Comparing regression modeling strategies for predicting hometime

Association Between Time to Treatment With Endovascular Thrombectomy and Home-Time After Acute Ischemic Stroke

BACKGROUND AND OBJECTIVES

Home-time is a patient-prioritized stroke outcome that can be derived from administrative data linkages. The effect of faster time-to-treatment with endovascular thrombectomy (EVT) on home-time after acute stroke is unknown.

METHODS

We used the Quality Improvement and Clinical Research registry to identify a cohort of patients who received EVT for acute ischemic stroke between 2015 and 2022 in Alberta, Canada. We calculated days at home in the first 90 days after stroke. We used ordinal regression across 6 ordered categories of home-time to evaluate the association between onset-to-arterial puncture and higher home-time, adjusting for age, sex, rural residence, NIH Stroke Scale, comorbidities, intravenous thrombolysis, and year of treatment. We used restricted cubic splines to assess the nonlinear relationship between continuous variation in time metrics and higher home-time, and also reported the adjusted odds ratios within time categories. We additionally evaluated door-to-puncture and reperfusion times. Finally, we analyzed home-time with zero-inflated models to determine the minutes of earlier treatment required to gain 1 day of home-time.

RESULTS

We had 1,885 individuals in our final analytic sample. There was a nonlinear increase in home-time with faster treatment when EVT was within 4 hours of stroke onset or 2 hours of hospital arrival. There was a higher odds of achieving more days at home when onset-to-puncture time was <2 hours (adjusted odds ratio 2.36, 95% CI 1.77-3.16) and 2 to <4 hours (1.37, 95% CI 1.11-1.71) compared with ≥6 hours, and when door-to-puncture time was <1 hour (aOR 2.25, 95% CI 1.74-2.90), 1 to <1.5 hours (aOR 1.89, 95% CI 1.47-2.41), and 1.5 to <2 hours (1.35, 95% CI 1.04-1.76) compared with ≥2 hours. Results were consistent for reperfusion times. For every hour of faster treatment within 6 hours of stroke onset, there was an estimated increase in home-time of 4.7 days, meaning that approximately 1 day of home-time was gained for each 12.8 minutes of faster treatment.

DISCUSSION

Faster time-to-treatment with EVT for acute stroke was associated with greater home-time, particularly within 4 hours of onset-to-puncture and 2 hours of door-to-puncture time. Within 6 hours of stroke onset, each 13 minutes of faster treatment is associated with a gain of 1 day of home-time.

Age-Specific Association of Co-Morbidity With Home-Time After Acute Stroke

OBJECTIVE

To examine the association of co-morbidity with home-time after acute stroke and whether the association is influenced by age.

METHODS

We conducted a province-wide study using linked administrative databases to identify all admissions for first acute ischemic stroke or intracerebral hemorrhage between 2007 and 2018 in Alberta, Canada. We used ischemic stroke-weighted Charlson Co-morbidity Index of 3 or more to identify those with severe co-morbidity. We used zero-inflated negative binomial models to determine the association of severe co-morbidity with 90-day and 1-year home-time, and logistic models for achieving ≥ 80 out of 90 days of home-time, assessing for effect modification by age and adjusting for sex, stroke type, comprehensive stroke center care, hypertension, atrial fibrillation, year of study, and separately adjusting for estimated stroke severity. We also evaluated individual co-morbidities.

RESULTS

Among 28,672 patients in our final cohort, severe co-morbidity was present in 27.7% and was associated with lower home-time, with a greater number of days lost at younger age (-13 days at age < 60 compared to -7 days at age 80+ years for 90-day home-time; -69 days at age < 60 compared to -51 days at age 80+ years for 1-year home-time). The reduction in probability of achieving ≥ 80 days of home-time was also greater at younger age (-22.7% at age < 60 years compared to -9.0% at age 80+ years). Results were attenuated but remained significant after adjusting for estimated stroke severity and excluding those who died. Myocardial infarction, diabetes, and cancer/metastases had a greater association with lower home-time at younger age, and those with dementia had the greatest reduction in home time.

CONCLUSION

Severe co-morbidity in acute stroke is associated with lower home-time, more strongly at younger age.

