Futurists have anticipated that novel autonomous technologies, embedded with machine learning (ML), will substantially influence healthcare. ML is focused on making predictions as accurate as possible, while traditional statistical models are aimed at inferring relationships between variables. The benefits of ML comprise flexibility and scalability compared with conventional statistical approaches, which makes it deployable for several tasks, such as diagnosis and classification, and survival predictions. However, much of ML-based analysis remains scattered, lacking a cohesive structure. There is a need to evaluate and compare the performance of well-developed conventional statistical methods and ML on patient outcomes, such as survival, response to treatment, and patient-reported outcomes (PROs). In this article, we compare the usefulness and limitations of traditional statistical methods and ML, when applied to the medical field. Traditional statistical methods seem to be more useful when the number of cases largely exceeds the number of variables under study and a priori knowledge on the topic under study is substantial such as in public health. ML could be more suited in highly innovative fields with a huge bulk of data, such as omics, radiodiagnostics, drug development, and personalized treatment. Integration of the two approaches should be preferred over a unidirectional choice of either approach.
Amphotericin B is the gold standard for antifungal treatment for the most severe mycoses. However, adverse effects are common, with nephrotoxicity being the most serious, occurring early in the course of treatment, and usually being reversible in most patients. Tubular damage is a well known problem associated with amphotericin B therapy but acute renal failure is the most serious complication. Recent studies have examined ways to ameliorate the well-known toxicities of amphotericin B. A new approach has been to complex the drug with lipids or entrap it in liposomes. This review will concern amphotericin B-induced nephrotoxicity, whose mechanisms are not completely clear. Nephrotoxicity seems related to direct amphotericin B action on the renal tubules as well as to drug-induced renal vasoconstriction. The main mechanisms of nephrotoxicity suggested in the literature are presented. The clinical picture at different ages (adults, children, newborns), interactions of clinical significance, strategies for prevention of amphotericin B-induced nephrotoxicity are summarized. To provide optimal patient care, it is imperative that the clinician understand the etiology of and the signs and symptoms associated with nephrotoxicity, as well as interventions to prevent nephrotoxicity in patients receiving amphotericin B.
Human cystatin C, a basic low molecular mass protein with 120 amino acid residues, is freely filtered by the glomerulus and almost completely reabsorbed and catabolized by the proximal tubular cells. Cystatin C has been recently proposed as a new sensitive endogenous serum marker for the early assessment of changes in the glomerular filtration rate. To define a reference basis for future clinical investigations in the perinatal period, we investigated the relationship between maternal and neonatal serum cystatin C in comparison with that of creatinine. We also defined reference values in healthy women at full-term pregnancy and in full-term newborns over the first 5 days of life. Seventy-eight women with uncomplicated pregnancy, aged between 19 and 40 years, and their infant newborns (43 males, 35 females) were enrolled in the study. The gestational age ranged from 37 to 43 weeks, and the birth weight from 2.50 to 4.15 kg. Blood samples were taken from all the women immediately before delivery and from their newborns at birth, 72 and 96 h after birth. Maternal and neonatal renal function was evaluated by standards parameters and by calculating creatinine clearance. In all serum samples, we measured cystatin C, creatinine, and urea. At term gestation, serum cystatin C ranged from 0.64 to 2.30 mg/L. At birth, serum cystatin C values ranged from 1.17 to 3.06 mg/L, significantly decreasing after 3 and 5 days of life. No correlation was found between maternal and neonatal serum cystatin C values (r = 0.09). As cystatin C serum levels in newborns are not significantly correlated with the respective maternal levels, neonatal serum cystatin C may originate almost exclusively in the neonate.
Human Severe Acute Respiratory Syndrome CoronaVirus 2 (SARS-CoV-2) infection activates a complex interaction host/virus, leading to the reprogramming of the host metabolism aimed at the energy supply for viral replication. Alterations of the host metabolic homeostasis strongly influence the immune response to SARS-CoV-2, forming the basis of a wide range of outcomes, from the asymptomatic infection to the onset of COVID-19 and up to life-threatening acute respiratory distress syndrome, vascular dysfunction, multiple organ failure, and death. Deciphering the molecular mechanisms associated with the individual susceptibility to SARS-CoV-2 infection calls for a system biology approach; this strategy can address multiple goals, including which patients will respond effectively to the therapeutic treatment. The power of metabolomics lies in the ability to recognize endogenous and exogenous metabolites within a biological sample, measuring their concentration, and identifying perturbations of biochemical pathways associated with qualitative and quantitative metabolic changes. Over the last year, a limited number of metabolomics- and lipidomics-based clinical studies in COVID-19 patients have been published and are discussed in this review. Remarkable alterations in the lipid and amino acid metabolism depict the molecular phenotype of subjects infected by SARS-CoV-2; notably, structural and functional data on the lipids-virus interaction may open new perspectives on targeted therapeutic interventions. Several limitations affect most metabolomics-based studies, slowing the routine application of metabolomics. However, moving metabolomics from bench to bedside cannot imply the mere determination of a given metabolite panel; rather, slotting metabolomics into clinical practice requires the conversion of metabolic patient-specific data into actionable clinical applications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.