Prediction of oxygen supplementation by a deep-learning model integrating clinical parameters and chest CT images in COVID-19.

PURPOSE: As of March 2023, the number of patients with COVID-19 worldwide is declining, but the early diagnosis of patients requiring inpatient treatment and the appropriate allocation of limited healthcare resources remain unresolved issues. In this study we constructed a deep-learning (DL) model to predict the need for oxygen supplementation using clinical information and chest CT images of patients with COVID-19. MATERIALS AND METHODS: We retrospectively enrolled 738 patients with COVID-19 for whom clinical information (patient background, clinical symptoms, and blood test findings) was available and chest CT imaging was performed. The initial data set was divided into 591 training and 147 evaluation data. We developed a DL model that predicted oxygen supplementation by integrating clinical information and CT images. The model was validated at two other facilities (n = 191 and n = 230). In addition, the importance of clinical information for prediction was assessed. RESULTS: The proposed DL model showed an area under the curve (AUC) of 89.9% for predicting oxygen supplementation. Validation from the two other facilities showed an AUC > 80%. With respect to interpretation of the model, the contribution of dyspnea and the lactate dehydrogenase level was higher in the model. CONCLUSIONS: The DL model integrating clinical information and chest CT images had high predictive accuracy. DL-based prediction of disease severity might be helpful in the clinical management of patients with COVID-19.

Riociguat for patients with chronic thromboembolic pulmonary hypertension: Usefulness of transitioning from phosphodiesterase type 5 inhibitor.

BACKGROUND: Riociguat, the first approved drug for patients with chronic thromboembolic pulmonary hypertension (CTEPH), is a soluble guanylate cyclase (sGC) Stimulator. It directly stimulates sGC independently of nitric oxide (NO) and increases sGC sensitivity for NO. The safety and efficacy of transitioning from a phosphodiesterase 5 inhibitor (PDE5i) to riociguat is unknown. METHODS AND RESULTS: Twenty-three patients were prospectively enrolled: 8 symptomatic patients with inadequate clinical responses to PDE5i were changed to riociguat (transitioned group); 15 started riociguat anew (new or add-on group). We analyzed the change from baseline to 6-12 months of riociguat treatment for the 6-minute walk distance (6MWD), mean pulmonary arterial pressure (mPAP), pulmonary vascular resistance (PVR), cardiac index (CI), partial pressure of oxygen in arterial blood (PaO2), brain natriuretic peptide (BNP), World Health Organization (WHO) functional class, safety and adverse events. The mPAP, BNP and WHO functional class significantly improved in total. In the transitioned group, BNP significantly decreased by -116.5±188.6pg/ml (P=0.0156). The 6MWD, mPAP, PVR, CI, and PaO2 improved but not significantly. The baseline condition was significantly more severe in the transitioned than in the new or add-on group. No patients discontinued riociguat. Relatively rapid transitioning from PDE5i to riociguat was safe under careful observation. CONCLUSIONS: Transitioning to riociguat may be safe and effective in CTEPH patients with inadequate clinical responses to PDE5i.

The dilatation of main pulmonary artery and right ventricle observed by enhanced chest computed tomography predict poor outcome in inoperable chronic thromboembolic pulmonary hypertension.

