Texture analysis can predict response to etoposide-doxorubicin-cisplatin in patients with adrenocortical carcinoma.

BACKGROUND: The adrenocortical carcinoma (ACC) is a rare and highly aggressive malignancy originating from the adrenal cortex. These patients usually undergo chemotherapy with etoposide, doxorubicin, cisplatin and mitotane (EDP-M) in case of locally advanced or metastatic ACC. Computed tomography (CT) radiomics showed to be useful in adrenal pathologies. The study aimed to analyze the association between response to EDP-M treatment and CT textural features at diagnosis in patients with locally advanced or metastatic ACCs. METHODS: We enrolled 17 patients with advanced or metastatic ACC who underwent CT before and after EDP-M therapy. The response to treatment was evaluated according to RECIST 1.1, Choi, and volumetric criteria. Based on the aforementioned criteria, the patients were classified as responders and not responders. Textural features were extracted from the biggest lesion in contrast-enhanced CT images with LifeX software. ROC curves were drawn for the variables that were significantly different (p < 0.05) between the two groups. RESULTS: Long-run high grey level emphasis (LRHGLE_GLRLM) and histogram kurtosis were significantly different between responder and not responder groups (p = 0.04) and the multivariate ROC curve combining the two features showed a very good AUC (0.900; 95%IC: 0.724-1.000) in discriminating responders from not responders. More heterogeneous tissue texture of initial staging CT in locally advanced or metastatic ACC could predict the positive response to EDP-M treatment. CONCLUSIONS: Adrenal texture is able to predict the response to EDP-M therapy in patients with advanced ACC.

Could CT Radiomic Analysis of Benign Adrenal Incidentalomas Suggest the Need for Further Endocrinological Evaluation?

We studied the application of CT texture analysis in adrenal incidentalomas with baseline characteristics of benignity that are highly suggestive of adenoma to find whether there is a correlation between the extracted features and clinical data. Patients with hormonal hypersecretion may require medical attention, even if it does not cause any symptoms. A total of 206 patients affected by adrenal incidentaloma were retrospectively enrolled and divided into non-functioning adrenal adenomas (NFAIs, n = 115) and mild autonomous cortisol secretion (MACS, n = 91). A total of 136 texture parameters were extracted in the unenhanced phase for each volume of interest (VOI). Random Forest was used in the training and validation cohorts to test the accuracy of CT textural features and cortisol-related comorbidities in identifying MACS patients. Twelve parameters were retained in the Random Forest radiomic model, and in the validation cohort, a high specificity (81%) and positive predictive value (74%) were achieved. Notably, if the clinical data were added to the model, the results did not differ. Radiomic analysis of adrenal incidentalomas, in unenhanced CT scans, could screen with a good specificity those patients who will need a further endocrinological evaluation for mild autonomous cortisol secretion, regardless of the clinical information about the cortisol-related comorbidities.

Three-dimensional numerical schemes for the segmentation of the psoas muscle in X-ray computed tomography images.

The analysis of the psoas muscle in morphological and functional imaging has proved to be an accurate approach to assess sarcopenia, i.e. a systemic loss of skeletal muscle mass and function that may be correlated to multifactorial etiological aspects. The inclusion of sarcopenia assessment into a radiological workflow would need the implementation of computational pipelines for image processing that guarantee segmentation reliability and a significant degree of automation. The present study utilizes three-dimensional numerical schemes for psoas segmentation in low-dose X-ray computed tomography images. Specifically, here we focused on the level set methodology and compared the performances of two standard approaches, a classical evolution model and a three-dimension geodesic model, with the performances of an original first-order modification of this latter one. The results of this analysis show that these gradient-based schemes guarantee reliability with respect to manual segmentation and that the first-order scheme requires a computational burden that is significantly smaller than the one needed by the second-order approach.

Artificial intelligence and prescription of antibiotic therapy: present and future.

