Anatomically and Functionally Distinct Lung Mesenchymal Populations Marked by Lgr5 and Lgr6.

The diversity of mesenchymal cell types in the lung that influence epithelial homeostasis and regeneration is poorly defined. We used genetic lineage tracing, single-cell RNA sequencing, and organoid culture approaches to show that Lgr5 and Lgr6, well-known markers of stem cells in epithelial tissues, are markers of mesenchymal cells in the adult lung. Lgr6+ cells comprise a subpopulation of smooth muscle cells surrounding airway epithelia and promote airway differentiation of epithelial progenitors via Wnt-Fgf10 cooperation. Genetic ablation of Lgr6+ cells impairs airway injury repair in vivo. Distinct Lgr5+ cells are located in alveolar compartments and are sufficient to promote alveolar differentiation of epithelial progenitors through Wnt activation. Modulating Wnt activity altered differentiation outcomes specified by mesenchymal cells. This identification of region- and lineage-specific crosstalk between epithelium and their neighboring mesenchymal partners provides new understanding of how different cell types are maintained in the adult lung.

Lung stem cell differentiation in mice directed by endothelial cells via a BMP4-NFATc1-thrombospondin-1 axis.

Lung stem cells are instructed to produce lineage-specific progeny through unknown factors in their microenvironment. We used clonal 3D cocultures of endothelial cells and distal lung stem cells, bronchioalveolar stem cells (BASCs), to probe the instructive mechanisms. Single BASCs had bronchiolar and alveolar differentiation potential in lung endothelial cell cocultures. Gain- and loss-of-function experiments showed that BMP4-Bmpr1a signaling triggers calcineurin/NFATc1-dependent expression of thrombospondin-1 (Tsp1) in lung endothelial cells to drive alveolar lineage-specific BASC differentiation. Tsp1 null mice exhibited defective alveolar injury repair, confirming a crucial role for the BMP4-NFATc1-TSP1 axis in lung epithelial differentiation and regeneration in vivo. Discovery of this pathway points to methods to direct the derivation of specific lung epithelial lineages from multipotent cells. These findings elucidate a pathway that may be a critical target in lung diseases and provide tools to understand the mechanisms of respiratory diseases at the single-cell level.

Altered TMPRSS2 usage by SARS-CoV-2 Omicron impacts infectivity and fusogenicity.

The SARS-CoV-2 Omicron BA.1 variant emerged in 20211 and has multiple mutations in its spike protein2. Here we show that the spike protein of Omicron has a higher affinity for ACE2 compared with Delta, and a marked change in its antigenicity increases Omicron's evasion of therapeutic monoclonal and vaccine-elicited polyclonal neutralizing antibodies after two doses. mRNA vaccination as a third vaccine dose rescues and broadens neutralization. Importantly, the antiviral drugs remdesivir and molnupiravir retain efficacy against Omicron BA.1. Replication was similar for Omicron and Delta virus isolates in human nasal epithelial cultures. However, in lung cells and gut cells, Omicron demonstrated lower replication. Omicron spike protein was less efficiently cleaved compared with Delta. The differences in replication were mapped to the entry efficiency of the virus on the basis of spike-pseudotyped virus assays. The defect in entry of Omicron pseudotyped virus to specific cell types effectively correlated with higher cellular RNA expression of TMPRSS2, and deletion of TMPRSS2 affected Delta entry to a greater extent than Omicron. Furthermore, drug inhibitors targeting specific entry pathways3 demonstrated that the Omicron spike inefficiently uses the cellular protease TMPRSS2, which promotes cell entry through plasma membrane fusion, with greater dependency on cell entry through the endocytic pathway. Consistent with suboptimal S1/S2 cleavage and inability to use TMPRSS2, syncytium formation by the Omicron spike was substantially impaired compared with the Delta spike. The less efficient spike cleavage of Omicron at S1/S2 is associated with a shift in cellular tropism away from TMPRSS2-expressing cells, with implications for altered pathogenesis.

Tracing oncogene-driven remodelling of the intestinal stem cell niche.