Data-driven decision-making for precision diagnosis of digestive diseases

Modern omics technologies can generate massive amounts of biomedical data, providing unprecedented opportunities for individualized precision medicine. However, traditional statistical methods cannot effectively process and utilize such big data. To meet this new challenge, machine learning algorithms have been developed and applied rapidly in recent years, which are capable of reducing dimensionality, extracting features, organizing data and forming automatable data-driven clinical decision systems. Data-driven clinical decision-making have promising applications in precision medicine and has been studied in digestive diseases, including early diagnosis and screening, molecular typing, staging and stratification of digestive malignancies, as well as precise diagnosis of Crohn's disease, auxiliary diagnosis of imaging and endoscopy, differential diagnosis of cystic lesions, etiology discrimination of acute abdominal pain, stratification of upper gastrointestinal bleeding (UGIB), and real-time diagnosis of esophageal motility function, showing good application prospects. Herein, we reviewed the recent progress of data-driven clinical decision making in precision diagnosis of digestive diseases and discussed the limitations of data-driven decision making after a brief introduction of methods for data-driven decision making.

Machine learning-assisted analysis for agronomic dataset of 49 Balangu (Lallemantia iberica L.) ecotypes from different regions of Iran

The Balangu (Lallemantia iberica) species have a high gastronomical impact in the Middle East and Balkan region. It is widely used in the local food industry, such as confectionery, edible oil, and protein food. In this study, 49 ecotypes were collected from different regions of Iran. 37 agronomic traits were measured during the growing season and at harvest time. To find the correlation between the grain yield per unit area, grain yield per single plant (GYSP), oil percent (OP), and protein percent (PP) with other measured traits, which these were utilized as the labels of different machine learning (ML) procedures including Linear Regression (LR), Support Vector Regression (SVR), Random Forest Regression (RFR), and Gradient Boosting Decision Tree Regression (GBDTR). It was observed that there is a linear relationship between the measured agronomic traits and the considered labels. So, the LR, RFR, and GBDTR models showed the lowest mean absolute error, mean square error, and root mean square error than SVR models and good prediction ability of the test data. Although, the RFR and GBDTR have naturally lower bias than other methods in this study, but the GBDTR scheme is preferred because of the over-fitting shortcoming of the RFR technique. The GBDTR method showed better results rather than the other ML regression methods according to the RMSE 3.302, 0.040, 0.028, and 0.060 for GYUA, GYSP, OP, and PP, respectively.

Identification of a Metabolic Reprogramming-Associated Risk Model Related to Prognosis, Immune Microenvironment, and Immunotherapy of Stomach Adenocarcinoma

Stomach adenocarcinoma (STAD) is one of the most common malignant digestive tumors. Metabolic reprogramming is an essential feature of tumorigenesis. The roles of metabolic reprogramming in STAD patients were investigated to explore the tumor immune microenvironment (TME) and potential therapeutic strategies. STAD samples' transcriptomic and clinical data were collected from The Cancer Genome Atlas (TCGA) set and the GSE84437 set. The signature based on the metabolism-related genes (MRGs) was built using the Cox regression model to predict prognosis in STAD. Notably, this MRG-based signature (MRGS) accurately predicted STAD patients' clinical survival in multiple datasets and could serve as an indicator independently. STAD patients with high scores on the MRGS were eligible for generating a type I/II interferon (IFN) response, according to a complete examination of the link between the MRGS and TME. Tumor Immune Dysfunction and Exclusion (TIDE) and immunophenoscore (IPS) analyses revealed that STAD patients with different MRGS scores had different reactions to immunotherapy. Consequently, assessing the pattern of these MRGs increases the understanding of TME features in STAD, hence directing the development of successful immunotherapy regimens.

