Development of a 3-Step theory of suicide ontology to facilitate 3ST factor extraction from clinical progress notes

OBJECTIVE

Suicide risk prediction algorithms at the Veterans Health Administration (VHA) do not include predictors based on the 3-Step Theory of suicide (3ST), which builds on hopelessness, psychological pain, connectedness, and capacity for suicide. These four factors are not available from structured fields in VHA electronic health records, but they are found in unstructured clinical text. An ontology and controlled vocabulary that maps psychosocial and behavioral terms to these factors does not exist. The objectives of this study were 1) to develop an ontology with a controlled vocabulary of terms that map onto classes that represent the 3ST factors as identified within electronic clinical progress notes, and 2) to determine the accuracy of automated extractions based on terms in the controlled vocabulary.

METHODS

A team of four annotators did linguistic annotation of 30,000 clinical progress notes from 231 Veterans in VHA electronic health records who attempted suicide or who died by suicide for terms relating to the 3ST factors. Annotation involved manually assigning a label to words or phrases that indicated presence or absence of the factor (polarity). These words and phrases were entered into a controlled vocabulary that was then used by our computational system to tag 14 million clinical progress notes from Veterans who attempted or died by suicide after 2013. Tagged text was extracted and machine-labelled for presence or absence of the 3ST factors. Accuracy of these machine-labels was determined for 1000 randomly selected extractions for each factor against a ground truth created by our annotators.

RESULTS

Linguistic annotation identified 8486 terms that related to 33 subclasses across the four factors and polarities. Precision of machine-labeled extractions ranged from 0.73 to 1.00 for most factor-polarity combinations, whereas recall was somewhat lower 0.65-0.91.

CONCLUSION

The ontology that was developed consists of classes that represent each of the four 3ST factors, subclasses, relationships, and terms that map onto those classes which are stored in a controlled vocabulary (https://bioportal.bioontology.org/ontologies/THREE-ST). The use case that we present shows how scores based on clinical notes tagged for terms in the controlled vocabulary capture meaningful change in the 3ST factors during weeks preceding a suicidal event.

Defining Essential Surgery in the US During the COVID-19 Pandemic Response

This cohort study compares the volume of performed surgical procedures classified as essential, urgent, and nonurgent before and after elective surgeries were restricted during the COVID-19 pandemic in the US.

A Tool to Estimate Risk of 30-day Mortality and Complications After Hip Fracture Surgery: Accurate Enough for Some but Not All Purposes? A Study From the ACS-NSQIP Database

BACKGROUND

Surgical repair of hip fracture carries substantial short-term risks of mortality and complications. The risk-reward calculus for most patients with hip fractures favors surgical repair. However, some patients have low prefracture functioning, frailty, and/or very high risk of postoperative mortality, making the choice between surgical and nonsurgical management more difficult. The importance of high-quality informed consent and shared decision-making for frail patients with hip fracture has recently been demonstrated. A tool to accurately estimate patient-specific risks of surgery could improve these processes.

QUESTIONS/PURPOSES

With this study, we sought (1) to develop, validate, and estimate the overall accuracy (C-index) of risk prediction models for 30-day mortality and complications after hip fracture surgery; (2) to evaluate the accuracy (sensitivity, specificity, and false discovery rates) of risk prediction thresholds for identifying very high-risk patients; and (3) to implement the models in an accessible web calculator.

METHODS

In this comparative study, preoperative demographics, comorbidities, and preoperatively known operative variables were extracted for all 82,168 patients aged 18 years and older undergoing surgery for hip fracture in the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) between 2011 and 2017. Eighty-two percent (66,994 of 82,168 ) of patients were at least 70 years old, 21% (17,007 of 82,168 ) were at least 90 years old, 70% (57,260 of 82,168 ) were female, and 79% (65,301 of 82,168 ) were White. A total of 5% (4260 of 82,168) of patients died within 30 days of surgery, and 8% (6786 of 82,168) experienced a major complication. The ACS-NSQIP database was chosen for its clinically abstracted and reliable data from more than 600 hospitals on important surgical outcomes, as well as rich characterization of preoperative demographic and clinical predictors for demographically diverse patients. Using all the preoperative variables in the ACS-NSQIP dataset, least absolute shrinkage and selection operator (LASSO) logistic regression, a type of machine learning that selects variables to optimize accuracy and parsimony, was used to develop and validate models to predict two primary outcomes: 30-day postoperative mortality and any 30-day major complications. Major complications were defined by the occurrence of ACS-NSQIP complications including: on a ventilator longer than 48 hours, intraoperative or postoperative unplanned intubation, septic shock, deep incisional surgical site infection (SSI), organ/space SSI, wound disruption, sepsis, intraoperative or postoperative myocardial infarction, intraoperative or postoperative cardiac arrest requiring cardiopulmonary resuscitation, acute renal failure needing dialysis, pulmonary embolism, stroke/cerebral vascular accident, and return to the operating room. Secondary outcomes were six clusters of complications recently developed and increasingly used for the development of surgical risk models, namely: (1) pulmonary complications, (2) infectious complications, (3) cardiac events, (4) renal complications, (5) venous thromboembolic events, and (6) neurological events. Tenfold cross-validation was used to assess overall model accuracy with C-indexes, a measure of how well models discriminate patients who experience an outcome from those who do not. Using the models, the predicted risk of outcomes for each patient were used to estimate the accuracy (sensitivity, specificity, and false discovery rates) of a wide range of predicted risk thresholds. We then implemented the prediction models into a web-accessible risk calculator.