Interactions between tumour cells and the surrounding microenvironment contribute to tumour progression, metastasis and recurrence1-3. Although mosaic analyses in Drosophila have advanced our understanding of such interactions4,5, it has been difficult to engineer parallel approaches in vertebrates. Here we present an oncogene-associated, multicolour reporter mouse model-the Red2Onco system-that allows differential tracing of mutant and wild-type cells in the same tissue. By applying this system to the small intestine, we show that oncogene-expressing mutant crypts alter the cellular organization of neighbouring wild-type crypts, thereby driving accelerated clonal drift. Crypts that express oncogenic KRAS or PI3K secrete BMP ligands that suppress local stem cell activity, while changes in PDGFRloCD81+ stromal cells induced by crypts with oncogenic PI3K alter the WNT signalling environment. Together, these results show how oncogene-driven paracrine remodelling creates a niche environment that is detrimental to the maintenance of wild-type tissue, promoting field transformation dominated by oncogenic clones.

SARS-CoV-2 B.1.617.2 Delta variant replication and immune evasion.

The B.1.617.2 (Delta) variant of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) was first identified in the state of Maharashtra in late 2020 and spread throughout India, outcompeting pre-existing lineages including B.1.617.1 (Kappa) and B.1.1.7 (Alpha)1. In vitro, B.1.617.2 is sixfold less sensitive to serum neutralizing antibodies from recovered individuals, and eightfold less sensitive to vaccine-elicited antibodies, compared with wild-type Wuhan-1 bearing D614G. Serum neutralizing titres against B.1.617.2 were lower in ChAdOx1 vaccinees than in BNT162b2 vaccinees. B.1.617.2 spike pseudotyped viruses exhibited compromised sensitivity to monoclonal antibodies to the receptor-binding domain and the amino-terminal domain. B.1.617.2 demonstrated higher replication efficiency than B.1.1.7 in both airway organoid and human airway epithelial systems, associated with B.1.617.2 spike being in a predominantly cleaved state compared with B.1.1.7 spike. The B.1.617.2 spike protein was able to mediate highly efficient syncytium formation that was less sensitive to inhibition by neutralizing antibody, compared with that of wild-type spike. We also observed that B.1.617.2 had higher replication and spike-mediated entry than B.1.617.1, potentially explaining the B.1.617.2 dominance. In an analysis of more than 130 SARS-CoV-2-infected health care workers across three centres in India during a period of mixed lineage circulation, we observed reduced ChAdOx1 vaccine effectiveness against B.1.617.2 relative to non-B.1.617.2, with the caveat of possible residual confounding. Compromised vaccine efficacy against the highly fit and immune-evasive B.1.617.2 Delta variant warrants continued infection control measures in the post-vaccination era.

Airway secretory cell fate conversion via YAP-mTORC1-dependent essential amino acid metabolism.

Tissue homeostasis requires lineage fidelity of stem cells. Dysregulation of cell fate specification and differentiation leads to various diseases, yet the cellular and molecular mechanisms governing these processes remain elusive. We demonstrate that YAP/TAZ activation reprograms airway secretory cells, which subsequently lose their cellular identity and acquire squamous alveolar type 1 (AT1) fate in the lung. This cell fate conversion is mediated via distinctive transitional cell states of damage-associated transient progenitors (DATPs), recently shown to emerge during injury repair in mouse and human lungs. We further describe a YAP/TAZ signaling cascade to be integral for the fate conversion of secretory cells into AT1 fate, by modulating mTORC1/ATF4-mediated amino acid metabolism in vivo. Importantly, we observed aberrant activation of the YAP/TAZ-mTORC1-ATF4 axis in the altered airway epithelium of bronchiolitis obliterans syndrome, including substantial emergence of DATPs and AT1 cells with severe pulmonary fibrosis. Genetic and pharmacologic inhibition of mTORC1 activity suppresses lineage alteration and subepithelial fibrosis driven by YAP/TAZ activation, proposing a potential therapeutic target for human fibrotic lung diseases.

Author Correction: Metastatic-niche labelling reveals parenchymal cells with stem features.

An Amendment to this paper has been published and can be accessed via a link at the top of the paper.

Metastatic-niche labelling reveals parenchymal cells with stem features.