INTRODUCTION: In the past few years, the use of artificial intelligence in healthcare has grown exponentially. Prescription of antibiotics is not exempt from its rapid diffusion, and various machine learning (ML) techniques, from logistic regression to deep neural networks and large language models, have been explored in the literature to support decisions regarding antibiotic prescription. AREAS COVERED: In this narrative review, we discuss promises and challenges of the application of ML-based clinical decision support systems (ML-CDSSs) for antibiotic prescription. A search was conducted in PubMed up to April 2024. EXPERT OPINION: Prescribing antibiotics is a complex process involving various dynamic phases. In each of these phases, the support of ML-CDSSs has shown the potential, and also the actual ability in some studies, to favorably impacting relevant clinical outcomes. Nonetheless, before widely exploiting this massive potential, there are still crucial challenges ahead that are being intensively investigated, pertaining to the transparency of training data, the definition of the sufficient degree of prediction explanations when predictions are obtained through black box models, and the legal and ethical framework for decision responsibility whenever an antibiotic prescription is supported by ML-CDSSs.

Distinct features of immune activation and exhaustion markers in people with perinatally-acquired HIV.

OBJECTIVE: The aim of this study was to characterize T cell activation, exhaustion, maturation and Treg frequencies in individuals who acquire perinatal HIV (PHIV), in individuals who acquired HIV as adult (AHIV), and in healthy controls (HC). DESIGN: This cross-sectional study included people with HIV ≥ 14 and <40 years, HIV-RNA < 50 copies/mL on antiretroviral therapy for at least 6 months, and HC. METHODS: We assessed the expression of PD-1, TIM-3, EOMES, CD38+ DR+, maturation status by CD4+ and CD8+T cells and the frequency of CD4+ and CD8+ Treg cells. Principal component analysis (PCA) and k-means cluster analysis investigated which combination of immunological parameters better associated with each group. RESULTS: 26 PHIV and 18 AHIV with median ages of 26 (8.0) and 28 (6.8) years were consecutively enrolled. PHIV showed significant higher frequency of naïve and lower frequency of terminal effector memory CD4+ and CD8+ T cells than AHIV. AHIV exhibited higher expression of exhaustion and activation markers. The statistical analysis returned two clusters with 94% of specificity and 88% of sensitivity identifying PHIV vs. AHIV. The 9 HC had a lower expression of exhaustion markers on both CD4+ and CD8+T lymphocytes than PHIV and AHIV. CONCLUSIONS: These data may exclude major alterations of lymphopoiesis in PHIV, with even lower state of immune-activation and exhaustion compared with AHIV. This suggests that recent lack of virological control, may affect immune activation and exhaustion of CD4+ and CD8+ T cells.

Prediction of candidemia with machine learning techniques: state of the art.

In this narrative review, we discuss studies assessing the use of machine learning (ML) models for the early diagnosis of candidemia, focusing on employed models and the related implications. There are currently few studies evaluating ML techniques for the early diagnosis of candidemia as a prediction task based on clinical and laboratory features. The use of ML tools holds promise to provide highly accurate and real-time support to clinicians for relevant therapeutic decisions at the bedside of patients with suspected candidemia. However, further research is needed in terms of sample size, data quality, recognition of biases and interpretation of model outputs by clinicians to better understand if and how these techniques could be safely adopted in daily clinical practice.

Candida is a type of fungus that can cause fatal infections. To confirm the presence of the infection, doctors may search for the fungus in the blood. Here, we discuss if computer systems can help to identify infection more easily and more rapidly.

Explainable and Interpretable Machine Learning for Antimicrobial Stewardship: Opportunities and Challenges.

There is growing interest in exploiting the advances in artificial intelligence and machine learning (ML) for improving and monitoring antimicrobial prescriptions in line with antimicrobial stewardship principles. Against this background, the concepts of interpretability and explainability are becoming increasingly essential to understanding how ML algorithms could predict antimicrobial resistance or recommend specific therapeutic agents, to avoid unintended biases related to the "black box" nature of complex models. In this commentary, we review and discuss some relevant topics on the use of ML algorithms for antimicrobial stewardship interventions, highlighting opportunities and challenges, with particular attention paid to interpretability and explainability of employed models. As in other fields of medicine, the exponential growth of artificial intelligence and ML indicates the potential for improving the efficacy of antimicrobial stewardship interventions, at least in part by reducing time-consuming tasks for overwhelmed health care personnel. Improving our knowledge about how complex ML models work could help to achieve crucial advances in promoting the appropriate use of antimicrobials, as well as in preventing antimicrobial resistance selection and dissemination.

