Artificial intelligence-assisted interpretation of systolic function by echocardiogram.

OBJECTIVE: Precise and reliable echocardiographic assessment of left ventricular ejection fraction (LVEF) is needed for clinical decision-making. Recently, artificial intelligence (AI) models have been developed to estimate LVEF accurately. The aim of this study was to evaluate whether an AI model could estimate an expert read of LVEF and reduce the interinstitutional variability of level 1 readers with the AI-LVEF displayed on the echocardiographic screen. METHODS: This prospective, multicentre echocardiographic study was conducted by five cardiologists of level 1 echocardiographic skill (minimum level of competency to interpret images) from different hospitals. Protocol 1: Visual LVEFs for the 48 cases were measured without input from the AI-LVEF. Protocol 2: the 48 cases were again shown to all readers with inclusion of AI-LVEF data. To assess the concordance and accuracy with or without AI-LVEF, each visual LVEF measurement was compared with an average of the estimates by five expert readers as a reference. RESULTS: A good correlation was found between AI-LVEF and reference LVEF (r=0.90, p<0.001) from the expert readers. For the classification LVEF, the area under the curve was 0.95 on heart failure with preserved EF and 0.96 on heart failure reduced EF. For the precision, the SD was reduced from 6.1±2.3 to 2.5±0.9 (p<0.001) with AI-LVEF. For the accuracy, the root-mean squared error was improved from 7.5±3.1 to 5.6±3.2 (p=0.004) with AI-LVEF. CONCLUSIONS: AI can assist with the interpretation of systolic function on an echocardiogram for level 1 readers from different institutions.

Deep learning approach for analyzing chest x-rays to predict cardiac events in heart failure.

Background: A deep learning (DL) model based on a chest x-ray was reported to predict elevated pulmonary artery wedge pressure (PAWP) as heart failure (HF). Objectives: The aim of this study was to (1) investigate the role of probability of elevated PAWP for the prediction of clinical outcomes in association with other parameters, and (2) to evaluate whether probability of elevated PAWP based on DL added prognostic information to other conventional clinical prognostic factors in HF. Methods: We evaluated 192 patients hospitalized with HF. We used a previously developed AI model to predict HF and calculated probability of elevated PAWP. Readmission following HF and cardiac mortality were the primary endpoints. Results: Probability of elevated PAWP was associated with diastolic function by echocardiography. During a median follow-up period of 58 months, 57 individuals either died or were readmitted. Probability of elevated PAWP appeared to be associated with worse clinical outcomes. After adjustment for readmission score and laboratory data in a Cox proportional-hazards model, probability of elevated PAWP at pre-discharge was associated with event free survival, independent of elevated left atrial pressure (LAP) based on echocardiographic guidelines (p < 0.001). In sequential Cox models, a model based on clinical data was improved by elevated LAP (p = 0.005), and increased further by probability of elevated PAWP (p < 0.001). In contrast, the addition of pulmonary congestion interpreted by a doctor did not statistically improve the ability of a model containing clinical variables (compared p = 0.086). Conclusions: This study showed the potential of using a DL model on a chest x-ray to predict PAWP and its ability to add prognostic information to other conventional clinical prognostic factors in HF. The results may help to enhance the accuracy of prediction models used to evaluate the risk of clinical outcomes in HF, potentially resulting in more informed clinical decision-making and better care for patients.

Deep Learning for Detection of Exercise-Induced Pulmonary Hypertension Using Chest X-Ray Images.