BACKGROUND: Dilatation of the pulmonary artery and right ventricle on chest computed tomography images is often observed in patients with pulmonary hypertension. The clinical significance of these image findings has not been defined in chronic thromboembolic pulmonary hypertension. We investigated whether the pulmonary arterial and right ventricle dilatation was associated with poor outcome in chronic thromboembolic pulmonary hypertension. METHODS: This was a retrospective cohort investigation in 60 subjects with inoperable chronic thromboembolic pulmonary hypertension diagnosed consecutively between 1997 and 2010 at Chiba University Hospital. Digital scout multi-detector chest computed tomography images were obtained. The main pulmonary arterial to ascending aortic diameter ratio and the right ventricular to left ventricular diameter ratio were calculated. RESULTS: Main pulmonary arterial to ascending aortic diameter ratio ranged from 0.85 to 1.84, and right ventricular to left ventricular diameter ratio ranged from 0.71 to 2.88. During the observation period of 1284.5days (range, 21-4550days), 13 patients required hospitalization due to worsening; 6 of them died. Kaplan-Meier analysis showed significant differences in hospitalization between the patients with main pulmonary arterial to ascending aortic diameter ratio of ≥1.1 and <1.1 (log-rank test, p=0.014) and between the patients with right ventricular to left ventricular diameter ratio of ≥1.2 and <1.2 (log-rank test, p=0.013). There was a significant difference in the prognosis between the patients with RV/LV ratio≥1.2 and those with RV/LV ratio<1.2 (log-rank test, p=0.033). CONCLUSIONS: Main pulmonary arterial to ascending aortic diameter ratio measured using enhanced CT images was associated with the risk for first clinical exacerbation, and right ventricular to left ventricular diameter ratio was associated with the risk for poor prognosis in inoperable chronic thromboembolic pulmonary hypertension.

The anticoagulant effects of warfarin and the bleeding risk associated with its use in patients with chronic thromboembolic pulmonary hypertension at a specialist center in Japan: a retrospective cohort study.

Patients with chronic thromboembolic pulmonary hypertension (CTEPH) require lifelong anticoagulation therapy. However, the bleeding risk and recurrence of venous thromboembolism (VTE) in CTEPH patients who are administered warfarin have not been adequately evaluated. The purpose of this study was to evaluate the risk of clinically relevant bleeding, recurrent VTE, and clinical worsening in patients with CTEPH who were administered warfarin. The clinical records of 72 patients with CTEPH who regularly visited our institution and were administered warfarin were retrospectively reviewed between 1 January 2011 and 31 December 2015. We investigated the incidence of clinically relevant bleeding events, recurrent VTE, and hospitalization for the deterioration of pulmonary hypertension or right heart failure (RHF) during the observation period. The mean observation period for the 72 patients was 3.60 ± 1.60 person-years. Clinically relevant bleeding, RHF, and recurrent VTE occurred in 21 (29.2%), eight (11.1%), and three (4.2%) of 72 patients, respectively, and the incidence rates for these events were 8.1%/person-year, 3.1%/person-year, and 1.2%/person-year, respectively. The incidence rates for the major and non-major bleeding events were 5.0%/person-year and 3.9%/person-year, respectively. The incidence of clinically relevant bleeding events was 20.8%/person-year during medical treatment with a soluble guanylate cyclase stimulator. One of 35 patients (2.9%) during the post-pulmonary endarterectomy period experienced hemoptysis during observation period (> 6 months after pulmonary endarterectomy). No bleeding events occurred during the post-balloon pulmonary angioplasty period. In conclusion, warfarin effectively prevents VTE recurrence in CTEPH patients, but its effects may be associated with a considerable bleeding risk.

Circulating Anti-Coatomer Protein Complex Subunit Epsilon (COPE) Autoantibodies as a Potential Biomarker for Cardiovascular and Cerebrovascular Events in Patients with Obstructive Sleep Apnea.

STUDY OBJECTIVES: Although moderate to severe obstructive sleep apnea (OSA) is an independent risk factor for severe arteriosclerotic diseases such as cardiovascular disease (CVD) and stroke, the development of atherosclerosis-related diseases cannot yet be predicted in patients with OSA. In a pilot study, we identified autoantibodies against the coatomer protein complex, subunit epsilon [circulating anti-coatomer protein complex subunit epsilon autoantibody (COPE-Ab)], a cytosolic complex that mediates protein transport in the Golgi compartment, as a potential novel biomarker of atherosclerosis. This study aimed to evaluate whether COPE-Ab levels had an association with cardiovascular and cerebrovascular events in patients with OSA. METHODS: Eighty-two adult patients with a diagnosis of OSA via polysomnography and 64 healthy donors were studied. Serum COPE-Ab levels were measured using an amplified luminescence proximity homogeneous assay. Then, clinical factors related to atherosclerosis were evaluated with respect to COPE-Ab levels. RESULTS: Significant differences in COPE-Ab levels were observed in terms of OSA severity. COPE-Ab levels were significantly higher in patients with OSA and also CVD and/or stroke, hypertension, and a high body mass index. Univariate and multivariate logistic regression analyses of patients with OSA identified elevated COPE-Ab level as a significant predictor of CVD and/or stroke. CONCLUSIONS: An elevated COPE-Ab level may be a potential predictor of the risks of cardiovascular and cerebrovascular events in patients with OSA. Therefore, patients with higher COPE-Ab levels may require more careful and intensive treatment. COMMENTARY: A commentary on this article appears in this issue on page 361.