Artificial intelligence of imaging and clinical neurological data for predictive, preventive and personalized (P3) medicine for Parkinson Disease: The NeuroArtP3 protocol for a multi-center research study.

BACKGROUND: The burden of Parkinson Disease (PD) represents a key public health issue and it is essential to develop innovative and cost-effective approaches to promote sustainable diagnostic and therapeutic interventions. In this perspective the adoption of a P3 (predictive, preventive and personalized) medicine approach seems to be pivotal. The NeuroArtP3 (NET-2018-12366666) is a four-year multi-site project co-funded by the Italian Ministry of Health, bringing together clinical and computational centers operating in the field of neurology, including PD. OBJECTIVE: The core objectives of the project are: i) to harmonize the collection of data across the participating centers, ii) to structure standardized disease-specific datasets and iii) to advance knowledge on disease's trajectories through machine learning analysis. METHODS: The 4-years study combines two consecutive research components: i) a multi-center retrospective observational phase; ii) a multi-center prospective observational phase. The retrospective phase aims at collecting data of the patients admitted at the participating clinical centers. Whereas the prospective phase aims at collecting the same variables of the retrospective study in newly diagnosed patients who will be enrolled at the same centers. RESULTS: The participating clinical centers are the Provincial Health Services (APSS) of Trento (Italy) as the center responsible for the PD study and the IRCCS San Martino Hospital of Genoa (Italy) as the promoter center of the NeuroartP3 project. The computational centers responsible for data analysis are the Bruno Kessler Foundation of Trento (Italy) with TrentinoSalute4.0 -Competence Center for Digital Health of the Province of Trento (Italy) and the LISCOMPlab University of Genoa (Italy). CONCLUSIONS: The work behind this observational study protocol shows how it is possible and viable to systematize data collection procedures in order to feed research and to advance the implementation of a P3 approach into the clinical practice through the use of AI models.

Data-driven analysis of regional brain metabolism in behavioral frontotemporal dementia and late-onset primary psychiatric diseases with frontal lobe syndrome: A PET/MRI study.

Late-onset primary psychiatric disease (PPD) and behavioral frontotemporal dementia (bvFTD) present with a similar frontal lobe syndrome. We compare brain glucose metabolism in bvFTD and late-onset PPD and investigate the metabolic correlates of cognitive and behavioral disturbances through FDG-PET/MRI. We studied 37 bvFTD and 20 late-onset PPD with a mean clinical follow-up of three years. At baseline evaluation, metabolism of the dorsolateral, ventrolateral, orbitofrontal regions and caudate could classify the patients with a diagnostic accuracy of 91% (95% CI: 0.81-0.98%). 45% of PPD showed low-grade hypometabolism in the anterior cingulate and/or parietal regions. Frontal lobe metabolism was normal in 32% of genetic bvFTD and bvFTD with motor neuron signs. Hypometabolism of the frontal and caudate regions could help in distinguishing bvFTD from PPD, except in cases with motor neuron signs and/or genetic bvFTD for which brain metabolism may be less informative.

Nodal staging with MRI after neoadjuvant chemo-radiotherapy for locally advanced rectal cancer: a fast and reliable method.

