Detection of Left Ventricular Systolic Dysfunction Using an Artificial Intelligence-Enabled Chest X-Ray.

BACKGROUND: Assessment of left ventricular systolic dysfunction provides essential information related to the prognosis and management of cardiovascular diseases. The aim of this study was to develop a deep-learning model to identify left ventricular ejection fraction (LVEF) ≤ 35% via chest X-ray (CXR [CXR-EF≤35%]) features and investigate the performance and clinical implications. METHODS: This study collected 90,547 CXRs with the corresponding LVEF according to transthoracic echocardiography from the outpatient department in an academic medical center. Among these, 77,227 CXRs were used to develop the identification of CXR-EF≤35%. Another 13,320 CXRs were used to validate the performance, which was evaluated by area under the receiver operating characteristic curve (AUC). Furthermore, CXR-EF≤35% was tested to assess the long-term risks of developing LVEF ≤ 35% and cardiovascular outcomes, which were evaluated by Kaplan-Meier survival analysis and the Cox proportional hazards model. RESULTS: The AUCs of CXR-EF≤35% for the detection of LVEF ≤ 35% were 0.888 and 0.867 in the internal and external validation cohorts, respectively. Patients with baseline LVEF > 50% but detected as CXR-EF≤35% were at higher risk of long-term development of LVEF ≤ 35% (hazard ratio, internal validation cohort [HRi] 3.91, 95% CI 2.98-5.14; hazard ratio, external validation cohort [HRe] 2.49, 95% CI 1.89-3.27). Furthermore, patients detected as LVEF ≤ 35% by CXR-EF≤35% had significantly higher future risks of all-cause mortality (HRi 1.40, 95% CI 1.15-1.71; HRe 1.38, 95% CI 1.15-1.66), cardiovascular mortality (HRi 3.02, 95% CI 1.84-4.98; HRe 2.60, 95% CI 1.77-3.82), and new-onset atrial fibrillation (HRi 2.81, 95% CI 2.15-3.66; HRe 2.93, 95% CI 2.34-3.67) compared with those detected as no LVEF ≤ 35%. CONCLUSIONS: CXR-EF≤35% may serve as a screening tool for early detection of LVEF ≤ 35% and could independently contribute to predictions of long-term development of LVEF ≤ 35% and cardiovascular outcomes. Further prospective studies are needed to confirm the model performance.

Dynamic Changes in Neutrophil-to-Lymphocyte Ratio are Associated with Survival and Liver Toxicity Following Stereotactic Body Radiotherapy for Hepatocellular Carcinoma.

PURPOSE: Immune response to antitumor therapies has been correlated with oncologic outcomes. This study aimed to determine whether dynamic changes in immune parameters could predict survival outcomes and assess their relationship with liver toxicity in hepatocellular carcinoma (HCC) patients treated with stereotactic body radiation therapy (SBRT). METHODS: Data on pre- and post-SBRT (within 3 months) peripheral blood cell counts, neutrophil-to-lymphocyte ratio (NLR), and platelet-to-lymphocyte ratio (PLR) were retrospectively collected. Kinetic changes in these immune parameters and delta-NLR (dNLR) and delta-PLR (dPLR) in response to SBRT were evaluated. Overall survival (OS) and progression-free survival (PFS) were compared based on baseline NLR/PLR and dNLR/dPLR. Additionally, the association of these dynamic measures with liver toxicity was determined. RESULTS: The study included 93 patients with a median 10.7-month follow-up. Significant increases in NLR (p<0.001) and PLR (p=0.003) were observed after SBRT. In the multivariable analysis, elevated pre-SBRT NLR (p<0.001) and dNLR (p=0.011) were predictive of worse OS. dNLR was not associated with PFS. Neither PLR nor dPLR was predictive of survival outcomes. Patients with Child-Turcotte-Pugh class B had higher dNLR and greater risk of liver toxicity than class A counterparts. Receiver operating characteristic curve analysis found that dNLR ≥1.9 was an optimal cut-off value for determining liver toxicity risk (35.1% vs 7.5%, p=0.002). CONCLUSION: Baseline NLR and dNLR can complementarily predict OS in HCC patients treated with SBRT. Elevated dNLR is associated with worse OS and development of liver toxicity, possibly through their relationship with baseline liver function. Dynamic changes in NLR should be monitored in HCC care.

Clinical outcome and pathologic correlation of stereotactic body radiation therapy as a bridge to transplantation for advanced hepatocellular carcinoma: a case series.

BACKGROUND: Stereotactic body radiotherapy (SBRT) is an emerging modality for hepatocellular carcinoma (HCC). However, there is scant information about its safety and effectiveness in the neoadjuvant setting prior to liver transplantation (LT). We present the clinical outcome and pathologic assessment of SBRT followed by LT for patients with advanced HCC. METHODS: This retrospective study included HCC patients treated with neoadjuvant SBRT prior to LT between 2009 and 2018. Radiographic response and adverse effects, including radiation-induced liver disease (RILD), were evaluated. Pathologic response was assessed by the percentage of tumor necrosis relative to the total tumor volume. Overall survival (OS) and recurrence-free survival (RFS) were calculated using the Kaplan-Meier method. RESULTS: Fourteen patients underwent SBRT for a total of 25 HCC lesions, followed by LT. The median tumor size was 4.45 cm in diameter, and the median prescribed dose was 45 Gy in 5 fractions. SBRT provided significant AFP reduction, 100% infield control, and a 62.5% response rate. The maximum detected toxicity included grade 3 thrombocytopenia and two grade 3-4 hyperbilirubinemia. One patient developed non-classic RILD. Patients were bridged to LT with a median time of 8.4 months after SBRT, and 23.1% of them achieved a complete pathologic response. The median OS and RFS were 37.8 and 18.3 months from the time of LT, respectively. CONCLUSIONS: SBRT provides favorable tumor control and acceptable adverse effects for patients awaiting LT. Further prospective studies to test SBRT as a bridging therapy for LT are feasible.

