TexSe1-x Shortwave Infrared Photodiode Arrays with Monolithic Integration.

TexSe1-x shortwave infrared (SWIR) photodetectors show promise for monolithic integration with readout integrated circuits (ROIC), making it a potential alternative to conventional expensive SWIR photodetectors. However, challenges such as a high dark current density and insufficient detection performance hinder their application in large-scale monolithic integration. Herein, we develop a ZnO/TexSe1-x heterojunction photodiode and synergistically address the interfacial elemental diffusion and dangling bonds via inserting a well-selected 0.3 nm amorphous TeO2 interfacial layer. The optimized device achieves a reduced dark current density of -3.5 × 10-5 A cm-2 at -10 mV, a broad response from 300 to 1700 nm, a room-temperature detectivity exceeding 2.03 × 1011 Jones, and a 3 dB bandwidth of 173 kHz. Furthermore, for the first time, we monolithically integrate the TexSe1-x photodiodes on ROIC (64 × 64 pixels) with the largest-scale array among all TexSe1-x-based detectors. Finally, we demonstrate its applications in transmission imaging and substance identification.

PMMA-induced biofilm promotes Schwann cells migration and proliferation mediated by EGF/Tnc/FN1 to improve sciatic nerve defect.

Objective: The purpose of this study is to investigate the role of PMMA-induced biofilm in nerve regeneration compared with silicone-induced biofilm involved in the mechanism. Methods: PMMA or silicon rods were placed next to the sciatic nerve to induce a biological membrane which was assayed by PCR, Western blot, immunohistochemistry, immunofluorescence and proteomics. A 10 mm sciatic nerve gaps were repaired with the autologous nerve wrapped in an induced biological membrane. The repair effects were observed through general observation, functional evaluation of nerve regeneration, ultrasound examination, neural electrophysiology, the wet weight ratio of bilateral pretibial muscle and histological evaluation. Cell proliferation and migration of Schwann cells co-cultured with EGF-treated fibroblasts combined with siRNA were investigated. Results: The results indicated that expression of GDNF, NGF and VEGF along with neovascularization was similar in the silicone and PMMA group and as the highest at 6 weeks after operation. Nerve injury repair mediated by toluidine blue and S100ß/NF200 expression, the sensory and motor function evaluation, ultrasound, target organ muscle wet-weight ratio, percentage of collagen fiber, electromyography and histochemical staining were not different between the two groups and better than blank group. EGF-treated fibroblasts promoted proliferation and migration may be Tnc expression dependently. Conclusion: Our study suggested that PMMA similar to silicon induced biofilm may promote autogenous nerve transplantation to repair nerve defects through EGF/Tnc/FN1 to increase Schwann cells proliferation and migration.

Quercetin alleviates difenoconazole-induced growth inhibition in carp through intestinal-brain axis.

Difenoconazole (DIF) is frequently used for the management of fungal infections in fruit and vegetables and excessive residues in the aquatic environment can have adverse effects on fish such as growth inhibition. A treatment based on the dietary additive quercetin (QUE) is a promising approach to positively regulate the state of fish growth. This study focused on whether and how QUE alleviated DIF-induced growth inhibition in fish. In this study, carp were exposed to DIF (0.3906 mg/L) for consecutive 30 d, which showed growth inhibition. Disruption of the intestinal barrier led to elevated levels of intestinal lipopolysaccharide (LPS) and an inflammatory response. Through the intestinal-brain axis, LPS entered the brain where it disrupted the blood-brain barrier, triggered neuroinflammation, caused brain cell apoptosis, and damaged nerves in addition to other things. The dietary supplementation of QUE (400 mg/kg) reduced the levels of LPS in the intestinal and brain, while reducing inflammation and increasing the expression of appetite factors, thereby reducing growth inhibition in carp. This work provided evidence for QUE from the intestinal-brain axis perspective as a potential candidate for alleviating growth inhibition in fish.

m6A-modified cenRNA stabilizes CENPA to ensure centromere integrity in cancer cells.