Mean Pulmonary Artery Pressure Using Echocardiography in Chronic Thromboembolic Pulmonary Hypertension.

BACKGROUND: Mean pulmonary arterial pressure (MPAP) is an important pulmonary hemodynamic parameter used in the management of patients with chronic thromboembolic pulmonary hypertension (CTEPH). We compared echocardiography-derived estimates of MPAP with right heart catheterization (RHC) to identify reliable noninvasive methods of estimating MPAP-derived RHC (MPAPRHC) in these patients. METHODS AND RESULTS: Echocardiography and RHC were performed in 56 patients with CTEPH (60.5±12.0 years; 44 females). We measured the tricuspid regurgitation (TR) pressure gradient (TRPG) using echocardiography. The mean systolic right ventricular (RV)-right atrial (RA) gradient was calculated by tracing the TR time velocity flow. Systolic and mean pulmonary artery pressures (SPAPTRand MPAPTR) estimated from TRPG and mean systolic RV-RA gradient were calculated by adding RA pressure based on the inferior vena cava. MPAPChemlawas calculated using Chemla's formula: 0.61×SPAPTR+2 mmHg. MPAPRHCand pulmonary vascular resistance were 35.9±11.3 mmHg and 6.6±3.6 Wood units, respectively. The mean difference from MPAPRHCand limits of agreement were -1.5 mmHg and -19.6 to 16.5 mmHg for MPAPTR, and -4.6 mmHg and -24.5 to 15.2 mmHg for MPAPChemla. Accuracy within 10 mmHg and 5 mmHg of MPAPRHCwas 80.4% and 46.4% for MPAPTR, and 71.4% and 48.2% for MPAPChemla, respectively. CONCLUSIONS: MPAPTRand MPAPChemlaare reliable estimates for MPAPRHCin patients with CTEPH. (Circ J 2016; 80: 1259-1264).

Noninvasive assessment of pulmonary vascular resistance by echocardiography in chronic thromboembolic pulmonary hypertension.

BACKGROUND: Pulmonary vascular resistance (PVR) is an important parameter in the management of patients with chronic thromboembolic pulmonary hypertension (CTEPH), and numerous noninvasive methods for PVR prediction have been proposed. However, a systematic evaluation of the methods that are specific for CTEPH has not been conducted. We compared a variety of echocardiography-derived prediction indices with direct right heart catheterization (RHC) to identify the most reliable noninvasive indicator of PVR in patients with CTEPH. PATIENTS AND METHODS: Echocardiography and RHC were performed sequentially in 40 patients (mean age: 62.4±11.4 years; 30 females) with CTEPH. We measured the peak flow velocity of tricuspid regurgitation (TRV), tricuspid regurgitation pressure gradient (TRPG), right ventricular outflow tract (RVOT) time-velocity integral (TVIRVOT), left ventricular outflow tract (LVOT) time-velocity integral (TVILVOT), cardiac output at RVOT (CORVOT), and the LVOT (COLVOT) using echocardiography. The parameters TRV/TVIRVOT, TRV/TVILVOT, TRV/CORVOT, TRV/COLVOT, TRPG/TVIRVOT, TRPG/TVILVOT, TRPG/CORVOT, and TRPG/COLVOT were then calculated to predict the PVR. Finally, correlations between these echocardiographic predictors of PVR and the PVR data obtained from RHC (PVRRHC) were assessed. RESULTS: The mean pulmonary arterial pressure and PVRRHC were 32.1±11.4mmHg and 5.4±2.9 Wood units, respectively. TRV/TVIRVOT, TRV/TVILVOT, TRV/COLVOT, TRPG/TVIRVOT, TRPG/TVILVOT, TRPG/CORVOT, and TRPG/COLVOT were all significantly correlated with the PVRRHC, and TRPG/COLVOT was the most strongly correlated with the PVRRHC (r=0.807, p<0.001). CONCLUSIONS: Echocardiographic measurement of TRPG/COLVOT is a reliable noninvasive predictor of PVR in CTEPH patients.