OBJECTIVES: In patients with locally advanced rectal carcinoma (LARC), negative nodal status after neoadjuvant chemoradiotherapy (nCRT) may allow for rectum-sparing protocols rather than total mesorectal excision; however, current MRI criteria for nodal staging have suboptimal accuracy. The aim of this study was to compare the diagnostic accuracy of different MRI dimensional criteria for nodal staging after nCRT in patients with LARC. MATERIALS AND METHODS: Patients who underwent MRI after nCRT for LARC followed by surgery were retrospectively included and divided into a training and a validation cohort of 100 and 39 patients, respectively. Short-, long-, and cranial-caudal axes and volume of the largest mesorectal node and nodal status based on European Society of Gastrointestinal Radiology consensus guidelines (i.e., ESGAR method) were assessed by two radiologists independently. Inter-reader agreement was assessed in the training cohort. Histopathology was the reference standard. ROC curves and the best cut-off were calculated, and accuracies compared with the McNemar test. RESULTS: The study population included 139 patients (median age 62 years [IQR 55-72], 94 men). Inter-reader agreement was high for long axis (κ = 0.81), volume (κ = 0.85), and ESGAR method (κ = 0.88) and low for short axis (κ = 0.11). Accuracy was similar (p > 0.05) for long axis, volume, and ESGAR method both in the training (71%, 74%, and 65%, respectively) and in the validation (83%, 78%, and 75%, respectively) cohorts. CONCLUSION: Accuracy of the measurement of long axis and volume of the largest lymph node is not inferior to the ESGAR method for nodal staging after nCRT in LARC. CLINICAL RELEVANCE STATEMENT: In MRI restaging of rectal cancer, measurement of the long axis or volume of largest mesorectal lymph node after preoperative chemoradiotherapy is a faster and reliable alternative to ESGAR criteria for nodal staging. KEY POINTS: • Current MRI criteria for nodal staging in locally advanced rectal cancer after chemo-radiotherapy have suboptimal accuracy and are time-consuming. • Measurement of long axis or volume of the largest mesorectal lymph node on MRI showed good accuracy for assessment of loco-regional nodal status in locally advanced rectal cancer. • MRI measurement of the long axis and volume of largest mesorectal lymph node after chemo-radiotherapy could be a faster and reliable alternative to ESGAR criteria for nodal staging.

Early diagnosis of candidemia with explainable machine learning on automatically extracted laboratory and microbiological data: results of the AUTO-CAND project.

BACKGROUND: Candidemia is associated with a heavy burden of morbidity and mortality in hospitalized patients. The availability of blood culture results could require up to 48-72 h after blood draw; thus, early treatment decisions are made in the absence of a definite diagnosis. METHODS: In this retrospective study, we assessed the performance of different supervised machine learning algorithms for the early differential diagnosis of candidemia and bacteremia in adult patients on a large dataset automatically extracted within the AUTO-CAND project. RESULTS: Overall, 12,483 episodes of candidemia (1275; 10%) or bacteremia (11,208; 90%) were included in the analysis. A random forest classifier achieved the best diagnostic performance for candidemia, with sensitivity 0.98 and specificity 0.65 on the training set (true skill statistic [TSS] = 0.63) and sensitivity 0.74 and specificity 0.57 on the test set (TSS = 0.31). Then, the random classifier was trained in the subgroup of patients with available serum ß-D-glucan (BDG) and procalcitonin (PCT) values by exploiting the feature ranking learned in the entire dataset. Although no statistically significant differences were observed from the performance measures obtained by employing BDG and PCT alone, the performance measures of the classifier that included the features selected in the entire dataset, plus BDG and PCT, were the highest in most cases. CONCLUSIONS: Random forest classifiers trained on large datasets of automatically extracted data have the potential to improve current diagnostic algorithms for candidemia. However, further development through implementation of automatically extracted clinical features may be necessary to achieve crucial improvements.

Semi-Quantification of Myocardial Uptake of Bone-Seeking Agents in Suspected Cardiac Amyloidosis.

