Clinical performance of AI-integrated risk assessment pooling reveals cost savings even at high prevalence of COVID-19.

Individual testing of samples is time- and cost-intensive, particularly during an ongoing pandemic. Better practical alternatives to individual testing can significantly decrease the burden of disease on the healthcare system. Herein, we presented the clinical validation of Segtnan™ on 3929 patients. Segtnan™ is available as a mobile application entailing an AI-integrated personalized risk assessment approach with a novel data-driven equation for pooling of biological samples. The AI was selected from a comparison between 15 machine learning classifiers (highest accuracy = 80.14%) and a feed-forward neural network with an accuracy of 81.38% in predicting the rRT-PCR test results based on a designed survey with minimal clinical questions. Furthermore, we derived a novel pool-size equation from the pooling data of 54 published original studies. The results demonstrated testing capacity increase of 750%, 60%, and 5% at prevalence rates of 0.05%, 22%, and 50%, respectively. Compared to Dorfman's method, our novel equation saved more tests significantly at high prevalence, i.e., 28% (p = 0.006), 40% (p = 0.00001), and 66% (p = 0.02). Lastly, we illustrated the feasibility of the Segtnan™ usage in clinically complex settings like emergency and psychiatric departments.

Prognostic Implications of Total Hemispheric Glucose Metabolism Ratio in Cerebrocerebellar Diaschisis.

Diaschisis denotes brain dysfunction remote from a focal brain lesion. We have quantified diaschisis and investigated its prognostic value in glioma. Methods: We compared 50 18F-FDG PET/CT studies collected prospectively from 14 patients with supratentorial glioma (5 men and 9 women; age range, 35-77 y) with 10 single scans from healthy controls (age range, 43-75 y). Dedicated 3-dimensional segmentation software was used to obtain total hemispheric glucose metabolic ratios (THGr) by dividing total hemispheric 18F-FDG uptake in each diaschitic hemisphere-that is, the ipsilateral cerebral hemisphere (THGr(Ce)) and the contralateral cerebellar hemisphere (THGr(Cb))-by its respective contralateral side. Receiver-operating-characteristic (ROC) analysis was performed to determine optimal cut-offs for combinations of THGr(Ce) and THGr(Cb). Two independent observers obtained data for reproducibility analysis, and THGr values were compared with qualitative assessment of diaschisis performed by a PET neuroimaging specialist. Results: Qualitative analysis confirmed cerebrocerebellar diaschisis in all glioblastoma PET studies performed within 1 y of death. Healthy subjects had significantly higher THGr(Ce) values (P = 0.0007) and THGr(Cb) values (P = 0.02) than glioblastoma patients. ROC analysis yielded diaschisis thresholds of 0.62 for THGr(Ce) and 0.84 for THGr (Cb). Qualitative assessment demonstrated cerebral diaschisis in 16 of 17 (94%) cases with THGr(Ce) below the determined threshold and cerebellar diaschisis in 25 of 26 (96%) cases with THGr(Cb) below the determined threshold. When both THGr(Ce) and THGr(Cb) were below the ROC threshold, the combined diaschisis measures had a positive predictive value for survival below 1 y of 100%. When one parameter was below the threshold, it had a positive predictive value of 75%, and when both parameters exceeded thresholds, the negative predictive value for survival above 1 y was 79%. Median interrater variability was 3.3% and 5.9% for THGr(Ce) and THGr(Cb), respectively. Conclusion: The THGr measures demonstrated diaschisis in the cerebrum and cerebellum of patients with glioma. Combined cerebrocerebellar diaschisis ratios with ROC thresholds for both forebrain and hindbrain had high negative and positive predictive values for survival for less than a year. The THGr method allows comparison of data obtained at different institutions and is now open for further validation in gliomas and other cerebral diseases.

How to assess intra- and inter-observer agreement with quantitative PET using variance component analysis: a proposal for standardisation.

BACKGROUND: Quantitative measurement procedures need to be accurate and precise to justify their clinical use. Precision reflects deviation of groups of measurement from another, often expressed as proportions of agreement, standard errors of measurement, coefficients of variation, or the Bland-Altman plot. We suggest variance component analysis (VCA) to estimate the influence of errors due to single elements of a PET scan (scanner, time point, observer, etc.) to express the composite uncertainty of repeated measurements and obtain relevant repeatability coefficients (RCs) which have a unique relation to Bland-Altman plots. Here, we present this approach for assessment of intra- and inter-observer variation with PET/CT exemplified with data from two clinical studies. METHODS: In study 1, 30 patients were scanned pre-operatively for the assessment of ovarian cancer, and their scans were assessed twice by the same observer to study intra-observer agreement. In study 2, 14 patients with glioma were scanned up to five times. Resulting 49 scans were assessed by three observers to examine inter-observer agreement. Outcome variables were SUVmax in study 1 and cerebral total hemispheric glycolysis (THG) in study 2. RESULTS: In study 1, we found a RC of 2.46 equalling half the width of the Bland-Altman limits of agreement. In study 2, the RC for identical conditions (same scanner, patient, time point, and observer) was 2392; allowing for different scanners increased the RC to 2543. Inter-observer differences were negligible compared to differences owing to other factors; between observer 1 and 2: -10 (95 % CI: -352 to 332) and between observer 1 vs 3: 28 (95 % CI: -313 to 370). CONCLUSIONS: VCA is an appealing approach for weighing different sources of variation against each other, summarised as RCs. The involved linear mixed effects models require carefully considered sample sizes to account for the challenge of sufficiently accurately estimating variance components.

Dual-time-point Imaging and Delayed-time-point Fluorodeoxyglucose-PET/Computed Tomography Imaging in Various Clinical Settings.

The techniques of dual-time-point imaging (DTPI) and delayed-time-point imaging, which are mostly being used for distinction between inflammatory and malignant diseases, has increased the specificity of fluorodeoxyglucose (FDG)-PET for diagnosis and prognosis of certain diseases. A gradually increasing trend of FDG uptake over time has been shown in malignant cells, and a decreasing or constant trend has been shown in inflammatory/infectious processes. Tumor heterogeneity can be assessed by using early and delayed imaging because differences between primary versus metastatic sites become more detectable compared with single time points. This article discusses the applications of DTPI and delayed-time-point imaging.