m6A modification is best known for its critical role in controlling multiple post-transcriptional processes of the mRNAs. Here, we discovered elevated levels of m6A modification on centromeric RNA (cenRNA) in cancerous cells compared with non-cancerous cells. We then identified CENPA, an H3 variant, as an m6A reader of cenRNA. CENPA is localized at centromeres and is essential in preserving centromere integrity and function during mitosis. The m6A-modified cenRNA stabilizes centromeric localization of CENPA in cancer cells during the S phase of the cell cycle. Mutations of CENPA at the Leu61 and the Arg63 or removal of cenRNA m6A modification lead to loss of centromere-bound CENPA during S phase. This in turn results in compromised centromere integrity and abnormal chromosome separation and hinders cancer cell proliferation and tumor growth. Our findings unveil an m6A reading mechanism by CENPA that epigenetically governs centromere integrity in cancer cells, providing potential targets for cancer therapy.

Emerging roles of the C-to-U RNA editing in plant stress responses.

RNA editing is an important post-transcriptional event in all living cells. Within chloroplasts and mitochondria of higher plants, RNA editing involves the deamination of specific cytosine (C) residues in precursor RNAs to uracil (U). An increasing number of recent studies detail specificity of C-to-U RNA editing as an essential prerequisite for several plant stress-related responses. In this review, we summarize the current understanding of responses and functions of C-to-U RNA editing in plants under various stress conditions to provide theoretical reference for future research.

Ultrasound-guided joystick technique for percutaneous leverage reduction with Kirschner wires and external fixator in pediatric proximal humerus fractures: A clinical outcome study.

OBJECTIVE: This study aims to evaluate the clinical application efficacy of the ultrasound-guided Joystick technique for percutaneous leverage reduction in conjunction with Kirschner wires and external fixator in the treatment of difficult-to-reduce pediatric Salter-Harris II type proximal humerus fractures. METHODS: A retrospective analysis was conducted on children with Salter-Harris II type proximal humerus fractures, who failed manual closed reduction from January 2018 to March 2022. The group consisted of 7 males and 2 females, aged between 10 and 14 years. The surgical method involved percutaneous leverage reduction using the ultrasound-guided Joystick technique, combined with Kirschner wires and external fixation. Throughout the procedure, ultrasound is used for monitoring, with the fracture condition being determined before surgery. An external support screw is inserted into the distal end of the humerus as an operating lever, along with 3.5 mm Kirschner wire for ultrasound-guided reduction and maintenance of position during the operation. Following fixation with Kirschner wire, a combination external fixator is applied. After fixation is completed, ultrasound is used once more to assess the quality of fracture reduction, followed by verification of the reduction status using a C-arm X-ray machine. RESULTS: All surgeries were successfully completed with a 100 % success rate in resetting. Notably, there were no postoperative complications like nerve or vascular injury, malunion, nonunion, or bone bridge formation in the proximal humeral physis. Three cases experienced minor complications (redness and swelling at the screw sites), which improved with conservative management. The follow-up period ranged from 6 to 18 months, averaging 10.6 months, with fracture clinical healing occurring within 6 to 8 weeks (average 6.3 weeks). The final follow-up revealed excellent functional outcomes, with Neer scores ranging from 90 to 100 (average 96.3 points). CONCLUSION: The ultrasound-guided Joystick technique for percutaneous leverage reduction in conjunction with Kirschner wires and external fixator can effectively treat difficult-to-reduce Salter-Harris II proximal humeral fractures in children, avoiding open reduction and minimizing intraoperative radiation exposure. This approach offers good stability and facilitates early rehabilitation, aligning with the ERAS (Enhanced Recovery After Surgery) concept in fracture management, thus warranting clinical promotion.

Alloy Reconstruction in Pyrolytic Bowknot-like Heteronuclear CoFe Clusters for Electrocatalytic Application.

