Search

Rationale: Data on longitudinal recovery after hospitalization for coronavirus disease (COVID-19) currently remain scarce, just as outcomes beyond 3 months of follow-up do. Objectives: To evaluate the sequelae up to 6 months after hospitalization for COVID-19 by considering 1) recovery as it relates to pulmonary function, radiological abnormalities, physical and mental health status, and health-related quality of life (HR-QoL) and 2) the predictors of the most clinically relevant sequelae. Methods: Patients were evaluated at 6 weeks, 3 months, and 6 months after hospitalization by using pulmonary function testing, radiological evaluation, and online questionnaires on the physical and mental health status and HR-QoL. Outcomes were analyzed using repeated-measurement analyses. Results: Ninety-two patients were included (mean age, 58.2 ± 12.3 yr; 58 [63.0%] men). The estimated percentage of patients with impaired forced vital capacity improved from 25% at 6 weeks to 11% at 6 months; for impaired diffusion capacity, this percentage improved from 63% to 46%. Radiologically, ground-glass opacity decreased but fibrosis persisted. The majority of patients (89.1%) still reported one or more symptoms 6 months after discharge. Fatigue decreased significantly over time (P = 0.006). Nonetheless, fatigue remained in 51% of the patients at 6 months. HR-QoL (nearly) normalized in most domains at 6 months, except for physical role functioning, with persistent fatigue and the length of hospitalization being the most important predictors. Conclusions: During the first 6 months after hospitalization for COVID-19, most patients demonstrated continuing recovery across all health domains, but persistent sequelae were frequent. Fatigue was the most frequent residual and persistent symptom up to 6 months after hospitalization, importantly impacting HR-QoL.

Patients with BRAF mutated (BRAF-mt) metastatic melanoma benefit significantly from treatment with BRAF inhibitors. Currently, the BRAF status is determined on archival tumor tissue or on fresh tumor tissue from an invasive biopsy. The aim of this study was to evaluate whether radiomics can predict the BRAF status in a non-invasive manner. Patients with melanoma lung metastases, known BRAF status, and a pretreatment computed tomography scan were included. After semi-automatic annotation of the lung lesions (maximum two per patient), 540 radiomics features were extracted. A chest radiologist scored all segmented lung lesions according to the Lung Image Database Consortium (LIDC) criteria. Univariate analysis was performed to assess the predictive value of each feature for BRAF mutation status. A combination of various machine learning methods was used to develop BRAF decision models based on the radiomics features and LIDC criteria. A total of 169 lung lesions from 103 patients (51 BRAF-mt; 52 BRAF wild type) were included. There were no features with a significant discriminative value in the univariate analysis. Models based on radiomics features and LIDC criteria both performed as poorly as guessing. Hence, the BRAF mutation status in melanoma lung metastases cannot be predicted using radiomics features or visually scored LIDC criteria., ImPhys/Medical Imaging, ImPhys/Computational Imaging

Radiomics uses quantitative medical imaging features to predict clinical outcomes. Currently, in a new clinical application, finding the optimal radiomics method out of the wide range of available options has to be done manually through a heuristic trial-anderror process. In this study we propose a framework for automatically optimizing the construction of radiomics workflows per application. To this end, we formulate radiomics as a modular workflow and include a large collection of common algorithms for each component. To optimize the workflow per application, we employ automated machine learning using a random search and ensembling. We evaluate our method in twelve different clinical applications, resulting in the following area under the curves: 1) liposarcoma (0.83); 2) desmoid-type fibromatosis (0.82); 3) primary liver tumors (0.80); 4) gastrointestinal stromal tumors (0.77); 5) colorectal liver metastases (0.61); 6) melanoma metastases (0.45); 7) hepatocellular carcinoma (0.75); 8) mesenteric fibrosis (0.80); 9) prostate cancer (0.72); 10) glioma (0.71); 11) Alzheimer’s disease (0.87); and 12) head and neck cancer (0.84). We show that our framework has a competitive performance compared human experts, outperforms a radiomics baseline, and performs similar or superior to Bayesian optimization and more advanced ensemble approaches. Concluding, our method fully automatically optimizes the construction of radiomics workflows, thereby streamlining the search for radiomics biomarkers in new applications. To facilitate reproducibility and future research, we publicly release six datasets, the software implementation of our framework, and the code to reproduce this study.

