Development and validation of a machine learning ASA-score to identify candidates for comprehensive preoperative screening and risk stratification.

OBJECTIVE: The ASA physical status (ASA-PS) is determined by an anesthesia provider or surgeon to communicate co-morbidities relevant to perioperative risk. Assigning an ASA-PS is a clinical decision and there is substantial provider-dependent variability. We developed and externally validated a machine learning-derived algorithm to determine ASA-PS (ML-PS) based on data available in the medical record. DESIGN: Retrospective multicenter hospital registry study. SETTING: University-affiliated hospital networks. PATIENTS: Patients who received anesthesia at Beth Israel Deaconess Medical Center (Boston, MA, training [n = 361,602] and internal validation cohorts [n = 90,400]) and Montefiore Medical Center (Bronx, NY, external validation cohort [n = 254,412]). MEASUREMENTS: The ML-PS was created using a supervised random forest model with 35 preoperatively available variables. Its predictive ability for 30-day mortality, postoperative ICU admission, and adverse discharge were determined by logistic regression. MAIN RESULTS: The anesthesiologist ASA-PS and ML-PS were in agreement in 57.2% of the cases (moderate inter-rater agreement). Compared with anesthesiologist rating, ML-PS assigned more patients into extreme ASA-PS (I and IV), (p < 0.01), and less patients in ASA II and III (p < 0.01). ML-PS and anesthesiologist ASA-PS had excellent predictive values for 30-day mortality, and good predictive values for postoperative ICU admission and adverse discharge. Among the 3594 patients who died within 30 days after surgery, net reclassification improvement analysis revealed that using the ML-PS, 1281 (35.6%) patients were reclassified into the higher clinical risk category compared with anesthesiologist rating. However, in a subgroup of multiple co-morbidity patients, anesthesiologist ASA-PS had a better predictive accuracy than ML-PS. CONCLUSIONS: We created and validated a machine learning physical status based on preoperatively available data. The ability to identify patients at high risk early in the preoperative process independent of the provider's decision is a part of the process we use to standardize the stratified preoperative evaluation of patients scheduled for ambulatory surgery.

An Accessible Clinical Decision Support System to Curtail Anesthetic Greenhouse Gases in a Large Health Network: Implementation Study.

BACKGROUND: Inhaled anesthetics in the operating room are potent greenhouse gases and are a key contributor to carbon emissions from health care facilities. Real-time clinical decision support (CDS) systems lower anesthetic gas waste by prompting anesthesia professionals to reduce fresh gas flow (FGF) when a set threshold is exceeded. However, previous CDS systems have relied on proprietary or highly customized anesthesia information management systems, significantly reducing other institutions' accessibility to the technology and thus limiting overall environmental benefit. OBJECTIVE: In 2018, a CDS system that lowers anesthetic gas waste using methods that can be easily adopted by other institutions was developed at the University of California San Francisco (UCSF). This study aims to facilitate wider uptake of our CDS system and further reduce gas waste by describing the implementation of the FGF CDS toolkit at UCSF and the subsequent implementation at other medical campuses within the University of California Health network. METHODS: We developed a noninterruptive active CDS system to alert anesthesia professionals when FGF rates exceeded 0.7 L per minute for common volatile anesthetics. The implementation process at UCSF was documented and assembled into an informational toolkit to aid in the integration of the CDS system at other health care institutions. Before implementation, presentation-based education initiatives were used to disseminate information regarding the safety of low FGF use and its relationship to environmental sustainability. Our FGF CDS toolkit consisted of 4 main components for implementation: sustainability-focused education of anesthesia professionals, hardware integration of the CDS technology, software build of the CDS system, and data reporting of measured outcomes. RESULTS: The FGF CDS system was successfully deployed at 5 University of California Health network campuses. Four of the institutions are independent from the institution that created the CDS system. The CDS system was deployed at each facility using the FGF CDS toolkit, which describes the main components of the technology and implementation. Each campus made modifications to the CDS tool to best suit their institution, emphasizing the versatility and adoptability of the technology and implementation framework. CONCLUSIONS: It has previously been shown that the FGF CDS system reduces anesthetic gas waste, leading to environmental and fiscal benefits. Here, we demonstrate that the CDS system can be transferred to other medical facilities using our toolkit for implementation, making the technology and associated benefits globally accessible to advance mitigation of health care-related emissions.

Keeping an Open Mind About Open Notes: Sharing Anesthesia Records With Patients.

ADDENDUM: Please note that in the interim since this paper was accepted for publication, new governmental regulations, pertinent to the topic, have been approved for implementation. The reader is thus directed to this online addendum for additional relevant information: http://links.lww.com/AA/E44.

Developing a COVID-19 WHO Clinical Progression Scale inpatient database from electronic health record data.