Background: Stress echocardiography is an emerging tool used to detect exercise-induced pulmonary hypertension (EIPH). However, facilities that can perform stress echocardiography are limited by issues such as cost and equipment. Objective: We evaluated the usefulness of a deep learning (DL) approach based on a chest X-ray (CXR) to predict EIPH in 6-min walk stress echocardiography. Methods: The study enrolled 142 patients with scleroderma or mixed connective tissue disease with scleroderma features who performed a 6-min walk stress echocardiographic test. EIPH was defined by abnormal cardiac output (CO) responses that involved an increase in mean pulmonary artery pressure (mPAP). We used the previously developed AI model to predict PH and calculated PH probability in this cohort. Results: EIPH defined as ΔmPAP/ΔCO >3.3 and exercise mPAP >25 mmHg was observed in 52 patients, while non-EIPH was observed in 90 patients. The patients with EIPH had a higher mPAP at rest than those without EIPH. The probability of PH based on the DL model was significantly higher in patients with EIPH than in those without EIPH. Multivariate analysis showed that gender, mean PAP at rest, and the probability of PH based on the DL model were independent predictors of EIPH. A model based on baseline parameters (age, gender, and mPAP at rest) was improved by adding the probability of PH predicted by the DL model (AUC: from 0.65 to 0.74; p = 0.046). Conclusion: Applying the DL model based on a CXR may have a potential for detection of EIPH in the clinical setting.

The entry of cucumber mosaic virus into cucumber xylem is facilitated by co-infection with zucchini yellow mosaic virus.

We investigated the synergistic effects of co-infection by zucchini yellow mosaic virus (ZYMV) and cucumber mosaic virus (CMV) on viral distribution in the vascular tissues of cucumber. Immunohistochemical observations indicated that ZYMV was present in both the phloem and xylem tissues. ZYMV-RNA was detected in both the xylem wash and guttation fluid of ZYMV-inoculated cucumber. Steam treatment at a stem internode indicated that ZYMV enters the xylem vessels and moves through them but does not cause systemic infection in the plant. CMV distribution in singly infected cucumbers was restricted to phloem tissue. By contrast, CMV was detected in the xylem tissue of cotyledons in plants co-infected with CMV and ZYMV. Although both ZYMV-RNA and CMV-RNA were detected in the xylem wash and upper internodes of steam-treated, co-infected cucumbers grown at 24 °C, neither virus was detected in the upper leaves using an ELISA assay. Genetically modified CMV harboring the ZYMV HC-Pro gene was distributed in the xylem and phloem tissues of singly inoculated cucumber cotyledons. These results indicate that the ZYMV HC-Pro gene facilitates CMV entry into the xylem vessels of co-infected cucumbers.

Cross-protection against bean yellow mosaic virus (BYMV) and clover yellow vein virus by Attenuated BYMV isolate M11.

Attenuated isolate M11 of Bean yellow mosaic virus (BYMV), obtained after exposing BYMV-infected plants to low temperature, and its efficacy in cross-protecting against infection by BYMV isolates from gladiolus, broad bean (Vicia faba) and white clover (Trifolium repens) was assessed with western blotting and reverse transcription-polymerase chain reaction. The level of cross-protection varied depending on the challenge virus isolates. Cross-protection was complete against BYMV isolates from gladiolus, but incomplete against BYMV isolates from other hosts. M11 also partially cross-protected against an isolate of Clover yellow vein virus. A comparison of the nucleotide sequence of M11 and those of BYMV isolates from gladiolus and from other hosts showed higher homology among gladiolus isolates than the homology between gladiolus isolates and nongladiolus isolates. In the phylogenetic trees, constructed using the nucleotide sequences of an overall polyprotein of the genomes, five gladiolus isolates clustered together, completely separated from the three BYMV isolates from other hosts. A comparison of the amino acid sequences between M11 and its parental isolate IbG, and analysis of recombinant infectious clones between M11 and IbG revealed that an amino acid at position 314 was involved in the attenuation of BYMV.

Characterization of silencing suppressor 2b of cucumber mosaic virus based on examination of its small RNA-binding abilities.

Double-stranded (ds) RNAs and imperfect hairpin RNAs of endogenous genes trigger post-transcriptional gene silencing (PTGS) and are cleaved by a Dicer-like nuclease into small interfering RNAs (siRNAs) and microRNs (miRNAs), respectively. Such small RNAs (siRNAs and miRNAs) then guide an RNA-induced silencing complex (RISC) for sequence-specific RNA degradation. While PTGS serves as an antiviral defense in plants, many plant viruses encode suppressors as a counter defense. Here we demonstrate that the PTGS suppressor (2b) of a severe strain (CM95R) of cucumber mosaic virus (CMV) can bind to in vitro synthesized siRNAs and even to long dsRNAs to a lesser extent. However, the 2b suppressor weakly bound to a miRNA (miR171) duplex in contrast to another small RNA-binding suppressor, p19 of tombusvirus that can effectively bind miRNAs. Because the 2b suppressor of an attenuated strain of CMV (CM95), which differs in a single amino acid from the 2b of CM95R, could barely bind siRNAs, we hypothesized that the weak suppressor activity of the attenuated strain resulted from a loss of the siRNA-binding property of 2b via a single amino acid change. Here we consider that 2b interferes with the PTGS pathway by directly binding siRNAs (or long dsRNA).