Patients with BRAF mutated (BRAF-mt) metastatic melanoma benefit significantly from treatment with BRAF inhibitors. Currently, the BRAF status is determined on archival tumor tissue or on fresh tumor tissue from an invasive biopsy. The aim of this study was to evaluate whether radiomics can predict the BRAF status in a non-invasive manner. Patients with melanoma lung metastases, known BRAF status, and a pretreatment computed tomography scan were included. After semi-automatic annotation of the lung lesions (maximum two per patient), 540 radiomics features were extracted. A chest radiologist scored all segmented lung lesions according to the Lung Image Database Consortium (LIDC) criteria. Univariate analysis was performed to assess the predictive value of each feature for BRAF mutation status. A combination of various machine learning methods was used to develop BRAF decision models based on the radiomics features and LIDC criteria. A total of 169 lung lesions from 103 patients (51 BRAF-mt; 52 BRAF wild type) were included. There were no features with a significant discriminative value in the univariate analysis. Models based on radiomics features and LIDC criteria both performed as poorly as guessing. Hence, the BRAF mutation status in melanoma lung metastases cannot be predicted using radiomics features or visually scored LIDC criteria.

Patients with BRAF mutated (BRAF-mt) metastatic melanoma benefit significantly from treatment with BRAF inhibitors. Currently, the BRAF status is determined on archival tumor tissue or on fresh tumor tissue from an invasive biopsy. The aim of this study was to evaluate whether radiomics can predict the BRAF status in a non-invasive manner. Patients with melanoma lung metastases, known BRAF status, and a pretreatment computed tomography scan were included. After semi-automatic annotation of the lung lesions (maximum two per patient), 540 radiomics features were extracted. A chest radiologist scored all segmented lung lesions according to the Lung Image Database Consortium (LIDC) criteria. Univariate analysis was performed to assess the predictive value of each feature for BRAF mutation status. A combination of various machine learning methods was used to develop BRAF decision models based on the radiomics features and LIDC criteria. A total of 169 lung lesions from 103 patients (51 BRAF-mt; 52 BRAF wild type) were included. There were no features with a significant discriminative value in the univariate analysis. Models based on radiomics features and LIDC criteria both performed as poorly as guessing. Hence, the BRAF mutation status in melanoma lung metastases cannot be predicted using radiomics features or visually scored LIDC criteria., ImPhys/Medical Imaging, ImPhys/Computational Imaging

Due to the outbreak of Severe Acute Respiratory Syndrome coronavirus (SARS-Cov-2), an efficient COVID-19 screening strategy is required for patients undergoing cardiac surgery. The objective of this prospective observational study was to evaluate the role of preoperative computed tomography (CT) screening for COVID-19 in a population of COVID-19 asymptomatic patients scheduled for cardiac surgery. Between the 29th of March and the 26th of May 2020, patients asymptomatic for COVID-19 underwent a CT-scan the day before surgery, with reverse-transcriptase polymerase-chain reaction (RT-PCR) reserved for abnormal scan results. The primary endpoint was the prevalence of abnormal scans, which was evaluated using the CO-RADS score, a COVID-19 specific grading system. In a secondary analysis, the rate of abnormal scans was compared between the screening cohort and matched historical controls who underwent routine preoperative CT-screening prior to the SARS-Cov-2 outbreak. Of the 109 patients that underwent CT-screening, an abnormal scan result was observed in 7.3% (95% confidence interval: 3.2–14.0%). One patient, with a normal screening CT, was tested positive for COVID-19, with the first positive RT-PCR on the ninth day after surgery. A rate of preoperative CT-scan abnormalities of 8% (n = 8) was found in the unexposed historical controls (P > 0.999). In asymptomatic patients undergoing cardiac surgery, preoperative screening for COVID-19 using computed tomography will identify pulmonary abnormalities in a small percentage of patients that do not seem to have COVID-19. Depending on the prevalence of COVID-19, this results in an unfavorable positive predictive value of CT screening. Care should be taken when considering CT as a screening tool prior to cardiac surgery.

Radiomics uses quantitative medical imaging features to predict clinical outcomes. Currently, in a new clinical application, finding the optimal radiomics method out of the wide range of available options has to be done manually through a heuristic trial-and-error process. In this study we propose a framework for automatically optimizing the construction of radiomics workflows per application. To this end, we formulate radiomics as a modular workflow and include a large collection of common algorithms for each component. To optimize the workflow per application, we employ automated machine learning using a random search and ensembling. We evaluate our method in twelve different clinical applications, resulting in the following area under the curves: 1) liposarcoma (0.83); 2) desmoid-type fibromatosis (0.82); 3) primary liver tumors (0.80); 4) gastrointestinal stromal tumors (0.77); 5) colorectal liver metastases (0.61); 6) melanoma metastases (0.45); 7) hepatocellular carcinoma (0.75); 8) mesenteric fibrosis (0.80); 9) prostate cancer (0.72); 10) glioma (0.71); 11) Alzheimer's disease (0.87); and 12) head and neck cancer (0.84). We show that our framework has a competitive performance compared human experts, outperforms a radiomics baseline, and performs similar or superior to Bayesian optimization and more advanced ensemble approaches. Concluding, our method fully automatically optimizes the construction of radiomics workflows, thereby streamlining the search for radiomics biomarkers in new applications. To facilitate reproducibility and future research, we publicly release six datasets, the software implementation of our framework, and the code to reproduce this study., Comment: 33 pages, 4 figures, 4 tables, 2 supplementary figures, 3 supplementary table, submitted to Medical Image Analysis; revision

