Deep learning model integrating radiologic and clinical data to predict mortality after ischemic stroke.

Objective: Most prognostic indexes for ischemic stroke mortality lack radiologic information. We aimed to create and validate a deep learning-based mortality prediction model using brain diffusion weighted imaging (DWI), apparent diffusion coefficient (ADC), and clinical factors. Methods: Data from patients with ischemic stroke who admitted to tertiary hospital during acute periods from 2013 to 2019 were collected and split into training (n = 1109), validation (n = 437), and internal test (n = 654). Data from patients from secondary cardiovascular center was used for external test set (n = 507). The algorithm for predicting mortality, based on DWI and ADC (DLP_DWI), was initially trained. Subsequently, important clinical factors were integrated into this model to create the integrated model (DLP_INTG). The performance of DLP_DWI and DLP_INTG was evaluated by using time-dependent area under the receiver operating characteristic curves (TD AUCs) and Harrell concordance index (C-index) at one-year mortality. Results: The TD AUC of DLP_DWI was 0.643 in internal test set, and 0.785 in the external dataset. DLP_INTG had a higher performance at predicting one-year mortality than premise score in internal dataset (TD- AUC: 0.859 vs. 0.746; p = 0.046), and in external dataset (TD- AUC: 0.876 vs. 0.808; p = 0.007). DLP_DWI and DLP_INTG exhibited strong discrimination for the high-risk group for one-year mortality. Interpretation: A deep learning model using brain DWI, ADC and the clinical factors was capable of predicting mortality in patients with ischemic stroke.

Combining clinical and imaging data for predicting functional outcomes after acute ischemic stroke: an automated machine learning approach.

This study aimed to develop and validate an automated machine learning (ML) system that predicts 3-month functional outcomes in acute ischemic stroke (AIS) patients by combining clinical and neuroimaging features. Functional outcomes were categorized as unfavorable (modified Rankin Scale ≥ 3) or not. A clinical model employing optimal clinical features (Model_A), a convolutional neural network model incorporating imaging data (Model_B), and an integrated model combining both imaging and clinical features (Model_C) were developed and tested to predict unfavorable outcomes. The developed models were compared with each other and with traditional risk-scoring models. The dataset comprised 4147 patients from a multicenter stroke registry, with 1268 (30.6%) experiencing unfavorable outcomes. Age, initial NIHSS, and early neurologic deterioration were identified as the most important clinical features. The ML model prediction achieved an area under the curves of 0.757 (95% CI 0.726-0.789) for Model_A, 0.725 (95% CI 0.693-0.755) for Model_B, and 0.786 (95% CI 0.757-0.814) for Model_C in the test set. The integrated models outperformed traditional risk-scoring models by 0.21 (95% CI 0.16-0.25) for HIAT and 0.15 (95% CI 0.11-0.19) for THRIVE. In conclusion, the integrated ML system enhanced stroke outcome prediction by combining imaging data and clinical features, outperforming traditional risk-scoring models.

A Deep Learning Model Using Chest Radiographs for Prediction of 30-Day Mortality in Patients With Community-Acquired Pneumonia: Development and External Validation.

