Highlights d Retrograde viruses express mRNA at levels detectable in single-cell sequencing d Different transgenes can be multiplexed in a single sequencing run d VECTORseq identifies both cortical and subcortical projection neurons d VECTORseq defines new superior colliculus and zona incerta projection populations

SummaryBehavior arises from concerted activity throughout the brain. Consequently, a major focus of modern neuroscience is defining the physiology and behavioral roles of projection neurons linking different brain areas. Single-cell RNA sequencing has facilitated these efforts by revealing molecular determinants of cellular physiology and markers that enable genetically targeted perturbations such as optogenetics, but existing methods for sequencing of defined projection populations are low-throughput, painstaking, and costly. We developed a straightforward, multiplexed approach, Virally Encoded Connectivity Transgenic Overlay RNA sequencing (VECTORseq). VECTORseq repurposes commercial retrogradely infecting viruses typically used to express functional transgenes, e.g., recombinases and fluorescent proteins, by treating viral transgene mRNA as barcodes within single-cell datasets. VECTORseq is compatible with different viral families, resolves multiple populations with different projection targets in one sequencing run, and identifies cortical and subcortical excitatory and inhibitory projection populations. Our study provides a roadmap for high-throughput identification of neuronal subtypes based on connectivity.

Importance: Large volumes of unstructured text notes exist for patients in electronic health records (EHR) that describe their state of health. Natural language processing (NLP) can leverage this information for perioperative risk prediction. Objective: Predict a modified American Society of Anesthesiologists Physical Status Classification (ASA-PS) score using preoperative note text, identify which model architecture and note sections are most useful, and interpret model predictions with Shapley values. Design: Retrospective cohort analysis from an EHR. Setting: Two-hospital integrated care system comprising a tertiary/quaternary academic medical center and a level 1 trauma center with a 5-state referral catchment area. Participants: Patients undergoing procedures requiring anesthesia care spanning across all procedural specialties from January 1, 2016 to March 29, 2021 who were not assigned ASA VI and also had a preoperative evaluation note filed within 90 days prior to the procedure. Exposures: Each procedural case paired with the most recent anesthesia preoperative evaluation note preceding the procedure. Main Outcomes and Measures: Prediction of a modified ASA-PS from preoperative note text. We compared 4 different text classification models for 8 different input text snippets. Performance was compared using area under the receiver operating characteristic curve (AUROC) and area under the precision recall curve (AUPRC). Shapley values were used to explain model predictions. Results: Final dataset includes 38566 patients undergoing 61503 procedures. Prevalence of ASA-PS was 8.81% for ASA I, 31.4% for ASA II, 43.25% for ASA III, and 16.54% for ASA IV-V. The best performing models were the BioClinicalBERT model on the truncated note task (macro-average AUROC 0.845) and the fastText model on the full note task (macro-average AUROC 0.865). Shapley values reveal human-interpretable model predictions. Conclusions and Relevance: Text classification models can accurately predict a patient's illness severity using only free-form text descriptions of patients without any manual data extraction. They can be an additional patient safety tool in the perioperative setting and reduce manual chart review for medical billing. Shapley feature attributions produce explanations that logically support model predictions and are understandable to clinicians.

No abstract