INTRODUCTION: Bone scintigraphy has emerged as a key tool for non-invasive etiologic diagnosis of transthyretin (ATTR) cardiac amyloidosis (CA). We focused on a new semi-quantification method (on planar imaging) that could complement the qualitative/visual Perugini scoring system, especially when SPET/CT is not available. MATERIAL AND METHODS: We retrospectively/qualitatively evaluated 8674 consecutive, planar 99mTc-biphosphonate scintigraphies (performed for non-cardiac reasons), identifying 68 (0.78%) individuals (mean age 79 ± 7 years, range 62-100 years; female/male ratio 16/52) presenting myocardial uptake. Due to the retrospective nature of the study, no SPET/CT, pathologic or genetic confirmation was obtained. The Perugini scoring system was determined (in patients presenting cardiac uptake) and compared with three newly proposed semi-quantitative indices. We took 349 consecutive bone scintigraphies, qualitatively absent of any cardiac/pulmonary uptake, as "healthy controls" (HC). RESULTS: The heart-to-thigh ratio (RHT) and lung-to-thigh ratio (RLT) indices were significantly higher in patients than in HCs (p ≤ 0.0001). There were statistically significant differences for RHT in HCs vs. patients with qualitative Perugini scores of 1 or >1 (with p ranging from ≤0.001 to ≤0.0001). ROC curves showed that RHT outperformed the other indices and was more accurate in both male and female groups. Furthermore, in the male population, RHT accurately distinguished HCs and patients with scores of 1 (less likely affected by ATTR) from patients with qualitative scores >1 (more likely affected by ATTR) with an AUC of 99% (sensitivity: 95%; specificity: 97%). CONCLUSION: The proposed semi-quantitative RHT index can accurately/semi-quantitatively distinguish between HCs and subjects probably affected by CA (Perugini scores from 1 to 3), and could be particularly useful when no SPET/CT data are available (such as in retrospective studies and data mining). Furthermore, RHT can semi-quantitatively predict, with very high accuracy, subjects in the male population more likely to be affected by ATTR. The present study, although using a very large sample, is however retrospective, monocentric, and therefore the generalizability of the results should be proved by an accurate external validation. ADVANCES IN KNOWLEDGE: The proposed heart-to-thigh ratio (RHT) can distinguish healthy controls and subjects that are probably affected by cardiac amyloidosis in a simple and more reproducible way, as compared to standard qualitative/visual evaluation.

Freehand 1.5T MR-Guided Vacuum-Assisted Breast Biopsy (MR-VABB): Contribution of Radiomics to the Differentiation of Benign and Malignant Lesions.

Radiomics and artificial intelligence have been increasingly applied in breast MRI. However, the advantages of using radiomics to evaluate lesions amenable to MR-guided vacuum-assisted breast biopsy (MR-VABB) are unclear. This study includes patients scheduled for MR-VABB, corresponding to subjects with MRI-only visible lesions, i.e., with a negative second-look ultrasound. The first acquisition of the multiphase dynamic contrast-enhanced MRI (DCE-MRI) sequence was selected for image segmentation and radiomics analysis. A total of 80 patients with a mean age of 55.8 years ± 11.8 (SD) were included. The dataset was then split into a training set (50 patients) and a validation set (30 patients). Twenty out of the 30 patients with a positive histology for cancer were in the training set, while the remaining 10 patients with a positive histology were included in the test set. Logistic regression on the training set provided seven features with significant p values (<0.05): (1) 'AverageIntensity', (2) 'Autocorrelation', (3) 'Contrast', (4) 'Compactness', (5) 'StandardDeviation', (6) 'MeanAbsoluteDeviation' and (7) 'InterquartileRange'. AUC values of 0.86 (95% C.I. 0.73-0.94) for the training set and 0.73 (95% C.I. 0.54-0.87) for the test set were obtained for the radiomics model. Radiological evaluation of the same lesions scheduled for MR-VABB had AUC values of 0.42 (95% C.I. 0.28-0.57) for the training set and 0.4 (0.23-0.59) for the test set. In this study, a radiomics logistic regression model applied to DCE-MRI images increased the diagnostic accuracy of standard radiological evaluation of MRI suspicious findings in women scheduled for MR-VABB. Confirming this performance in large multicentric trials would imply that using radiomics in the assessment of patients scheduled for MR-VABB has the potential to reduce the number of biopsies, in suspicious breast lesions where MR-VABB is required, with clear advantages for patients and healthcare resources.

Validation of an Automated System for the Extraction of a Wide Dataset for Clinical Studies Aimed at Improving the Early Diagnosis of Candidemia.

There is increasing interest in assessing whether machine learning (ML) techniques could further improve the early diagnosis of candidemia among patients with a consistent clinical picture. The objective of the present study is to validate the accuracy of a system for the automated extraction from a hospital laboratory software of a large number of features from candidemia and/or bacteremia episodes as the first phase of the AUTO-CAND project. The manual validation was performed on a representative and randomly extracted subset of episodes of candidemia and/or bacteremia. The manual validation of the random extraction of 381 episodes of candidemia and/or bacteremia, with automated organization in structured features of laboratory and microbiological data resulted in ≥99% correct extractions (with confidence interval < ±1%) for all variables. The final automatically extracted dataset consisted of 1338 episodes of candidemia (8%), 14,112 episodes of bacteremia (90%), and 302 episodes of mixed candidemia/bacteremia (2%). The final dataset will serve to assess the performance of different ML models for the early diagnosis of candidemia in the second phase of the AUTO-CAND project.