[A case of pulmonary tuberculosis in which diagnosis was delayed because of prior treatment with fluoroquinolone and metronidazole].

We report the case of a patient with pulmonary tuberculosis, whose diagnosis was delayed because of prior treatment with fluoroquinolone and metronidazole. A 35-year-old woman developed productive cough, fever, and back pain, which lasted for 3 weeks before admission to hospital. She had been diagnosed with lower respiratory infection and was treated with garenoxacin mesilate hydrate for 7 days before admission. As her symptoms did not improve, she was referred to our hospital for further evaluation. A chest computed tomography scan revealed confluent consolidation in the right lower lung, predominantly in segment 7, and lung abscess was initially suspected. Since chemotherapy with ceftriaxone and minomycin did not reduce her symptoms, metronidazole was added on day 4. Her symptoms improved dramatically and she was discharged on day 15. Metronidazole was given for a total of 3 weeks, and 2 weeks after discontinuation of metronidazole, she presented with recurrent chest pain and was diagnosed with active pulmonary tuberculosis. In addition to the atypical imaging findings in this patient, the use of chemotherapeutics such as garenoxacin mesilate hydrate and metronidazole, which have anti-tuberculosis effects, meant that the diagnosis of tuberculosis was complicated and hence delayed. We should keep in mind that some general chemotherapy agents, including linezolid, also have anti-tuberculosis effects and may cause similar problems with diagnosis.

Multiple granulomatous lung lesions in a patient with Epstein-Barr-virus-induced mononucleosis and new-onset systemic lupus erythematosus: a case report.

INTRODUCTION: Granulomatous lesions are commonly encountered abnormalities in pulmonary pathology, and often pose a diagnostic challenge. We report an unusual case of granulomatous lung disease with uncommon characteristics, which developed following Epstein-Barr-virus-induced mononucleosis and new-onset systemic lupus erythematosus. We aim to highlight a diagnostic approach for the condition and to raise awareness of the possibility of it being related to the immunological reaction caused by Epstein-Barr virus infection. CASE PRESENTATION: A 36-year-old Japanese man, who had been diagnosed with Epstein-Barr-virus-induced infectious mononucleosis, new-onset systemic lupus erythematosus, and secondary Sjögren's syndrome three weeks previously, presented to our facility with fever and diffuse pulmonary infiltrates. A computed tomography scan of the chest revealed multiple small nodules in both lungs. Fiberoptic bronchoscopy with bronchoalveolar lavage revealed lymphocytosis with predominance of T lymphocytes. A histological examination of a lung biopsy taken during video-assisted thoracic surgery showed randomly distributed tiny granulomatous lesions with infiltration of eosinophils. The differential diagnoses included hypersensitivity pneumonitis, sarcoidosis, and pulmonary involvement of Crohn's disease, systemic lupus erythematosus, and Sjögren's syndrome, but the clinical and pathological findings were not consistent with any of these. Our patient's condition did not improve; therefore, prednisolone therapy was started because of the possibility of specific immunological reactions associated with Epstein-Barr virus infection. After steroid treatment, our patient showed radiological and clinical improvement. CONCLUSIONS: To the best of our knowledge, this is the first case of a patient developing randomly distributed multiple granulomatous lung lesions with eosinophilic infiltrates after Epstein-Barr virus infection and systemic lupus erythematosus. On the basis of our data, we hypothesize that Epstein-Barr virus infection altered the immune response of our predisposed patient and contributed to the pathogenesis of the lung lesions. Our patient's clinical response to steroid treatment was excellent.