Machine learning-enabled optimization of extrusion-based 3D printing

Machine learning (ML) and three-dimensional (3D) printing are among the fastest-growing branches of science. While ML can enable computers to independently learn from available data to make decisions with minimal human intervention, 3D printing has opened up an avenue for modern, multi-material, manufacture of complex 3D structures with a rapid turn-around ability for users with limited manufacturing experience. However, the determination of optimum printing parameters is still a challenge, increasing pre-printing process time and material wastage. Here, we present the first integration of ML and 3D printing through an easy-to-use graphical user interface (GUI) for printing parameter optimization. Unlike the widely held orthogonal design used in most of the 3D printing research, we, for the first time, used nine different computer-aided design (CAD) images and in order to enable ML algorithms to distinguish the difference between designs, we devised a self-designed method to calculate the "complexity index" of CAD designs. In addition, for the first time, the similarity of the print outcomes and CAD images are measured using four different self-designed labeling methods (both manually and automatically) to figure out the best labeling method for ML purposes. Subsequently, we trained eight ML algorithms on 224 datapoints to identify the best ML model for 3D printing applications. The "gradient boosting regression" model yields the best prediction performance with an R-2 score of 0.954. The ML-embedded GUI developed in this study enables users (either skilled or unskilled in 3D printing and/or ML) to simply upload a design (desired to print) to the GUI along with desired printing temperature and pressure to obtain the approximate similarity in the case of actual 3D printing of the uploaded design. This ultimately can prevent error-and-trial steps prior to printing which in return can speed up overall design-to-end-product time with less material waste and more cost-efficiency.

Prediction of 90 day home time among patients with low baseline ASPECTS undergoing endovascular thrombectomy: results from Alberta's Provincial Stroke Registry (QuICR)

BACKGROUND

The benefit of endovascular thrombectomy (EVT) in stroke patients with a low baseline Alberta Stroke Program Early CT Score (ASPECTS, ≤5) is uncertain. We aim to use random forest regression modeling to predict 90 day home time in patients with low ASPECTS.

METHODS

We used the Quality Improvement and Clinical Research (QuICR) provincial stroke registry and administrative data from southern Alberta to identify patients who underwent EVT in our center from July 2015 to November 2020. Baseline ASPECTS on non-contrast CT and CT angiography data were scored by a two physician consensus. The primary outcome was the predicted 90 day home time (the number of nights a patient is back at their premorbid living situation without an increase in level of care within 90 days of the stroke) using random forests regression. Estimates were generated using 200 bootstrapped datasets. Covariate contribution to home time was determined using partial dependence plots.

RESULTS

Of 657 EVT patients, 85 (12.9%) had baseline ASPECTS ≤5 (mean age 70.9 years, 44.7% women, 93.9% good-moderate collaterals, 60% M1-middle cerebral artery occlusion). Using partial dependence estimates, mean predicted home times were similar in the low ASPECTS (44.3 days) versus higher ASPECTS (43.1) groups. Factors predicting lower 90 day home time in this population were diabetes mellitus (-8.8 days), hypertension (-5.7 days), and atrial fibrillation (-3.6 days). There was no meaningful difference in predicted 90 day home time by sex, baseline National Institutes of Health Stroke Severity Scale score, occlusion site, tandem lesion, collateral grade or thrombolysis.

CONCLUSIONS

Patients with low ASPECTS who are selected for EVT using demographic and clinical profiles similar to higher ASPECTS patients achieved comparable outcomes.

The Allure of Big Data to Improve Stroke Outcomes: Review of Current Literature

PURPOSE OF REVIEW

To critically appraise literature on recent advances and methods using "big data" to evaluate stroke outcomes and associated factors.

RECENT FINDINGS

Recent big data studies provided new evidence on the incidence of stroke outcomes, and important emerging predictors of these outcomes. Main highlights included the identification of COVID-19 infection and exposure to a low-dose particulate matter as emerging predictors of mortality post-stroke. Demographic (age, sex) and geographical (rural vs. urban) disparities in outcomes were also identified. There was a surge in methodological (e.g., machine learning and validation) studies aimed at maximizing the efficiency of big data for improving the prediction of stroke outcomes. However, considerable delays remain between data generation and publication. Big data are driving rapid innovations in research of stroke outcomes, generating novel evidence for bridging practice gaps. Opportunity exists to harness big data to drive real-time improvements in stroke outcomes.

Perspectives on Home Time and Its Association With Quality of Life After Inpatient Surgery Among US Veterans

IMPORTANCE

Home time, defined as time spent at home after hospital discharge, is emerging as a novel, patient-oriented outcome in stroke recovery and end-of-life care. Longer home time is associated with lower mortality and higher patient satisfaction. However, a knowledge gap exists in the measurement and understanding of home time in the population undergoing surgery.

OBJECTIVES

To examine the association between postoperative home time and quality of life (QoL), functional status, and decisional regret and to identify themes regarding the meaning of time spent at home after surgery.