CT Texture Analysis of Adrenal Pheochromocytomas: A Pilot Study.

Radiomics is a promising research field that combines big data analysis (from tissue texture analysis) with clinical questions. We studied the application of CT texture analysis in adrenal pheochromocytomas (PCCs) to define the correlation between the extracted features and the secretory pattern, the histopathological data, and the natural history of the disease. A total of 17 patients affected by surgically removed PCCs were retrospectively enrolled. Before surgery, all patients underwent contrast-enhanced CT and complete endocrine evaluation (catecholamine secretion and genetic evaluation). The pheochromocytoma adrenal gland scaled score (PASS) was determined upon histopathological examination. After a resampling of all CT images, the PCCs were delineated using LifeX software in all three phases (unenhanced, arterial, and venous), and 58 texture parameters were extracted for each volume of interest. Using the Mann-Whitney test, the correlations between the hormonal hypersecretion, the malignancy score of the lesion (PASS > 4), and texture parameters were studied. The parameters DISCRETIZED_HUpeak and GLZLM_GLNU in the unenhanced phase and GLZLM_SZE, CONVENTIONAL_HUmean, CONVENTIONAL_HUQ3, DISCRETIZED_HUmean, DISCRETIZED_AUC_CSH, GLRLM_HGRE, and GLZLM_SZHGE in the venous phase were able to differentiate secreting PCCs (p < 0.01), and the parameters GLZLM_GLNU in the unenhanced phase and GLRLM_GLNU and GLRLM_RLNU in the venous differentiated tumors with low and high PASS. CT texture analysis of adrenal PCCs can be a useful tool for the early identification of secreting or malignant tumors.

Gene's expression underpinning the divergent predictive value of [18F]F-fluorodeoxyglucose and prostate-specific membrane antigen positron emission tomography in primary prostate cancer: a bioinformatic and experimental study.

BACKGROUND: Positron Emission Tomography (PET) imaging with Prostate-Specific Membrane Antigen (PSMA) and Fluorodeoxyglucose (FDG) represent promising biomarkers for risk-stratification of Prostate Cancer (PCa). We verified whether the expression of genes encoding for PSMA and enzymes regulating FDG cellular uptake are independent and additive prognosticators in PCa. METHODS: mRNA expression of genes involved in glucose metabolism and PSMA regulation obtained from primary PCa specimens were retrieved from open-source databases and analyzed using an integrative bioinformatics approach. Machine Learning (ML) techniques were used to create predictive Progression-Free Survival (PFS) models. Cellular models of primary PCa with different aggressiveness were used to compare [18F]F-PSMA-1007 and [18F]F-FDG uptake kinetics in vitro. Confocal microscopy, immunofluorescence staining, and quantification analyses were performed to assess the intracellular and cellular membrane PSMA expression. RESULTS: ML analyses identified a predictive functional network involving four glucose metabolism-related genes: ALDOB, CTH, PARP2, and SLC2A4. By contrast, FOLH1 expression (encoding for PSMA) did not provide any additive predictive value to the model. At a cellular level, the increase in proliferation rate and migratory potential by primary PCa cells was associated with enhanced FDG uptake and decreased PSMA retention (paralleled by the preferential intracellular localization). CONCLUSIONS: The overexpression of a functional network involving four glucose metabolism-related genes identifies a higher risk of disease progression since the earliest phases of PCa, in agreement with the acknowledged prognostic value of FDG PET imaging. By contrast, the prognostic value of PSMA PET imaging is independent of the expression of its encoding gene FOLH1. Instead, it is influenced by the protein docking to the cell membrane, regulating its accessibility to tracer binding.

Longitudinal Cluster Analysis of Hemodialysis Patients with COVID-19 in the Pre-Vaccination Era.