RESULTS

The 30-day mortality and major complication models had good to fair discrimination (C-indexes of 0.76 and 0.64, respectively) and good calibration throughout the range of predicted risk. Thresholds of predicted risk to identify patients at very high risk of 30-day mortality had high specificity but also high false discovery rates. For example, a 30-day mortality predicted risk threshold of 15% resulted in 97% specificity, meaning 97% of patients who lived longer than 30 days were below that risk threshold. However, this threshold had a false discovery rate of 78%, meaning 78% of patients above that threshold survived longer than 30 days and might have benefitted from surgery. The tool is available here: https://s-spire-clintools.shinyapps.io/hip_deploy/ .

CONCLUSION

The models of mortality and complications we developed may be accurate enough for some uses, especially personalizing informed consent and shared decision-making with patient-specific risk estimates. However, the high false discovery rate suggests the models should not be used to restrict access to surgery for high-risk patients. Deciding which measures of accuracy to prioritize and what is "accurate enough" depends on the clinical question and use of the predictions. Discrimination and calibration are commonly used measures of overall model accuracy but may be poorly suited to certain clinical questions and applications. Clinically, overall accuracy may not be as important as knowing how accurate and useful specific values of predicted risk are for specific purposes.Level of Evidence Level III, therapeutic study.

Artificial intelligence for prediction of donor liver allograft steatosis and early post-transplantation graft failure

BACKGROUND

Donor livers undergo subjective pathologist review of steatosis before transplantation to mitigate the risk for early allograft dysfunction (EAD). We developed an objective, computer vision artificial intelligence (CVAI) platform to score donor liver steatosis and compared its capability for predicting EAD against pathologist steatosis scores.

METHODS

Two pathologists scored digitized donor liver biopsy slides from 2014 to 2019. We trained four CVAI platforms with 1:99 training:prediction split. Mean intersection-over-union (IU) characterized CVAI model accuracy. We defined EAD using liver function tests within 1 week of transplantation. We calculated separate EAD logistic regression models with CVAI and pathologist steatosis and compared the models' discrimination and internal calibration.

RESULTS

From 90 liver biopsies, 25,494 images trained CVAI models yielding peak mean IU = 0.80. CVAI steatosis scores were lower than pathologist scores (median 3% vs 20%, P < 0.001). Among 41 transplanted grafts, 46% developed EAD. The median CVAI steatosis score was higher for those with EAD (2.9% vs 1.9%, P = 0.02). CVAI steatosis was independently associated with EAD after adjusting for donor age, donor diabetes, and MELD score (aOR = 1.34, 95%CI = 1.03-1.75, P = 0.03).

CONCLUSION

The CVAI steatosis EAD model demonstrated slightly better calibration than pathologist steatosis, meriting further investigation into which modality most accurately and reliably predicts post-transplantation outcomes.

Trends in US Surgical Procedures and Health Care System Response to Policies Curtailing Elective Surgical Operations During the COVID-19 Pandemic

IMPORTANCE

The COVID-19 pandemic has affected every aspect of medical care, including surgical treatment. It is critical to understand the association of government policies and infection burden with surgical access across the United States.

OBJECTIVE

To describe the change in surgical procedure volume in the US after the government-suggested shutdown and subsequent peak surge in volume of patients with COVID-19.

DESIGN, SETTING, AND PARTICIPANTS

This retrospective cohort study was conducted using administrative claims from a nationwide health care technology clearinghouse. Claims from pediatric and adult patients undergoing surgical procedures in 49 US states within the Change Healthcare network of health care institutions were used. Surgical procedure volume during the 2020 initial COVID-19-related shutdown and subsequent fall and winter infection surge were compared with volume in 2019. Data were analyzed from November 2020 through July 2021.

EXPOSURES

2020 policies to curtail elective surgical procedures and the incidence rate of patients with COVID-19.

MAIN OUTCOMES AND MEASURES

Incidence rate ratios (IRRs) were estimated from a Poisson regression comparing total procedure counts during the initial shutdown (March 15 to May 2, 2020) and subsequent COVID-19 surge (October 22, 2020-January 31, 2021) with corresponding 2019 dates. Surgical procedures were analyzed by 11 major procedure categories, 25 subcategories, and 12 exemplar operative procedures along a spectrum of elective to emergency indications.