BACKGROUND. Chest radiography is an essential tool for diagnosing community-acquired pneumonia (CAP), but it has an uncertain prognostic role in the care of patients with CAP. OBJECTIVE. The purpose of this study was to develop a deep learning (DL) model to predict 30-day mortality from diagnosis among patients with CAP by use of chest radiographs to validate the performance model in patients from different time periods and institutions. METHODS. In this retrospective study, a DL model was developed from data on 7105 patients from one institution from March 2013 to December 2019 (3:1:1 allocation to training, validation, and internal test sets) to predict the risk of all-cause mortality within 30 days after CAP diagnosis by use of patients' initial chest radiographs. The DL model was evaluated in a cohort of patients diagnosed with CAP during emergency department visits at the same institution from January 2020 to March 2020 (temporal test cohort [n = 947]) and in two additional cohorts from different institutions (external test cohort A [n = 467], January 2020 to December 2020; external test cohort B [n = 381], March 2019 to October 2021). AUCs were compared between the DL model and an established risk prediction tool based on the presence of confusion, blood urea nitrogen level, respiratory rate, blood pressure, and age 65 years or older (CURB-65 score). The combination of CURB-65 score and DL model was evaluated with a logistic regression model. RESULTS. The AUC for predicting 30-day mortality was significantly larger (p < .001) for the DL model than for CURB-65 score in the temporal test set (0.77 vs 0.67). The larger AUC for the DL model than for CURB-65 score was not significant (p > .05) in external test cohort A (0.80 vs 0.73) or external test cohort B (0.80 vs 0.72). In the three cohorts, the DL model, in comparison with CURB-65 score, had higher (p < .001) specificity (range, 61-69% vs 44-58%) at the sensitivity of CURB-65 score. The combination of DL model and CURB-65 score, in comparison with CURB-65 score, yielded a significant increase in AUC in the temporal test cohort (0.77, p < .001) and external test cohort B (0.80, p = .04) and a nonsignificant increase in AUC in external test cohort A (0.80, p = .16). CONCLUSION. A DL-based model consisting of initial chest radiographs was predictive of 30-day mortality among patients with CAP with improved performance over CURB-65 score. CLINICAL IMPACT. The DL-based model may guide clinical decision-making in the care of patients with CAP.

Conservation and transmission of seed bacterial endophytes across generations following crossbreeding and repeated inbreeding of rice at different geographic locations.

There are comparatively diverse bacterial communities inside seeds, which are vertically transmitted and conserved, becoming sources of endophytes in the next generation of host plants. We studied how rice seed endophyte composition changed over time following crossbreeding, repeated inbreeding, subsequent human selection and planting of different rice seeds in different ecogeographical locations. Using terminal-restriction fragment length polymorphism analysis to study bacterial communities, we observed that diversity between the original parents and their offspring may show significant differences in richness, evenness and diversity indices. Heat maps reveal substantial contributions of both or either parent in the shaping of the bacterial seed endophytes of the offspring. Most of the terminal restriction fragments (T-RFs) of the subsequent progeny could be traced to any or both of its parents while unique T-RFs of the offspring suggest external sources of colonization particularly when the seeds were cultivated in different locations. Many similar groups of endophytic bacteria persist in the seeds even after recultivation in different locations, indicating resilience to environmental changes and conservation of bacteria across generations. This study suggests that parent plants contributed to the shaping of seed bacterial endophytes of their offspring, although it is also possible that these soil grown rice plants recruit similar populations of endophytes from the soil generation after generation. This study also highlights some bacterial groups belonging to Herbaspirillum, Microbacterium, Curtobacterium, Stenotrophomonas, Xanthomonas and Enterobacter that may be part of a transmitted and conserved "core microbiota" that are ubiquitous and dominant members of the endophytic communities of the rice seeds.

Intravascular large B cell lymphoma: proposed of the strategy for early diagnosis and treatment of patients with rapid deteriorating condition.

We summarize our experience and propose methods for early diagnosis and treatment of intravascular large B cell lymphoma (IVL). A total of 16 patients with IVL between 1994 and 2007 were included and analyzed in this study. Predicted survival durations were short until September 2003. However, there have been marked improvement since the introduction of rituximab, and all patients responded to treatment and survived for more than 1 year following diagnosis of IVL. We propose an early clinical diagnostic strategy for starting treatment for IVL patients with quite poor performance status (PS) and in whom time is a limiting factor: (1) age >40 years, (2) fever above 38 degrees C with poor PS (ECOG 2-4), (3) lactate dehydrogenase (LDH) more than twice the upper limit of the normal level and/or sIL2R >5,000 IU/ml in serum, (4) worsening PS and/or elevation of serum LDH on a daily basis, and (5) confirmation of pathological lymphoid cells in peripheral blood or bone marrow smear and/or flow cytometry. Although accurate pathological diagnosis is quite important, time is a limiting factor for most of IVL patients. In such cases, we can start chemotherapy based on early clinical diagnostic strategy with high sensitivity and obtain good clinical outcome.