The construction of doped molecular clusters is an intriguing way to perform bimetallic doping for electrocatalysts. However, efficiently harnessing the benefits of a doping strategy and alloy engineering to create a nanostructure for electrocatalytic application at the molecular level has consistently posed a challenge. Here we propose an in situ reconstruction strategy aimed at producing an alloy nanostructure through a pyrolysis process, originating from bowknot-like heterometallic clusters. The Schiff base, denoted as ligand L1 (o-vanillin ethylenediamine), was introduced as a precursor to coordinate Fe and Co metals, thereby yielding a heteronuclear metal cluster [(FeCo)(L1)2O]CH3CN. Subsequently, a comprehensive investigation of the in situ reconstruction process [(FeCo)(L1)2O](CH3CN) → [(FeCo)(L1)2O] → [M-O-M/M-O] [CH3+/CH3O+/H2C═N/C2H5+/C4H4+] → [FeCo/Fe3O4/Fe2O3/Co3O4][carbon layer] led to the formation of MOx/CoFe@NC-700 during the pyrolysis. This process reveals that the metals Fe and Co in the clusters undergo partly in situ evolution into FeCo alloys, resulting in the successful preparation of MOx/CoFe@NC (M = Fe, Co) nanomaterials that leverage the advantages of both doping strategies and alloy engineering. The synergistic interaction between alloy particles and metal oxides establishes active sites that contribute to the excellent oxygen evolution (OER) and hydrogen evolution (HER) catalytic behaviors. Notably, these materials exhibit outstanding OER and HER properties under alkaline conditions, with overpotentials of 191 and 88 mV for OER and HER, respectively, at 10 mA cm-2. Investigation of the in situ conversion of Schiff base bimetal clusters into alloy materials through pyrolysis offers a novel strategy for advancing electrocatalytic applications.

Dual-Locked Enzyme-Activatable Bioorthogonal Fluorescence Turn-On Imaging of Senescent Cancer Cells.

Bioorthogonal pretargeting optical imaging shows the potential for enhanced diagnosis and prognosis. However, the bioorthogonal handles, known for being "always reactive", may engage in reactions at unintended sites with their counterparts, resulting in nonspecific fluorescence activation and diminishing detection specificity. Meanwhile, despite the importance of detecting senescent cancer cells in cancer therapy, current methods mainly rely on common single senescence-associated biomarkers, which lack specificity for differentiating between various types of senescent cells. Herein, we report a dual-locked enzyme-activatable bioorthogonal fluorescence (DEBOF) turn-on imaging approach for the specific detection of senescent cancer cells. A dual-locked bioorthogonal targeting agent (DBTA) and a bioorthogonally activatable fluorescent imaging probe (BAP) are synthesized as the biorthogonal pair. DBTA is a tetrazine derivative dually caged by two enzyme-cleavable moieties, respectively, associated with senescence and cancer, which ensures that its bioorthogonal reactivity ("clickability") is only triggered in the presence of senescent cancer cells. BAP is a fluorophore caged by trans-cyclooctane (TCO), whose fluorescence is only activated upon bioorthogonal reaction between its TCO and the decaged tetrazine of DBTA. As such, the DEBOF imaging approach differentiates senescent cancer cells from nonsenescent cancer cells or other senescent cells, allowing noninvasive tracking of the population fluctuation of senescent cancer cells in the tumor of living mice to guide cancer therapies. This study thus provides a general molecular strategy for biomarker-activatable in vivo bioorthogonal pretargeting imaging with the potential to be applied to other imaging modalities beyond optics.

Fluorescent and colorimetric dual-mode detection of Cu2+ based on carbon dots.

A fluorescent and colorimetric dual-mode strategy based on carbon dots (CDs) was rationally designed for sensitive determination of Cu2+. Green fluorescent CDs with high absolute quantum yield of 72.9% were synthesized by facile one-step hydrothermal treatment of triethylenetetramine and Rose Bengal. Cu2+ could trigger the oxidative and chromogenic reaction of p-phenylenediamine (PPD) to generate chromogenic PPDox, accompanied by the fluorescence quenching of the CDs. The quenching mechanism was identified as the inner filter effect between PPDox and CDs. Therefore, a colorimetric/fluorescent dual-mode detection method for Cu2+ recognition was constructed. The limits of detection for Cu2+ were 4.14 µM and 1.28 µM for colorimetric and fluorescent mode, respectively. In addition, this method had achieved satisfactory results in the detection of Cu2+ in real serum samples.