DESIGN, SETTING, AND PARTICIPANTS

This mixed-methods study including a survey and qualitative interviews used an explanatory sequential design involving 152 quantitative surveys followed by in-depth interviews with 12 participants from February 26, 2020, to December 17, 2020. US veterans older than 65 years who underwent inpatient surgery at a single-center veterans hospital within the prior 6 to 12 months were studied.

EXPOSURES

Quality of life, measured by the Veterans RAND 12-item Health Survey and 19-item Control, Autonomy, Self-realization, and Pleasure scale; functional status, measured by activities of daily living (ADL) and instrumental ADL scales; and regret, measured by the Decision Regret Scale.

MAIN OUTCOMES AND MEASURES

Home time, standardized as percentage of total time spent at home from the time of surgery to the time of survey administration. Associations between home time and QoL, function, and decisional regret in the survey data were analyzed using Spearman correlation in the overall cohort and in operative stress score subcohorts (1-2 [low] vs 3-5 [high]) in a stratified analysis. The 12 semistructured interviews were analyzed to elicit patients' perspectives on home time in postoperative recovery. Qualitative data were coded and analyzed using content and thematic analysis and integrated with quantitative data in joint displays.

RESULTS

A total of 152 patients (mean [SD] age, 72.3 [4.4] years; 146 [96.0%] male) were surveyed, and 12 patients (mean [SD] age, 72.3 [4.8] years; 11 [91.7%] male) were interviewed. The median time to survey completion was 307 days (IQR, 265-344 days). The median home time was 97.8% (IQR, 94.6%-98.6%; range, 22.2%-99.5%). Increased home time was associated with better physical health-related QoL in the Veterans RAND 12-item Health Survey (r = 0.33; 95% CI, 0.18-0.47; P < .001) and higher ADL scores (r = 0.21; 95% CI, 0.06-0.36; P = .008) and instrumental ADL functional scores (r = 0.21; 95% CI, 0.04-0.37; P = .009). Decisional regret was inversely associated with home time in only the high operative stress score subcohort (r = -0.22; 95% CI, -0.47 to -0.04; P = .047). Home was perceived as a safe and familiar environment that accelerated recovery through nurturing support of loved ones.

CONCLUSIONS AND RELEVANCE

In this mixed-methods study including a survey and qualitative interviews, increased home time in the first year after major surgery was associated with improved daily function and physical QoL among US veterans. Interviewees considered the transition to home to be an indicator of recovery, suggesting that home time may be a promising, patient-oriented quality outcome measure for surgical recovery that warrants further study.

A Machine Learning Approach to Identify Predictors of Frequent Vaping and Vulnerable Californian Youth Subgroups

INTRODUCTION

Machine learning presents a unique opportunity to improve electronic cigarette (vaping) monitoring in youth. Here we built a random forest model to predict frequent vaping status among Californian youth and to identify contributing factors and vulnerable populations.

METHODS

In this prospective cohort study, 1,281 ever-vaping twelfth-grade students from metropolitan Los Angeles were surveyed in Fall and in 6-month in Spring. Frequent vaping was measured at the 6-month follow-up as nicotine-containing vaping on 20 or more days in past 30 days. Predictors (n=131) encompassed sociodemographic characteristics, substance use and perceptions, health status, and characteristics of the household, school and neighborhood. A random forest was developed to identify the top ten predictors of frequent vaping and interactions by sociodemographic variables.

RESULTS

Forty participants (3.1%) reported frequent vaping at the follow-up. The random forest outperformed a logistic regression model in prediction (C-Index=0.87 vs. 0.77). Higher past-month nicotine concentration in vape, more daily vaping sessions, and greater nicotine dependence were the top three of the ten most important predictors of frequent vaping. Interactions were found between age and perceived discrimination, and between age and race/ethnicity, as those who were younger than their classmates and either reported experiencing discrimination frequently or identified as Asian or Native American/Pacific Islander were at increased risk of becoming frequent vapers.

CONCLUSIONS

Machine learning can produce models that accurately predict progression of vaping behaviours among youth. The potential association between frequent vaping and perceived discrimination warrants more in-depth analyses to confirm if discrimination constitutes a cause of increased vaping.