OBJECTIVE: There is a need for a systematic method to implement the World Health Organization's Clinical Progression Scale (WHO-CPS), an ordinal clinical severity score for coronavirus disease 2019 patients, to electronic health record (EHR) data. We discuss our process of developing guiding principles mapping EHR data to WHO-CPS scores across multiple institutions. MATERIALS AND METHODS: Using WHO-CPS as a guideline, we developed the technical blueprint to map EHR data to ordinal clinical severity scores. We applied our approach to data from 2 medical centers. RESULTS: Our method was able to classify clinical severity for 100% of patient days for 2756 patient encounters across 2 institutions. DISCUSSION: Implementing new clinical scales can be challenging; strong understanding of health system data architecture was integral to meet the clinical intentions of the WHO-CPS. CONCLUSION: We describe a detailed blueprint for how to apply the WHO-CPS scale to patient data from the EHR.

The emerging role of clinical informatics fellows in service learning during the COVID-19 pandemic.

OBJECTIVE: The study sought to describe the contributions of clinical informatics (CI) fellows to their institutions' coronavirus disease 2019 (COVID-19) response. MATERIALS AND METHODS: We designed a survey to capture key domains of health informatics and perceptions regarding fellows' application of their CI skills. We also conducted detailed interviews with select fellows and described their specific projects in a brief case series. RESULTS: Forty-one of the 99 CI fellows responded to our survey. Seventy-five percent agreed that they were "able to apply clinical informatics training and interest to the COVID-19 response." The most common project types were telemedicine (63%), reporting and analytics (49%), and electronic health record builds and governance (32%). Telehealth projects included training providers on existing telehealth tools, building entirely new virtual clinics for video triage of COVID-19 patients, and pioneering workflows and implementation of brand-new emergency department and inpatient video visit types. Analytics projects included reports and dashboards for institutional leadership, as well as developing digital contact tracing tools. For electronic health record builds, fellows directly contributed to note templates with embedded screening and testing guidance, adding COVID-19 tests to order sets, and validating clinical triage workflows. DISCUSSION: Fellows were engaged in projects that span the breadth of the CI specialty and were able to make system-wide contributions in line with their educational milestones. CONCLUSIONS: CI fellows contributed meaningfully and rapidly to their institutions' response to the COVID-19 pandemic.

An optimized method for the estimation of the respiratory rate from electrocardiographic signals: implications for estimating minute ventilation.

It is well-known that respiratory activity influences electrocardiographic (ECG) morphology. In this article we present a new algorithm for the extraction of respiratory rate from either intracardiac or body surface electrograms. The algorithm optimizes selection of ECG leads for respiratory analysis, as validated in a swine model. The algorithm estimates the respiratory rate from any two ECG leads by finding the power spectral peak of the derived ratio of the estimated root-mean-squared amplitude of the QRS complexes on a beat-by-beat basis across a 32-beat window and automatically selects the lead combination with the highest power spectral signal-to-noise ratio. In 12 mechanically ventilated swine, we collected intracardiac electrograms from catheters in the right ventricle, coronary sinus, left ventricle, and epicardial surface, as well as body surface electrograms, while the ventilation rate was varied between 7 and 13 breaths/min at tidal volumes of 500 and 750 ml. We found excellent agreement between the estimated and true respiratory rate for right ventricular (R(2) = 0.97), coronary sinus (R(2) = 0.96), left ventricular (R(2) = 0.96), and epicardial (R(2) = 0.97) intracardiac leads referenced to surface lead ECGII. When applied to intracardiac right ventricular-coronary sinus bipolar leads, the algorithm exhibited an accuracy of 99.1% (R(2) = 0.97). When applied to 12-lead body surface ECGs collected in 4 swine, the algorithm exhibited an accuracy of 100% (R(2) = 0.93). In conclusion, the proposed algorithm provides an accurate estimation of the respiratory rate using either intracardiac or body surface signals without the need for additional hardware.

New genes that extend Caenorhabditis elegans' lifespan in response to reproductive signals.

In Caenorhabditis elegans and Drosophila, removing germline stem cells increases lifespan. In C. elegans, this lifespan extension requires DAF-16, a FOXO transcription factor, and DAF-12, a nuclear hormone receptor. To better understand the regulatory relationships between DAF-16 and DAF-12, we used microarray analysis to identify downstream genes. We found that these two transcription factors influence the expression of distinct but overlapping sets of genes in response to loss of the germline. In addition, we identified several new genes that are required for loss of the germline to increase lifespan. One, phi-62, encodes a conserved, predicted RNA-binding protein. PHI-62 influences DAF-16-dependent transcription, possibly by collaborating with TCER-1, a putative transcription elongation factor, and FTT-2, a 14-3-3 protein known to bind DAF-16. Three other genes encode proteins involved in lipid metabolism; one is a triacylglycerol lipase, and another is an acyl-CoA reductase. These genes do not noticeably affect bulk fat storage levels; therefore, we propose a model in which they may influence production of a lifespan-extending signal or metabolite.

Large-scale analysis of neurite growth dynamics on micropatterned substrates.