The mechanisms underlying acute myocardial infarction in chronic kidney disease patients undergoing hemodialysis.

Cardiovascular disease (CVD) is a leading cause of death in chronic kidney disease (CKD). Hemodialysis is one of the main treatments for patients with end-stage kidney disease. Epidemiological data has shown that acute myocardial infarction (AMI) accounts for the main reason for death in patients with CKD under hemodialysis therapy. Immune dysfunction and changes in metabolism (including a high level of inflammatory cytokines, a disorder of lipid and mineral ion homeostasis, accumulation of uremic toxins et al.) during CKD can deteriorate stability of atherosclerotic plaque and promote vascular calcification, which are exactly the pathophysiological mechanisms underlying the occurrence of AMI. Meanwhile, the hemodialysis itself also has adverse effects on lipoprotein, the immune system and hemodynamics, which contribute to the high incidence of AMI in these patients. This review aims to summarize the mechanisms and further promising methods of prevention and treatment of AMI in CKD patients undergoing hemodialysis, which can provide an excellent paradigm for exploring the crosstalk between the kidney and cardiovascular system.

Cell-free DNA: a promising biomarker in infectious diseases.

Infectious diseases pose serious threats to public health worldwide. Conventional diagnostic methods for infectious diseases often exhibit low sensitivity, invasiveness, and long turnaround times. User-friendly point-of-care tests are urgently needed for early diagnosis, treatment monitoring, and prognostic prediction of infectious diseases. Cell-free DNA (cfDNA), a promising non-invasive biomarker widely used in oncology and pregnancy, has shown great potential in clinical applications for diagnosing infectious diseases. Here, we discuss the most recent cfDNA research on infectious diseases from both the pathogen and host perspectives. We also discuss the technical challenges in this field and propose solutions to overcome them. Additionally, we provide an outlook on the potential of cfDNA as a diagnostic, treatment, and prognostic marker for infectious diseases.

Prediction of Human Liver Microsome Clearance with Chirality-Focused Graph Neural Networks.

In drug candidate design, clearance is one of the most crucial pharmacokinetic parameters to consider. Recent advancements in machine learning techniques coupled with the growing accumulation of drug data have paved the way for the construction of computational models to predict drug clearance. However, concerns persist regarding the reliability of data collected from public sources, and a majority of current in silico quantitative structure-property relationship models tend to neglect the influence of molecular chirality. In this study, we meticulously examined human liver microsome (HLM) data from public databases and constructed two distinct data sets with varying HLM data quantity and quality. Two baseline models (RF and DNN) and three chirality-focused GNNs (DMPNN, TetraDMPNN, and ChIRo) were proposed, and their performance on HLM data was evaluated and compared with each other. The TetraDMPNN model, which leverages chirality from 2D structure, exhibited the best performance with a test R2 of 0.639 and a test root-mean-squared error of 0.429. The applicability domain of the model was also defined by using a molecular similarity-based method. Our research indicates that graph neural networks capable of capturing molecular chirality have significant potential for practical application and can deliver superior performance.

New Strategies for Responding to SARS-CoV-2: The Present and Future of Dual-Target Drugs.

The 2019 coronavirus disease (COVID-19) pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has resulted in millions of deaths, posing a serious threat to public health and safety. Rapid mutations of SARS-CoV-2 and complex interactions among multiple targets during infection pose a risk of expiry for small molecule inhibitors. This suggests that the traditional concept of "one bug, one drug" could be ineffective in dealing with the coronavirus. The dual-target drug strategy is expected to be the key to ending coronavirus infections. However, the lack of design method and improper combination of dual-targets poses obstacle to the discovery of new dual-target drugs. In this Perspective, we summarized the profiles concerning drug design methods, structure-activity relationships, and pharmacological parameters of dual-target drugs for the treatment of COVID-19. Importantly, we underscored how target combination and rational drug design illuminate the development of dual-target drugs for SARS-CoV-2.