Direct investigation of the early cellular changes induced by metastatic cells within the surrounding tissue remains a challenge. Here we present a system in which metastatic cancer cells release a cell-penetrating fluorescent protein, which is taken up by neighbouring cells and enables spatial identification of the local metastatic cellular environment. Using this system, tissue cells with low representation in the metastatic niche can be identified and characterized within the bulk tissue. To highlight its potential, we applied this strategy to study the cellular environment of metastatic breast cancer cells in the lung. We report the presence of cancer-associated parenchymal cells, which exhibit stem-cell-like features, expression of lung progenitor markers, multi-lineage differentiation potential and self-renewal activity. In ex vivo assays, lung epithelial cells acquire a cancer-associated parenchymal-cell-like phenotype when co-cultured with cancer cells and support their growth. These results highlight the potential of this method as a platform for new discoveries.

Myth and Truth in Opioid Consumption with Intrathecal Morphine Pump Implantation in Chronic Pain: A Retrospective Cohort Study with Claims Database in South Korea.

OBJECTIVE: To investigate the opioid consumption and the healthcare resource utilization in patients with the intrathecal drug delivery system (IDDS) therapy and the comprehensive medical management (CMM) alone. DESIGN: A retrospective cohort study with a customized claims database. SETTING: In a university-based hospital. SUBJECTS: Patients with complex regional pain syndrome, post-laminectomy syndrome, and fibromyalgia. METHODS: Using propensity score matching (1:3), we selected patients with morphine infusion through IDDS (IDDS group) and CMM alone (CMM group). The primary endpoints were comparisons of average morphine equivalents daily dosages (MEDD, mg/day) for 6 and 12 months from an index date. The number of emergency room (ER) visits and hospitalizations and the total medical expenditures were compared as secondary outcomes. RESULTS: In total, 82 patients (N = 23 in the IDDS group and N = 59 in the CMM group) were analyzed. Although a 6-month average MEDD did not reach statistical significance, a 12-month average MEDD was significantly decreased in the IDDS group compared to the CMM group (53.2 ± 46.3 vs 123.9 ± 176.4, respectively; P = 0.008). ER visits were more frequent in the IDDS group than the CMM group at baseline (5.4 vs 0.5, respectively; P = .002), which was maintained for 12 months (P < 0.001). Otherwise, the number of hospitalization and the medical expenditures for pain management were not different between the groups for 12 months. CONCLUSIONS: The combined IDDS therapy had some benefits in reducing opioid consumption for 1-year follow-up compared to the CMM alone in chronic noncancer pain patients.

Emerging Roles of Using Small Extracellular Vesicles as an Anti-Cancer Drug.

Small extracellular vesicles (sEVs) are emerging as a novel therapeutic strategy for cancer therapy. Tumor-cell-derived sEVs contain biomolecules that can be utilized for cancer diagnosis. sEVs can directly exert tumor-killing effects or modulate the tumor microenvironment, leading to anti-cancer effects. In this review, the application of sEVs as a diagnostic tool, drug delivery system, and active pharmaceutical ingredient for cancer therapy will be highlighted. The therapeutic efficacies of sEVs will be compared to conventional immune checkpoint inhibitors. Additionally, this review will provide strategies for sEV engineering to enhance the therapeutic efficacies of sEVs. As a bench-to-bedside application, we will discuss approaches to encourage good-manufacturing-practice-compliant industrial-scale manufacturing and purification of sEVs.

External Validation of Postpartum Hemorrhage Prediction Models Using Electronic Health Record Data.

OBJECTIVE: A recent study leveraging machine learning methods found that postpartum hemorrhage (PPH) can be predicted accurately at the time of labor admission in the U.S. Consortium for Safe Labor (CSL) dataset, with a C-statistic as high as 0.93. These CSL models were developed in older data (2002-2008) and used an estimated blood loss (EBL) of ≥1,000 mL to define PPH. We sought to externally validate these models using a more recent cohort of births where blood loss was measured using quantitative blood loss (QBL) methods. STUDY DESIGN: Using data from 5,261 deliveries between February 1, 2019 and May 11, 2020 at a single tertiary hospital, we mapped our electronic health record (EHR) data to the 55 predictors described in previously published CSL models. PPH was defined as QBL ≥1,000 mL within 24 hours after delivery. Model discrimination and calibration of the four CSL models were measured using our cohort. In a secondary analysis, we fit new models in our study cohort using the same predictors and algorithms as the original CSL models. RESULTS: The original study cohort had a substantially lower rate of PPH, 4.8% (7,279/228,438) versus 25% (1,321/5,261), possibly due to differences in measurement. The CSL models had lower discrimination in our study cohort, with a C-statistic as high as 0.57 (logistic regression). Models refit in our study cohort achieved better discrimination, with a C-statistic as high as 0.64 (random forest). Calibration improved in the refit models as compared with the original models. CONCLUSION: The CSL models' accuracy was lower in a contemporary EHR where PPH is assessed using QBL. As institutions continue to adopt QBL methods, further data are needed to understand the differences between EBL and QBL to enable accurate prediction of PPH. KEY POINTS: · Machine learning methods may help predict PPH.. · EBL models do not generalize when QBL is used.. · Blood loss estimation alters model accuracy..