During both development and regeneration of the nervous system, neurons display complex growth dynamics, and several neurites compete to become the neuron's single axon. Numerous mathematical and biophysical models have been proposed to explain this competition, which remain experimentally unverified. Large-scale, precise, and repeatable measurements of neurite dynamics have been difficult to perform, since neurons have varying numbers of neurites, which themselves have complex morphologies. To overcome these challenges using a minimal number of primary neurons, we generated repeatable neuronal morphologies on a large scale using laser-patterned micron-wide stripes of adhesive proteins on an otherwise highly non-adherent substrate. By analyzing thousands of quantitative time-lapse measurements of highly reproducible neurite growth dynamics, we show that total neurite growth accelerates until neurons polarize, that immature neurites compete even at very short lengths, and that neuronal polarity exhibits a distinct transition as neurites grow. Proposed neurite growth models agree only partially with our experimental observations. We further show that simple yet specific modifications can significantly improve these models, but still do not fully predict the complex neurite growth behavior. Our high-content analysis puts significant and nontrivial constraints on possible mechanistic models of neurite growth and specification. The methodology presented here could also be employed in large-scale chemical and target-based screens on a variety of complex and subtle phenotypes for therapeutic discoveries using minimal numbers of primary neurons.

Global stabilization of rRNA structure by ribosomal proteins S4, S17, and S20.

Ribosomal proteins stabilize the folded structure of the ribosomal RNA and enable the recruitment of further proteins to the complex. Quantitative hydroxyl radical footprinting was used to measure the extent to which three different primary assembly proteins, S4, S17, and S20, stabilize the three-dimensional structure of the Escherichia coli 16S 5' domain. The stability of the complexes was perturbed by varying the concentration of MgCl(2). Each protein influences the stability of the ribosomal RNA tertiary interactions beyond its immediate binding site. S4 and S17 stabilize the entire 5' domain, while S20 has a more local effect. Multistage folding of individual helices within the 5' domain shows that each protein stabilizes a different ensemble of structural intermediates that include nonnative interactions at low Mg(2+) concentration. We propose that the combined interactions of S4, S17, and S20 with different helical junctions bias the free-energy landscape toward a few RNA conformations that are competent to add the secondary assembly protein S16 in the next step of assembly.

S16 throws a conformational switch during assembly of 30S 5' domain.

Rapid and accurate assembly of new ribosomal subunits is essential for cell growth. Here we show that the ribosomal proteins make assembly more cooperative by discriminating against non-native conformations of the Escherichia coli 16S ribosomal RNA. We used hydroxyl radical footprinting to measure how much the proteins stabilize individual ribosomal RNA tertiary interactions, revealing the free-energy landscape for assembly of the 16S 5' domain. When ribosomal proteins S4, S17 and S20 bind the 5' domain RNA, a native and a non-native assembly intermediate are equally populated. The secondary assembly protein S16 suppresses the non-native intermediate, smoothing the path to the native complex. In the final step of 5' domain assembly, S16 drives a conformational switch at helix 3 that stabilizes pseudoknots in the 30S decoding center. Long-range communication between the S16 binding site and the decoding center helps to explain the crucial role of S16 in 30S assembly.

Protein-independent folding pathway of the 16S rRNA 5' domain.

Evolution of the ribosome from an RNA catalyst suggests that the intrinsic folding pathway of the rRNA dictates the hierarchy of ribosome assembly. To address this possibility, we probed the tertiary folding pathway of the 5' domain of the Escherichia coli 16S rRNA at 20 ms intervals using X-ray-dependent hydroxyl radical footprinting. Comparison with crystallographic structures and footprinting reactions on native 30S ribosomes showed that the RNA formed all of the predicted tertiary interactions in the absence of proteins. In 20 mM MgCl2, many tertiary interactions appeared within 20 ms. By contrast, interactions between H6, H15 and H17 near the spur of the 30S ribosome evolved over several minutes, likely due to mispairing of a central helix junction. The kinetic folding pathway of the RNA corresponded to the expected order of protein binding, suggesting that the RNA folding pathway forms the basis for early steps of ribosome assembly.

GSK-3 kinases enhance calcineurin signaling by phosphorylation of RCNs.

The conserved RCN family of proteins can bind and directly regulate calcineurin, a Ca(2+)-activated protein phosphatase involved in immunity, heart growth, muscle development, learning, and other processes. Whereas high levels of RCNs can inhibit calcineurin signaling in fungal and animal cells, RCNs can also stimulate calcineurin signaling when expressed at endogenous levels. Here we show that the stimulatory effect of yeast Rcn1 involves phosphorylation of a conserved serine residue by Mck1, a member of the GSK-3 family of protein kinases. Mutations at the GSK-3 consensus site of Rcn1 and human DSCR1/MCIP1 abolish the stimulatory effects on calcineurin signaling. RCNs may therefore oscillate between stimulatory and inhibitory forms in vivo in a manner similar to the Inhibitor-2 regulators of type 1 protein phosphatase. Computational modeling indicates a biphasic response of calcineurin to increasing RCN concentration such that protein phosphatase activity is stimulated by low concentrations of phospho-RCN and inhibited by high concentrations of phospho- or dephospho-RCN. This prediction was verified experimentally in yeast cells expressing Rcn1 or DSCR1/MCIP1 at different concentrations. Through the phosphorylation of RCNs, GSK-3 kinases can potentially contribute to a positive feedback loop involving calcineurin-dependent up-regulation of RCN expression. Such feedback may help explain the large induction of DSCR1/MCIP1 observed in brain of Down syndrome individuals.