Leveraging Long-Distance Singlet-Oxygen Transfer for Bienzyme-Locked Afterglow Imaging of Intratumoral Granule Enzymes.

Dual-locked activatable optical probes, leveraging the orthogonal effects of two biomarkers, hold great promise for the specific imaging of biological processes. However, their design approaches are limited to a short-distance energy or charge transfer mechanism, while the signal readout relies on fluorescence, which inevitably suffers from tissue autofluorescence. Herein, we report a long-distance singlet oxygen transfer approach to develop a bienzyme-locked activatable afterglow probe (BAAP) that emits long-lasting self-luminescence without real-time light excitation for the dynamic imaging of an intratumoral granule enzyme. Composed of an immuno-biomarker-activatable singlet oxygen (1O2) donor and a cancer-biomarker-activatable 1O2 acceptor, BAAP is initially nonafterglow. Only in the presence of both immune and cancer biomarkers can 1O2 be generated by the activated donor and subsequently diffuse toward the activated acceptor, resulting in bright near-infrared afterglow with a high signal-to-background ratio and specificity toward an intratumoral granule enzyme. Thus, BAAP allows for real-time tracking of tumor-infiltrating cytotoxic T lymphocytes, enabling the evaluation of cancer immunotherapy and the differentiation of tumor from local inflammation with superb sensitivity and specificity, which are unachievable by single-locked probes. Thus, this study not only presents the first dual-locked afterglow probe but also proposes a new design way toward dual-locked probes via reactive oxygen species transfer processes.

Beaconet: A Reference-Free Method for Integrating Multiple Batches of Single-Cell Transcriptomic Data in Original Molecular Space.

Integrating multiple single-cell datasets is essential for the comprehensive understanding of cell heterogeneity. Batch effect is the undesired systematic variations among technologies or experimental laboratories that distort biological signals and hinder the integration of single-cell datasets. However, existing methods typically rely on a selected dataset as a reference, leading to inconsistent integration performance using different references, or embed cells into uninterpretable low-dimensional feature space. To overcome these limitations, a reference-free method, Beaconet, for integrating multiple single-cell transcriptomic datasets in original molecular space by aligning the global distribution of each batch using an adversarial correction network is presented. Through extensive comparisons with 13 state-of-the-art methods, it is demonstrated that Beaconet can effectively remove batch effect while preserving biological variations and is superior to existing unsupervised methods using all possible references in overall performance. Furthermore, Beaconet performs integration in the original molecular feature space, enabling the characterization of cell types and downstream differential expression analysis directly using integrated data with gene-expression features. Additionally, when applying to large-scale atlas data integration, Beaconet shows notable advantages in both time- and space-efficiencies. In summary, Beaconet serves as an effective and efficient batch effect removal tool that can facilitate the integration of single-cell datasets in a reference-free and molecular feature-preserved mode.

Tab-Cox: An Interpretable Deep Survival Analysis Model for Patients With Nasopharyngeal Carcinoma Based on TabNet.

The nutritional status of cancer patients is closely associated with the clinical progression of the disease. A survival analysis model combined with a neural network can predict future disease trends in patients, facilitating early prevention and assisting physicians in making diagnoses. However, the complexity of neural networks and their incompatibility with medical tabular data can reduce the interpretability of the model. To address this issue, thr paper propose a novel survival analysis model called Tab-Cox, which combines TabNet and Cox models. This model is specifically designed to predict the survival outcomes of patients with nasopharyngeal carcinoma. The model utilizes TabNet's sequential attention mechanism to extract more interpretable features, providing an interpretable method for identifying disease risk factors. Consequently, the model ensures accurate survival prediction while also making the results more comprehensible for both patients and doctors. The paper tested the efficacy of the model by conducting experiments on various diverse datasets in comparison with other commonly used survival models. The results showed that the proposed model delivered the highest or second-highest accuracy across all datasets. Furthermore, the paper conducted a comparative interpretability analysis against the classical Cox model. In addition and compare the interpretability of the Tab-Cox model with the classical Cox model and discuss the advantages and disadvantages of its interpretability. This demonstrates that Tab-Cox can assist doctors in identifying risk factors that are challenging to capture using artificial methods.

