critical role of positive charges in the second intracellular loop for G-protein coupling and receptor trafficking.

Prokineticins are a pair of signal factors involved in many physiological processes by binding to two closely related G-protein-coupled receptors, PKR1 and PKR2. Recently, mutations in prokineticin 2 (PK2) and PKR2 are found to be associated with Kallmann syndrome and/or idiopathic hypogonadotropic hypogonadism, disorders characterized by delayed puberty and infertility. However, little is known how PKRs interact and activate G-proteins to elicit signal transduction. In the present study, we took advantage of one disease-associated mutation (R164Q) located in the second intracellular (IL2) loop of PKR2, to investigate the role of IL2 loop in the cell signaling, G-protein binding and receptor trafficking. R164Q mutant PKR2 showed normal cell surface expression and ligand binding capacity. However, the PKR2 signaling was abolished by R164Q mutation. We demonstrated that R164Q mutation disrupted the interaction of IL2 loop to the Gα(q), Gα(i), and Gα(16)-proteins. A positive-charged amino acid at this position is required for proper function, and the signaling efficacy and potency depend on the net amount of positive charges. We also demonstrated that the interactive partner of Arg-164 may localize in the C-terminal five residues of Gα(q)-protein. A series of mutation analysis indicated that the basic amino acids at the C terminus of IL2 loop may function cooperatively in GPCRs. Furthermore, R164Q mutation also results in minimal ligand-induced endocytosis of PKR2. As many GPCRs share structural homology in the C terminus of IL2 loop, our findings may have general application in understanding structure and function of GPCRs.

[Determination of Na, K and Ca in brains of less white mouse by AAS].

Sodium, potassium and calcium in brain of less white mouse were determined using an atomic absorption spectrometry. The sodium was atomized by air-town-gas flame, and the potassium and calcium were atomized by air-acetylene flame. The brains took from 46 less white mice which came from 4 sets of contrast samples. The brain (0.05-0.1 g) after drying up was digested by a nitric-perchloric acid system. The interference effect of phosphor in the brain on the calcium was overcome by adding in lanthanum chloride. Sodium and potassium in the brain itself were used as deionization agents for determining calcium. Cesium chloride was used as the deionization agent for determining sodium and potassium. The experimental results showed that the RSD (n = 6) was 0.886% for sodium, 0.691% for potassium and 0.824% for calcium, and the addition standard recovery (ASR) (n = 3) was 97.5%-102.4% for sodium, 100.3%-104.0% for potassium and 96.0%-103.2% for calcium, respectively.