Pretreatment Neutrophil-to-Lymphocyte Ratio Predicts Survival and Liver Toxicity in Patients With Hepatocellular Carcinoma Treated With Stereotactic Ablative Radiation Therapy.

PURPOSE: The objective of this study was to determine whether pretreatment neutrophil-to-lymphocyte ratio (NLR) could predict survival outcomes and liver toxicity in hepatocellular carcinoma (HCC) patients treated with stereotactic ablative radiation therapy (SABR). METHODS AND MATERIALS: In this retrospective study we collected pretreatment NLR of HCC patients treated with SABR between December 2007 and August 2018 and determined its association with overall survival (OS), progression-free survival, and radiation-related liver toxicity defined as an increase in the Child-Turcotte-Pugh score by ≥2 within 3 months after SABR in the absence of disease progression. RESULTS: A total of 153 patients with a median follow-up of 13.3 months were included. Receiver operating characteristic curve analysis found that an NLR ≥2.4 was optimum (area under the curve, 0.762; 95% confidence interval [CI], 0.682-0.841, P < .001) for predicting poor 1-year OS (38.2% vs 83.6%, P < .001). Multivariable analysis demonstrated that NLR was significantly associated with OS, both as a continuous (P = .006) and a binary variable (NLR set at 2.4; P = .003). Multiple tumors (P = .003), macrovascular invasion (P = .024), extrahepatic spread (P = .002), and albumin-bilirubin score (P = .020) were also significant predictors of OS. Elevated NLR independently prognosticated poor progression-free survival (P = .016). Liver toxicity was seen in 22 evaluable patients (15.4%). Receiver operating characteristic curve analysis found NLR ≥4.0 was optimum at predicting liver toxicity (31.4% vs 10.2%, P = .005). A higher NLR (P = .049) and albumin-bilirubin score (P = .002) were independent risk factors for liver toxicity. CONCLUSIONS: NLR is an objective and ubiquitous inflammatory marker that can predict OS and liver toxicity in HCC patients undergoing SABR. NLR could be a useful biomarker for patient risk stratification and therapeutic decision-making.

Prognostic Significance of Apparent Diffusion Coefficient in Hepatocellular Carcinoma Patients treated with Stereotactic Ablative Radiotherapy.

The role of diffusion-weighted magnetic resonance imaging (DW MRI) in assessing durable tumor control for patients with hepatocellular carcinoma (HCC) treated with stereotactic ablative radiotherapy (SABR) was not defined. This retrospective study included 34 HCC patients with 45 lesions who had DW MRI data at baseline and within 6 months post-SABR. On the first post-SABR MRI, 13 lesions (28.9%) had a complete response (CR), 12 (26.7%) had a partial response (PR), 17 (37.8%) had stable disease, and 3 (6.7%) had progressive disease by modified Response Evaluation Criteria in Solid Tumors (mRECIST). On subsequent imaging, the response rate improved from 55.6% to 75.6%. The apparent diffusion coefficients (ADCs) (mean ± standard deviation) pre- and post-SABR were 1.43 ± 0.28 and 1.72 ± 0.34 (×10-3 mm2/s), respectively (p < 0.001). An ADC change ≥25% (DW[+]) was identified as a predictor of favorable in-field control (IFC) (1-year IFC, 93.3% vs. 50.0% for DW[-], p = 0.004), but an mRECIST-based positive response (CR and PR) at the first MRI was not (p = 0.130). In conclusion, ADC change on early MRI is closely related to IFC in HCCs treated with SABR. Standardization of the DW MRI protocol, as well as prospective validation studies, are warranted.

Clinical features and computed tomography characteristics of non-Klebsiella pneumoniae liver abscesses in elderly (>65 years) and nonelderly patients.

PURPOSE: To compare the clinical and computed tomography (CT) appearances of liver abscesses caused by non-Klebsiella pneumoniae bacterial pathogens in elderly and nonelderly patients. MATERIALS AND METHODS: Eighty patients with confirmed non-Klebsiella pneumoniae liver abscesses (non-KPLAs) were enrolled and divided into two age groups: elderly (age ≥65 years, n=42) and nonelderly (age <65 years, n=38). Diagnosis of non-KPLA was established by pus and/or blood culture. We compared clinical presentations, outcomes, and CT characteristics of the two groups, and performed multivariate analysis for significant variables and receiver-operating-characteristic analysis to determine the cutoff value of abscess diameter for predicting non-KPLA. RESULTS: Elderly patients with non-KPLA were associated with a longer hospital stay (p<0.01). Regarding etiology, biliary sources had a strong association in the elderly group (p<0.01), and chronic liver diseases were related to the nonelderly group (p<0.01). Non-KPLAs (52.5%) tended to show a large, multiloculated appearance in the elderly group and were associated with bile duct dilatation (p<0.01), compared with the nonelderly group. The abscess diameter (cutoff value, 5.2 cm; area under the curve, 0.78) between the two groups was predicted. In multivariate analysis, underlying biliary tract disease [odds ratio (OR), 3.58, p<0.05], abscess diameter (OR, 2.40, p<0.05), and multiloculated abscess (OR, 1.19, p<0.01) independently predicted elderly patients with non-KPLA. CONCLUSION: In the elderly patients with non-KPLA, a large, multiloculated abscess with a diameter greater than 5.2 cm was the predominant imaging feature.