[Application of three-dimensional ultrasound technique in repairing dorsal foot wounds with medial sural artery perforator flaps].

Objective: To investigate the accuracy of positioning perforator of medial sural artery with three-dimensional ultrasound technique guided by a wide band linear matrix array volume transducer probe before operation, and the effectiveness of the flap design based on this in repairing the dorsal foot wounds. Methods: Between January 2019 and December 2022, 30 patients with skin and soft tissue defects of the dorsal foot were treated. There were 19 males and 11 females, with an average age of 43.9 years (range, 22-63 years). There were 12 cases of traffic accident injury, 15 cases of heavy crushing injury, and 3 cases of machine injury. The time from injury to hospitalization was 1-8 hours (mean, 3.5 hours). The wounds in size of 5 cm×3 cm to 17 cm×5 cm were thorough debrided and covered with vacuum sealing drainage dressing. Then the wounds were repaired with the medial sural artery perforator flaps after no obvious infection observed. To obtain the complete three-dimensional image, the number and position of the medial sural artery perforator branches and the position of the main blood vessels in the muscle were detected and recorded by wide band linear matrix array volume transducer probe before operation. Suitable perforating branches were selected to design the flap and guide the flap incision on this basis. The size of the perforating flap ranged from 6 cm×4 cm to 18 cm×6 cm. The sensitivity and positive predictive value were calculated by comparing preoperative exploration with intraoperative observation of perforating branches, so as to evaluate the positioning accuracy of three-dimensional ultrasound technique. The donor sites were sutured directly in 25 cases and repaired with free skin grafting in 5 cases. Results: The 60 perforating branches of medial sural artery were found before operation and 58 during operation in 30 patients. Among them, pre- and intra-operative perforations were consistent with 56. The sensitivity was 93.3% and positive predictive value was 96.6%. The intramuscular position and route of the main blood vessels were basically consistent with the pre- and intra-operative observation. All flaps survived and wounds healed by first intention. All incisions at the donor sites healed by first intention, and all skin grafts survived. All patients were follow up 9-24 months (mean, 14.7 months). The appearance, color, and texture of the flaps were good, and no obvious effect on wearing shoes and walking. At last follow-up, the American Orthopaedic Foot and Ankle Society (AOFAS) ankle-hind score ranged from 80 to 92, with an average of 87.5. The patient satisfaction was excellent in 29 cases and good in 1 case. Conclusion: The three-dimensional ultrasound technique guided by the wide band linear matrix array volume transducer probe can accurately locate the perforating branch of the medial sural artery, and the three-dimensional imaging is more intuitive, which can be used to guide the design and incision of the medial sural artery perforator flap.

One-Dimensional Crystal-Structure Te-Se Alloy for Flexible Shortwave Infrared Photodetector and Imaging.

Flexible shortwave infrared detectors play a crucial role in wearable devices, bioimaging, automatic control, etc. Commercial shortwave infrared detectors face challenges in achieving flexibility due to the high fabrication temperature and rigid material properties. Herein, we develop a high-performance flexible Te0.7Se0.3 photodetector, resulting from the unique 1D crystal structure and small elastic modulus of Te-Se alloying. The flexible photodetector exhibits a broad-spectrum response ranging from 365 to 1650 nm, a fast response time of 6 µs, a broad linear dynamic range of 76 dB, and a specific detectivity of 4.8 × 1010 Jones at room temperature. The responsivity of the flexible detector remains at 93% of its initial value after bending with a small curvature of 3 mm. Based on the optimized flexible detector, we demonstrate its application in shortwave infrared imaging. These results showcase the great potential of Te0.7Se0.3 photodetectors for flexible electronics.