RESULTS

A total of 13 108 567 surgical procedures were identified from January 1, 2019, through January 30, 2021, based on 3498 Current Procedural Terminology (CPT) codes. This included 6 651 921 procedures in 2019 (3 516 569 procedures among women [52.9%]; 613 192 procedures among children [9.2%]; and 1 987 397 procedures among patients aged ≥65 years [29.9%]) and 5 973 573 procedures in 2020 (3 156 240 procedures among women [52.8%]; 482 637 procedures among children [8.1%]; and 1 806 074 procedures among patients aged ≥65 years [30.2%]). The total number of procedures during the initial shutdown period and its corresponding period in 2019 (ie, epidemiological weeks 12-18) decreased from 905 444 procedures in 2019 to 458 469 procedures in 2020, for an IRR of 0.52 (95% CI, 0.44 to 0.60; P < .001) with a decrease of 48.0%. There was a decrease in surgical procedure volume across all major categories compared with corresponding weeks in 2019. During the initial shutdown, otolaryngology (ENT) procedures (IRR, 0.30; 95% CI, 0.13 to 0.46; P < .001) and cataract procedures (IRR, 0.11; 95% CI, -0.11 to 0.32; P = .03) decreased the most among major categories. Organ transplants and cesarean deliveries did not differ from the 2019 baseline. After the initial shutdown, during the ensuing COVID-19 surge, surgical procedure volumes rebounded to 2019 levels (IRR, 0.97; 95% CI, 0.95 to 1.00; P = .10) except for ENT procedures (IRR, 0.70; 95% CI, 0.65 to 0.75; P < .001). There was a correlation between state volumes of patients with COVID-19 and surgical procedure volume during the initial shutdown (r = -0.00025; 95% CI, -0.0042 to -0.0009; P = .003), but there was no correlation during the COVID-19 surge (r = -0.00034; 95% CI, -0.0075 to 0.00007; P = .11).

CONCLUSIONS AND RELEVANCE

This study found that the initial shutdown period in March through April 2020, was associated with a decrease in surgical procedure volume to nearly half of baseline rates. After the reopening, the rate of surgical procedures rebounded to 2019 levels, and this trend was maintained throughout the peak burden of patients with COVID-19 in fall and winter; these findings suggest that after initial adaptation, health systems appeared to be able to self-regulate and function at prepandemic capacity.

Spatiotemporal variation in the fecal microbiota of mule deer is associated with proximate and future measures of host health

Background

Mule deer rely on fat and protein stored prior to the winter season as an energy source during the winter months when other food sources are sparse. Since associated microorganisms (‘microbiota’) play a significant role in nutrient metabolism of their hosts, we predicted that variation in the microbiota might be associated with nutrient storage and overwintering in mule deer populations. To test this hypothesis we performed a 16S rRNA marker gene survey of fecal samples from two deer populations in the western United States before and after onset of winter.

Results

PERMANOVA analysis revealed the deer microbiota varied interactively with geography and season. Further, using metadata collected at the time of sampling, we were able to identify different fecal bacterial taxa that could potentially act as bioindicators of mule deer health outcomes. First, we identified the abundance of Collinsella (family: Coriobacteriaceae) reads as a possible predictor of poor overwintering outcomes for deer herds in multiple locations. Second, we showed that reads assigned to the Bacteroides and Mollicutes Order RF39 were both positively correlated with deer protein levels, leading to the idea that these sequences might be useful in predicting mule deer protein storage.

Conclusions

These analyses confirm that variation in the microbiota is associated with season-dependent health outcomes in mule deer, which may have useful implications for herd management strategies.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12917-021-02972-0.

Patient-reported distress and age-related stress biomarkers among colorectal cancer patients

OBJECTIVE

Distress among cancer patients has been broadly accepted as an important indicator of well-being but has not been well studied. We investigated patient characteristics associated with high distress levels as well as correlations among measures of patient-reported distress and "objective" stress-related biomarkers among colorectal cancer patients.

METHODS

In total, 238 patients with colon or rectal cancer completed surveys including the Distress Thermometer, Problem List, and the Hospital Anxiety and Depression Scale. We abstracted demographic and clinical information from patient charts and determined salivary cortisol level and imaging-based sarcopenia. We evaluated associations between patient characteristics (demographics, clinical factors, and psychosocial and physical measures) and three outcomes (patient-reported distress, cortisol, and sarcopenia) with Spearman's rank correlations and multivariable linear regression. The potential moderating effect of age was separately investigated by including an interaction term in the regression models.

RESULTS

Patient-reported distress was associated with gender (median: women 5.0, men 3.0, p < 0.001), partnered status (single 5.0, partnered 4.0, p = 0.018), and cancer type (rectal 5.0, colon 4.0, p = 0.026); these effects varied with patient age. Cortisol level was associated with "emotional problems" (ρ = 0.34, p = 0.030), anxiety (ρ = 0.46, p = 0.006), and depression (ρ = 0.54, p = 0.001) among younger patients. We found no significant associations between patient-reported distress, salivary cortisol, and sarcopenia.

CONCLUSIONS

We found that young, single patients reported high levels of distress compared to other patient groups. Salivary cortisol may have limited value as a cancer-related stress biomarker among younger patients, based on association with some psychosocial measures. Stress biomarkers may not be more clinically useful than patient-reported measures in assessing distress among colorectal cancer patients.