Wearable Fabric Loop Sensor Based on Magnetic-Field-Induced Conductivity for Simultaneous Detection of Cardiac Activity and Respiration Signals.

In this study, a noncontact fabric loop sensor based on magnetic-field-induced conductivity, which can simultaneously detect cardiac activity and respiration signals, was developed and the effects of the sensor's shape and measurement position on the sensing performance were analyzed. Fifteen male subjects in their twenties wore sleeveless shirts equipped with various types of fabric loop sensors (spiky, extrusion, and spiral), and the cardiac activity and respiratory signals were measured twice at positions P2, P4, and P6. The measurements were verified by comparing them against the reference electrocardiogram (ECG) and respiratory signals measured using BIOPAC® (MP150, ECG100B, RSP100C). The waveforms of the raw signal measured by the fabric loop sensor were filtered with a bandpass filter (1-20 Hz) and qualitatively compared with the ECG signal obtained from the Ag/AgCI electrode. Notwithstanding a slight difference in performance, the three fabric sensors could simultaneously detect cardiac activity and respiration signals at all measurement positions. In addition, it was verified through statistical analysis that the highest-quality signal was obtained at the measurement position of P4 or P6 using the spiral loop sensor.

[Digital transformation of COVID-19 research].

In a current life sciences research, we are in an era in which advanced technology emerging and utilize big data. Data-driven approaches such as machine learnings play an important role to analyze these datasets. However, limited clinical (time-course) datasets are available for infectious diseases, cancer, and other diseases. Especially in the case of emerging infectious disease outbreaks, clinical data obtained from a limited number of cases must be used to develop treatment strategies and public health policies. This means that many clinical data are not big data, which often makes the application of data-driven approaches difficult. In this paper, we mainly apply a mathematical model-based approach to the clinical data of COVID-19 and discuss how biologically important information can be extracted from the limited data and how they can benefit society.

Machine Embroidered Sensors for Limb Joint Movement-Monitoring Smart Clothing.

In this study, a strain gauge sensor based on a change of contact or network structure between conductive materials was implemented using the handle-machine embroidery technique, and the variables (embroidery shape, embroidery distance, embroidery size, and implementation location) affecting its performance were studied. As a result of Experiment I on the structure of embroidery suitable for joint motion monitoring, the embroidery distance, rather than the embroidery size, was found to have a significant effect on the electric resistance changes caused by elongation. Based on the results of Experiment I, two types of zigzag embroideries, four types of embroideries with few contact points, and two types of embroideries with more contact points (all with short distances (2.0)) were selected for Experiment II (the dummy motion experiment). As a result of the dummy motion experiment, it was found that the locations of the suitable embroidered sensors for joint motion monitoring was the HJP (Hinge Joint Position) in the 'types without a contact point' (zigzag) and the LHJP (Lower Hinge Joint Position) in the 'types with more contact points'. On the other hand, although there was no consistency among the 'types with few contact points', the resistance changes measured by the 2CP and 7CP embroidered sensors showed similar figures and patterns, and the HJP location was most suitable. The resistance changes measured by the 4CP and 6CP embroidered sensors exhibited no consistent patterns, but the LHJP locations were more suitable. These results indicate that the location of the HJP is suitable for measuring joint motion in the 'type without a contact point', and the location of the LHJP is suitable for measuring joint motion when the number of contact points exceeds a certain limit. Among them, the average resistance change of the 9CP sensor located at the LHJP was 40 Ω with the smallest standard deviation of less than 1, and it is thus considered to have the best performance among all the sensors.

Therapeutic Application of Exosomes in Inflammatory Diseases.