Bienzyme-Locked Activatable Fluorescent Probes for Specific Imaging of Tumor-Associated Mast Cells.

Tumor-associated mast cells (TAMCs) have been recently revealed to play a multifaceted role in the tumor microenvironment. Noninvasive optical imaging of TAMCs is thus highly desired to gain insights into their functions in cancer immunotherapy. However, due to the lack of a single enzyme that is specific to mast cells, a common probe design approach based on single-enzyme activation is not applicable. Herein, we reported a bienzyme-locked molecular probe (THCMC) based on a photoinduced electron transfer-intramolecular charge-transfer hybrid strategy for in vivo imaging of TAMCs. The bienzyme-locked activation mechanism ensures that THCMC exclusively turns on near-infrared (NIR) fluorescence only in the presence of both tryptase and chymase specifically coexpressed by mast cells. Thus, THCMC effectively distinguishes mast cells from other leukocytes, including T cells, neutrophils, and macrophages, a capability lacking in single-locked probes. Such a high specificity of THCMC allows noninvasive tracking of the fluctuation of TAMCs in the tumor of living mice during cancer immunotherapy. The results reveal that the decreased intratumoral signal of THCMC after combination immunotherapy correlates well with the reduced population of TAMCs, accurately predicting the inhibition of tumor growth. Thus, this study not only presents the first NIR fluorescent probe specific for TAMCs but also proposes a generic bienzyme-locked probe design approach for in vivo cell imaging.

Development and external validation of a dynamic risk score for early prediction of cardiogenic shock in cardiac intensive care units using machine learning.

AIMS: Myocardial infarction and heart failure are major cardiovascular diseases that affect millions of people in the USA with morbidity and mortality being highest among patients who develop cardiogenic shock. Early recognition of cardiogenic shock allows prompt implementation of treatment measures. Our objective is to develop a new dynamic risk score, called CShock, to improve early detection of cardiogenic shock in the cardiac intensive care unit (ICU). METHODS AND RESULTS: We developed and externally validated a deep learning-based risk stratification tool, called CShock, for patients admitted into the cardiac ICU with acute decompensated heart failure and/or myocardial infarction to predict the onset of cardiogenic shock. We prepared a cardiac ICU dataset using the Medical Information Mart for Intensive Care-III database by annotating with physician-adjudicated outcomes. This dataset which consisted of 1500 patients with 204 having cardiogenic/mixed shock was then used to train CShock. The features used to train the model for CShock included patient demographics, cardiac ICU admission diagnoses, routinely measured laboratory values and vital signs, and relevant features manually extracted from echocardiogram and left heart catheterization reports. We externally validated the risk model on the New York University (NYU) Langone Health cardiac ICU database which was also annotated with physician-adjudicated outcomes. The external validation cohort consisted of 131 patients with 25 patients experiencing cardiogenic/mixed shock. CShock achieved an area under the receiver operator characteristic curve (AUROC) of 0.821 (95% CI 0.792-0.850). CShock was externally validated in the more contemporary NYU cohort and achieved an AUROC of 0.800 (95% CI 0.717-0.884), demonstrating its generalizability in other cardiac ICUs. Having an elevated heart rate is most predictive of cardiogenic shock development based on Shapley values. The other top 10 predictors are having an admission diagnosis of myocardial infarction with ST-segment elevation, having an admission diagnosis of acute decompensated heart failure, Braden Scale, Glasgow Coma Scale, blood urea nitrogen, systolic blood pressure, serum chloride, serum sodium, and arterial blood pH. CONCLUSION: The novel CShock score has the potential to provide automated detection and early warning for cardiogenic shock and improve the outcomes for millions of patients who suffer from myocardial infarction and heart failure.