Effectiveness of an Attenuated Zucchini yellow mosaic virus Isolate for Cross-Protecting Cucumber.

To cross-protect cucumber plants from Zucchini yellow mosaic virus (ZYMV), we used cold treatment to obtain an attenuated isolate of ZYMV, designated ZYMV-2002. ZYMV-2002 was obtained from a virulent ZYMV isolate after repeated low temperature treatment at 12.5 to 15°C followed by five cycles of single-plant transfer. The isolate produced very mild or no symptoms on cucurbit plants. In addition, inoculated cucumber plants had very similar fruit productivity to healthy control plants under field conditions. During field experiments in 2002 and 2003, when other viruses were also present, protected plants significantly suppressed infection with ZYMV, progression of disease severity, and reduction of fruit yield and quality. These results demonstrate that ZYMV-2002 is a potentially useful attenuated ZYMV isolate for reducing the impact of ZYMV.

A New Technique to Select Mild Strains of Cucumber mosaic virus.

An efficient technique to select a good attenuated virus to control Cucumber mosaic virus (CMV) disease was developed. Preliminary screenings were conducted to assess the virulence of virus recovered from dark-green islands and yellow tissues of mosaic leaves of Nicotiana rustica after co-inoculation with an attenuated mutant P2bR46C of CMV and its original severe isolate Pepo. All single-lesion isolates (SLIs) obtained from dark-green islands had the attenuated P2bR46C phenotype, but the SLIs from yellow tissue had either the virulent Pepo or the P2bR46C phenotype. When Pepo-infected N. rustica and tomato plants were grown at 15 or 36°C for 30 days, 17 of 288 SLIs obtained from the treated leaves elicited mosaic and dark-green spots without malformation. Dark-green tissue from each plant infected with 1 of these 17 SLIs then was used to inoculate one plant of N. rustica. All 17 plants had either very mild mosaic or no visible symptoms. One of these potential mild strains, 36R37, had an amino acid substitution on the 2b gene encoding the 2b protein. Isolate 36R37 also was highly cross-protective, and its symptom attenuation was stable for three serial host passages. After cold or heat treatment, the dark-green tissue proved to be a good source for isolating mild strains of the virus.

Cucumber mosaic virus 2b protein compensates for restricted systemic spread of Potato virus Y in doubly infected tobacco.

Tobacco plants (Nicotiana tabacum cv. Xanthi-nc) inoculated with a necrotic strain of Potato virus Y (PVY, T01 isolate) developed necrotic symptoms in some systemically infected leaves, but not in younger leaves. However, PVY expressed distinct symptoms not only in the older leaves, but also in the younger leaves, of plants that had been doubly inoculated with PVY and with Cucumber mosaic virus (CMV, strain Pepo). A tissue blot immunoassay of tissues from various positions of the stem detected PVY weakly in each stem, but not in the shoot apex, of singly infected plants, whereas PVY was detected at high levels in almost all sections of doubly infected plants. CMV was also detected at high levels in sections of singly and doubly infected plants. Immunohistochemistry of stem tissues showed that in singly infected plants, PVY was confined to external phloem cells and was not detected in internal phloem cells. However, in doubly infected plants, PVY was distributed uniformly throughout whole tissues, including the external phloem, xylem parenchyma and internal phloem cells. In plants that were doubly infected with PVY and Pepo Delta 2b, a modified CMV that cannot translate the 2b protein, the spread of PVY was restricted as in singly infected plants. These results suggested that the plant host has a counterdefence mechanism that restricts systemic spread of PVY T01, and that the 2b protein of CMV strain Pepo negates this restriction.