Immunomodulation is on the cusp of being an important therapy for treating many diseases, due to the significant role of the immune system in defending the human body. Although the immune system is an essential defense system, overactivity can result in diverse sicknesses such as inflammation and autoimmune disease. Exosomes are emerging as a state-of-the-art therapeutic strategy for treating an overactive immune system. Thus, exosomes have drawn great interest for their potential clinical applications in treating diseases associated with abnormal immune regulation. Hence, in this review, we will discuss trends in exosome research related to inflammatory and autoimmune diseases. Possible therapeutic applications of exosomes will be summarized. Finally, an outlook to the future of exosomal therapy will be introduced.

Enhanced Production of a Thermostable Carbonic Anhydrase in Escherichia coli by Using a Modified NEXT Tag.

Carbonic anhydrase (CA) is an ultrafast enzyme that catalyzes the reversible conversion of carbon dioxide (CO2) to bicarbonate. CA is considered to be a green catalyst for enzyme-based CO2 capture and utilization. In particular, the CA of Thermovibrio ammonificans (taCA) has attracted increasing attention as a highly stable enzyme. However, the poor solubility and the low expression level in Escherichia coli have hampered further utilization of taCA. In a recent study, these limitations were partly resolved by using a small solubility-enhancing fusion tag named NEXT, which originates from the N-terminal extension of Hydrogenovibrio marinus CA. In this study, the NEXT tag was engineered by adding small peptides to the N terminus to further increase the production yield of NEXT-tagged taCA. The addition of ng3 peptide (His-Gly-Asn) originating from the N-terminal sequence of Neisseria gonorrhoeae CA improved the expression of NEXT-taCA, while the previously developed translation-enhancing element (TEE) and Ser-Lys-Ile-Lys (SKIK) tag were not effective. The expression test with all 16 codon combinations for the ng3 sequence revealed that the change in translation initiation rate brought about by the change in nucleotide sequence was not the primary determinant for the change in expression level. The modified ng3-NEXT tag may be applied to increase the production yields of various recombinant proteins.

Loganin Alleviates Gout Inflammation by Suppressing NLRP3 Inflammasome Activation and Mitochondrial Damage.

Gout is a type of inflammatory arthritis caused by the deposition of monosodium uric acid (MSU) crystals in tissues. The etiology of gout is directly linked to the NLRP3 inflammasome, since MSU crystals are NLRP3 inflammasome activators. Therefore, we decided to search for a small-molecule inhibitor of the NLRP3 inflammasome for the prevention of gout inflammation. We found that loganin suppressed MSU crystals-induced caspase-1 (p20) and interleukin (IL)-1ß production and apoptosis-associated speck-like protein containing a caspase recruitment domain (ASC) specks formation in mouse primary macrophages, showing its ability to inhibit the NLRP3 inflammasome. In an air pouch inflammation model, oral administration of loganin to mice prevented MSU crystals-induced production of mature IL-1ß and IL-18 in air pouch exudates, resulting in decreased neutrophil recruitment. Furthermore, oral administration of loganin suppressed MSU crystals-induced gout inflammation in a mouse foot gout model, which was accompanied by the inhibition of the NLRP3 inflammasome. Loganin blocked de novo synthesis of mitochondrial DNA in air pouches and foot tissues injected with MSU crystals. Consistently, loganin prevented MSU crystals-induced mitochondrial damage in macrophages, as it increased mitochondrial membrane potential and decreased the amount of mitochondrial reactive oxygen species. These data demonstrate that loganin suppresses NLRP3 inflammasome activation by inhibiting mitochondrial stress. These results suggest a novel pharmacological strategy to prevent gout inflammation by blocking NLRP3 inflammasome activation and mitochondrial dysfunction.

Conditions for CNT - Coated Textile Sensors Applied to Wearable Platforms to Monitor Limb Joint Motion.

