Forecasting Progressive Trends in Keratoconus by Means of a Time Delay Neural Network

Early and accurate detection of keratoconus progression is particularly important for the prudent, cost-effective use of corneal cross-linking and judicious timing of clinical follow-up visits. The aim of this study was to verify whether a progression could be predicted based on two prior tomography measurements and to verify the accuracy of the system when labelling the eye as stable or suspect progressive. Data from 743 patients measured by Pentacam (Oculus, Wetzlar, Germany) were available, and they were filtered and preprocessed to data quality needs. The time delay neural network received six features as input, measured in two consecutive examinations, predicted the future values, and determined the classification (stable or suspect progressive) based on the significance of the change from the baseline. The system showed a sensitivity of 70.8% and a specificity of 80.6%. On average, the positive and negative predictive values were 71.4% and 80.2%. Including data of less quality (as defined by the software) did not significantly worsen the results. This predictive system constitutes another step towards a personalized management of keratoconus. While the results obtained were modest and perhaps insufficient to decide on a surgical procedure, such as cross-linking, they may be useful to customize the timing for the patient’s next follow-up.

Molecular Pathology and Targeted Therapies for Personalized Management of Central Nervous System Germinoma

Intracranial germinomas are rare tumours, usually affecting male paediatric patients. They frequently develop in the pineal and suprasellar regions, causing endocrinological disturbances, visual deficits, and increased intracranial pressure. The diagnosis is established on magnetic resonance imaging (MRI), serum and cerebrospinal fluid (CSF) markers, and tumour stereotactic biopsy. Imaging techniques, such as susceptibility-weighted imaging (SWI), T2* (T2-star) gradient echo (GRE) or arterial spin labelling based perfusion-weighted MRI (ASL-PWI) facilitate the diagnosis. Germinomas are highly radiosensitive tumours, with survival rates >90% in the context of chemoradiotherapy. However, patients with resistant disease have limited therapeutic options and poor survival. The aim of this review is to highlight the genetic, epigenetic, and immunologic features, which could provide the basis for targeted therapy. Intracranial germinomas present genetic and epigenetic alterations (chromosomal aberrations, KIT, MAPK and PI3K pathways mutations, DNA hypomethylation, miRNA dysregulation) that may represent targets for therapy. Tyrosine kinase and mTOR inhibitors warrant further investigation in these cases. Immune markers, PD-1 (programmed cell death protein 1) and PD-L1 (programmed death-ligand 1), are expressed in germinomas, representing potential targets for immune checkpoint inhibitors. Resistant cases should benefit from a personalized management: genetic and immunological testing and enrolment in trials evaluating targeted therapies in intracranial germinomas.

Personalized management of pheochromocytoma and paraganglioma

Pheochromocytomas/paragangliomas are characterized by a unique molecular landscape that allows their assignment to clusters depending on underlying genetic alterations. With around 30-35% of Caucasian patients (a lower percentage in the Chinese population) showing germline mutations in susceptibility genes, pheochromocytomas/paragangliomas have the highest rate of heritability among all tumors. A further 35-40% of Caucasian patients (a higher percentage in the Chinese population) are affected by somatic driver-mutations. Thus, around 70% of all patients with pheochromocytoma/paraganglioma can be assigned to one of three main molecular clusters with different phenotypes and clinical behavior. Krebs cycle/VHL/EPAS1-related cluster 1 tumors tend to a noradrenergic biochemical phenotype, and require very close follow-up due to the risk of metastasis and recurrence. In contrast, kinase signaling-related cluster 2 tumors are characterized by an adrenergic phenotype and episodic symptoms, with generally a less aggressive course. The clinical correlates of patients with Wnt signaling-related cluster 3 tumors are currently poorly described, but aggressive behavior seems likely. In this review, we explore and explain why cluster-specific (personalized) management of pheochromocytoma/paraganglioma is essential to ascertain clinical behavior and prognosis, guide individual diagnostic procedures (biochemical interpretation, choice of the most sensitive imaging modalities), and personalized management and follow-up. Although cluster-specific therapy of inoperable/metastatic disease has not yet entered routine clinical practice, we suggest that informed personalized genetic-driven treatment should be implemented as a logical next step. This review amalgamates published guidelines and expert views within each cluster for a coherent individualized patient management plan.

Three Different Genetic Risk Scores Based on Fatty Liver Index, Magnetic Resonance Imaging and Lipidomic for a Nutrigenetic Personalized Management of NAFLD: The Fatty Liver in Obesity Study

Non-alcoholic fatty liver disease (NAFLD) affects 25% of the global population. The pathogenesis of NAFLD is complex; available data reveal that genetics and ascribed interactions with environmental factors may play an important role in the development of this morbid condition. The purpose of this investigation was to assess genetic and non-genetic determinants putatively involved in the onset and progression of NAFLD after a 6-month weight loss nutritional treatment. A group of 86 overweight/obese subjects with NAFLD from the Fatty Liver in Obesity (FLiO) study were enrolled and metabolically evaluated at baseline and after 6 months. A pre-designed panel of 95 genetic variants related to obesity and weight loss was applied and analyzed. Three genetic risk scores (GRS) concerning the improvement on hepatic health evaluated by minimally invasive methods such as the fatty liver index (FLI) (GRSFLI), lipidomic-OWLiver®-test (GRSOWL) and magnetic resonance imaging (MRI) (GRSMRI), were derived by adding the risk alleles genotypes. Body composition, liver injury-related markers and dietary intake were also monitored. Overall, 23 SNPs were independently associated with the change in FLI, 16 SNPs with OWLiver®-test and 8 SNPs with MRI, which were specific for every diagnosis tool. After adjusting for gender, age and other related predictors (insulin resistance, inflammatory biomarkers and dietary intake at baseline) the calculated GRSFLI, GRSOWL and GRSMRI were major contributors of the improvement in hepatic status. Thus, fitted linear regression models showed a variance of 53% (adj. R2 = 0.53) in hepatic functionality (FLI), 16% (adj. R2 = 0.16) in lipidomic metabolism (OWLiver®-test) and 34% (adj. R2 = 0.34) in liver fat content (MRI). These results demonstrate that three different genetic scores can be useful for the personalized management of NAFLD, whose treatment must rely on specific dietary recommendations guided by the measurement of specific genetic biomarkers.