Background: Nivolumab is administered in a weight-based or fixed-flat dosing regimen. For patients with non-small cell lung cancer (NSCLC), a potential exposure-response relationship has recently been reported and may argue against the current dosing strategies. The primary objectives were to determine nivolumab pharmacokinetics (PK) and to assess the relationship between drug clearance and clinical outcome in NSCLC, melanoma, and renal cell cancer (RCC). Methods: In this prospective observational cohort study, individual estimates of nivolumab clearance and the impact of baseline covariates were determined using a population-PK model. Clearance was related to best overall response (RECISTv1.1), and stratified by tumor type. Results: Two-hundred-twenty-one patients with metastatic cancer receiving nivolumab-monotherapy were included of whom 1,715 plasma samples were analyzed. Three baseline parameters had a significant effect on drug clearance and were internally validated in the population-PK model: gender, BSA, and serum albumin. Women had 22% lower clearance compared to men, while the threshold of BSA and albumin that led to > 20% increase of clearance was > 2.2m2 and < 37.5 g/L, respectively. For NSCLC, drug clearance was 42% higher in patients with progressive disease (mean: 0.24; 95% CI: 0.22-0.27 L/day) compared to patients with partial/complete response (mean: 0.17; 95% CI: 0.15-0.19 L/day). A similar trend was observed in RCC, however, no clearance-response relationship was observed in melanoma. Conclusions: Based on the first real-world population-PK model of nivolumab, covariate analysis revealed a significant effect of gender, BSA, and albumin on nivolumab clearance. A clearance-response relationship was observed in NSCLC, with a non-significant trend in RCC, but not in melanoma. Individual pharmacology of nivolumab in NSCLC appears important and should be prospectively studied.

Objective: Chest radiographs (CXR) are an important diagnostic tool for the detection of invasive pulmonary aspergillosis (IPA) in critically ill patients, but their diagnostic value is limited by a poor sensitivity. By using advanced image processing, the aim of this study was to increase the value of chest radiographs in the diagnostic work up of neutropenic patients who are suspected of IPA. Methods: The frontal CXRs of 105 suspected cases of IPA were collected from four institutions. Radiographs could contain single or multiple sites of infection. CT was used as reference standard. Five radiologists and two residents participated in an observer study for the detection of IPA on CXRs with and without bone suppressed images (ClearRead BSI 3.2; Riverain Technologies). The evaluation was performed separately for the right and left lung, resulting in 78 diseased cases (or lungs) and 132 normal cases (or lungs). For each image, observers scored the likelihood of focal infectious lesions being present on a continuous scale (0-100). The area under the receiver operating characteristics curve (AUC) served as the performance measure. Sensitivity and specificity were calculated by considering only the lungs with a suspiciousness score of greater than 50 to be positive. Results: The average AUC for only CXRs was 0.815. Performance significantly increased, to 0.853, when evaluation was aided with BSI (p = 0.01). Sensitivity increased from 49% to 66% with BSI, while specificity decreased from 95% to 90%. Conclusion: The detection of IPA in CXRs can be improved when their evaluation is aided by bone suppressed images. BSI improved the sensitivity of the CXR examination, outweighing a small loss in specificity.

This study was performed to examine the association of cardiovascular risk factors with calcification in the coronary arteries, aortic arch and carotid arteries, assessed by multislice computed tomography (MSCT). This study was embedded in the Rotterdam Study, a population-based study in subjects aged 55 years and over. From October 2003 until December 2004, subjects were invited to undergo a MSCT scan. Coronary, aortic arch and carotid calcification were quantified according to the Agatston score. Analyses were performed in the first 1003 subjects. Age and current smoking were the strongest independent risk factors for arterial calcification. The odds ratio (OR) for age in women, irrespective of the vessel bed, was 1.1 (P<0.001) and in men it was 1.2 with aortic arch and 1.1 with carotid calcification (both P<0.001). Current smoking was associated with aortic arch calcification with an OR of 3.5 in women and of 4.7 in men ( both P<0.001); and with carotid calcification with an OR of 2.1 in women (P<0.05) and of 4.1 in men (P<0.01). Hypertension, hypercholesterolemia and diabetes were also independently related to calcification, although not consistent across all vessel beds and for men and women. Obesity tended to be inversely related to arterial calcification in women, whereas low high-density lipoprotein-cholesterol showed no relation with arterial calcification. In conclusion, although associations were not completely consistent across the different vessel beds and for men and women, our results indicate that generally the same risk factors are present for atherosclerosis in the coronary, aortic arch and carotid circulation. Journal of Human Hypertension ( 2010) 24, 86-92; doi:10.1038/jhh.2009.42; published online 4 June 2009