Despite recent research on joint motion measurement to monitor human body movement, current measurement techniques and tools have significant limitations, including requiring large space for measurement and causing discomfort in test subjects wearing motion sensors. Our study aims, first, to develop carbon nanotube (CNT)-based textile joint motion sensors. Second, ours study aims to identify the most suitable CNT-based sensor structure and attachment method for use on a wearable platform during general exercise speeds. Lastly, we used these sensors on the human body, using sleeves and legs to find the most stable location, and we used the CNT-based sensor condition to monitor joint motions. We utilized our CNT-based sensor, which has proper elasticity as well as conductivity, and applied it to the elbow and knee joints. Based on the strain gauge principle, we monitored the variance of electric resistance that occurred when the CNT-based sensor was stretched due to limb motion. Our study tested 48 types of sensors. These sensors were applied to the CNT using different base knit textiles as well as different attachment methods, layers, sensor lengths, and sensor widths. The four most successful sensor types, which showed superior efficacy over the others in joint motion measurement, were selected for further study. These four sensors were then used to measure the elbow and knee joint motions of human subjects by placing them on different locations on sleeves and legs. The CNT knit textile sensors best suited to measuring joint motions are those with a double-layered CNT knit and 5 cm long × 0.5 cm or 1 cm wide sensors attached to a polyester¬-based knit using a welding method. The best position for the sensor to more stably monitor joint motions was the "below hinge position" from the elbow or knee hinge joint. Our study suggests an alternative strategy for joint-motion measurement that could contribute to the development of more comfortable and human-friendly methods of human limb motion measurement.

Stunning symmetries involved in the self-assembly of the HSV-1 capsid.

Herpes simplex virus-1 (HSV-1) is an enveloped dsDNA virus, infecting ~ 67% of humans. Here, we present the essential components of the HSV-1, focusing on stunning symmetries on the capsid. However, little is known about how the symmetries are involved dynamically in the self-assembly process. We suggest small angle X-ray scattering as a suitable method to capture the dynamics of self-assembly. Furthermore, our understanding of the viruses can be expanded by using an integrative approach that combines heterogeneous types of data, thus promoting new diagnostic tools and a cure for viral infections.

Early Detection of Heart Failure With Reduced Ejection Fraction Using Perioperative Data Among Noncardiac Surgical Patients: A Machine-Learning Approach.

BACKGROUND: Heart failure with reduced ejection fraction (HFrEF) is a condition imposing significant health care burden. Given its syndromic nature and often insidious onset, the diagnosis may not be made until clinical manifestations prompt further evaluation. Detecting HFrEF in precursor stages could allow for early initiation of treatments to modify disease progression. Granular data collected during the perioperative period may represent an underutilized method for improving the diagnosis of HFrEF. We hypothesized that patients ultimately diagnosed with HFrEF following surgery can be identified via machine-learning approaches using pre- and intraoperative data. METHODS: Perioperative data were reviewed from adult patients undergoing general anesthesia for major surgical procedures at an academic quaternary care center between 2010 and 2016. Patients with known HFrEF, heart failure with preserved ejection fraction, preoperative critical illness, or undergoing cardiac, cardiology, or electrophysiologic procedures were excluded. Patients were classified as healthy controls or undiagnosed HFrEF. Undiagnosed HFrEF was defined as lacking a HFrEF diagnosis preoperatively but establishing a diagnosis within 730 days postoperatively. Undiagnosed HFrEF patients were adjudicated by expert clinician review, excluding cases for which HFrEF was secondary to a perioperative triggering event, or any event not associated with HFrEF natural disease progression. Machine-learning models, including L1 regularized logistic regression, random forest, and extreme gradient boosting were developed to detect undiagnosed HFrEF, using perioperative data including 628 preoperative and 1195 intraoperative features. Training/validation and test datasets were used with parameter tuning. Test set model performance was evaluated using area under the receiver operating characteristic curve (AUROC), positive predictive value, and other standard metrics. RESULTS: Among 67,697 cases analyzed, 279 (0.41%) patients had undiagnosed HFrEF. The AUROC for the logistic regression model was 0.869 (95% confidence interval, 0.829-0.911), 0.872 (0.836-0.909) for the random forest model, and 0.873 (0.833-0.913) for the extreme gradient boosting model. The corresponding positive predictive values were 1.69% (1.06%-2.32%), 1.42% (0.85%-1.98%), and 1.78% (1.15%-2.40%), respectively. CONCLUSIONS: Machine-learning models leveraging perioperative data can detect undiagnosed HFrEF with good performance. However, the low prevalence of the disease results in a low positive predictive value, and for clinically meaningful sensitivity thresholds to be actionable, confirmatory testing with high specificity (eg, echocardiography or cardiac biomarkers) would be required following model detection. Future studies are necessary to externally validate algorithm performance at additional centers and explore the feasibility of embedding algorithms into the perioperative electronic health record for clinician use in real time.