Coronavirus disease 2019 (COVID-19) in hemodialysis patients (HD) is characterized by heterogeneity of clinical presentation and outcomes. To stratify patients, we collected clinical and laboratory data in two cohorts of HD patients at COVID-19 diagnosis and during the following 4 weeks. Baseline and longitudinal values were used to build a linear mixed effect model (LME) and define different clusters. The development of the LME model in the derivation cohort of 17 HD patients (66.7 ± 12.3 years, eight males) allowed the characterization of two clusters (cl1 and cl2). Patients in cl1 presented a prevalence of females, higher lymphocyte count, and lower levels of lactate dehydrogenase, C-reactive protein, and CD8 + T memory stem cells as a possible result of a milder inflammation. Then, this model was tested in an independent validation cohort of 30 HD patients (73.3 ± 16.3 years, 16 males) assigned to cl1 or cl2 (16 and 14 patients, respectively). The cluster comparison confirmed that cl1 presented a milder form of COVID-19 associated with reduced disease activity, hospitalization, mortality rate, and oxygen requirement. Clustering analysis on longitudinal data allowed patient stratification and identification of the patients at high risk of complications. This strategy could be suitable in different clinical settings.

Neurological long-COVID in the outpatient clinic: Two subtypes, two courses.

INTRODUCTION: Symptoms referable to central and peripheral nervous system involvement are often evident both during the acute phase of COVID-19 infection and during long-COVID. In this study, we evaluated a population of patients with prior COVID-19 infection who showed signs and symptoms consistent with neurological long-COVID. METHODS: We prospectively collected demographic and acute phase course data from patients with prior COVID-19 infection who showed symptoms related to neurological involvement in the long-COVID phase. Firstly, we performed a multivariate logistic linear regression analysis to investigate the impact of demographic and clinical data, the severity of the acute COVID-19 infection and hospitalization course, on the post-COVID neurological symptoms at three months follow-up. Secondly, we performed an unsupervised clustering analysis to investigate whether there was evidence of different subtypes of neurological long COVID-19. RESULTS: One hundred and nine patients referred to the neurological post-COVID outpatient clinic. Clustering analysis on the most common neurological symptoms returned two well-separated and well-balanced clusters: long-COVID type 1 contains the subjects with memory disturbances, psychological impairment, headache, anosmia and ageusia, while long-COVID type 2 contains all the subjects with reported symptoms related to PNS involvement. The analysis of potential risk-factors among the demographic, clinical presentation, COVID 19 severity and hospitalization course variables showed that the number of comorbidities at onset, the BMI, the number of COVID-19 symptoms, the number of non-neurological complications and a more severe course of the acute infection were all, on average, higher for the cluster of subjects with reported symptoms related to PNS involvement. CONCLUSION: We analyzed the characteristics of neurological long-COVID and presented a method to identify well-defined patient groups with distinct symptoms and risk factors. The proposed method could potentially enable treatment deployment by identifying the optimal interventions and services for well-defined patient groups, so alleviating long-COVID and easing recovery.

18F-FDG-PET/MRI texture analysis in rectal cancer after neoadjuvant chemoradiotherapy.

OBJECTIVE: Reliable markers to predict the response to neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer (LARC) are lacking. We aimed to assess the ability of 18F-FDG PET/MRI to predict response to nCRT among patients undergoing curative-intent surgery. METHODS: Patients with histological-confirmed LARC who underwent curative-intent surgery following nCRT and restaging with 18F-FDG PET/MRI were included. Statistical correlation between radiomic features extracted in PET, apparent diffusion coefficient (ADC) and T2w images and patients' histopathologic response to chemoradiotherapy using a multivariable logistic regression model ROC-analysis. RESULTS: Overall, 50 patients were included in the study. A pathological complete response was achieved in 28.0% of patients. Considering second-order textural features, nine parameters showed a statistically significant difference between the two groups in ADC images, six parameters in PET images and four parameters in T2w images. Combining all the features selected for the three techniques in the same multivariate ROC curve analysis, we obtained an area under ROC curve of 0.863 (95% CI, 0.760-0.966), showing a sensitivity, specificity and accuracy at the Youden's index of 100% (14/14), 64% (23/36) and 74% (37/50), respectively. CONCLUSION: PET/MRI texture analysis seems to represent a valuable tool in the identification of rectal cancer patients with a complete pathological response to nCRT.