In this paper, new features relevant to blood pressure (BP) estimation using photoplethysmography (PPG) are presented. A total of 195 features, including the proposed ones and those already known in ...the literature, have been calculated on a set composed of 50,000 pulses from 1080 different patients. Three feature selection methods, namely Correlation-based Feature Selection (CFS), RReliefF and Minimum Redundancy Maximum Relevance (MRMR), have then been applied to identify the most significant features for BP estimation. Some of these features have been extracted through a novel PPG signal enhancement method based on the use of the Maximal Overlap Discrete Wavelet Transform (MODWT). As a matter of fact, the enhanced signal leads to a reliable identification of the characteristic points of the PPG signal (e.g., systolic, diastolic and dicrotic notch points) by simple means, obtaining results comparable with those from purposely defined algorithms. For systolic points, mean and std of errors computed as the difference between the locations obtained using a purposely defined already known algorithm and those using the MODWT enhancement are, respectively, 0.0097 s and 0.0202 s; for diastolic points they are, respectively, 0.0441 s and 0.0486 s; for dicrotic notch points they are 0.0458 s and 0.0896 s. Hence, this study leads to the selection of several new features from the MODWT enhanced signal on every single pulse extracted from PPG signals, in addition to features already known in the literature. These features can be employed to train machine learning (ML) models useful for estimating systolic blood pressure (
) and diastolic blood pressure (
) in a non-invasive way, which is suitable for telemedicine health-care monitoring.
In this paper, a machine learning (ML) approach to estimate blood pressure (BP) using photoplethysmography (PPG) is presented. The final aim of this paper was to develop ML methods for estimating ...blood pressure (BP) in a non-invasive way that is suitable in a telemedicine health-care monitoring context. The training of regression models useful for estimating systolic blood pressure (SBP) and diastolic blood pressure (DBP) was conducted using new extracted features from PPG signals processed using the Maximal Overlap Discrete Wavelet Transform (MODWT). As a matter of fact, the interest was on the use of the most significant features obtained by the Minimum Redundancy Maximum Relevance (MRMR) selection algorithm to train eXtreme Gradient Boost (XGBoost) and Neural Network (NN) models. This aim was satisfactorily achieved by also comparing it with works in the literature; in fact, it was found that XGBoost models are more accurate than NN models in both systolic and diastolic blood pressure measurements, obtaining a Root Mean Square Error (RMSE) for SBP and DBP, respectively, of 5.67 mmHg and 3.95 mmHg. For SBP measurement, this result is an improvement compared to that reported in the literature. Furthermore, the trained XGBoost regression model fulfills the requirements of the Association for the Advancement of Medical Instrumentation (AAMI) as well as grade A of the British Hypertension Society (BHS) standard.
Digitalization is playing a prominent role in cultural economics reshaping GLAM organizations toward a more relevant income generation. However achieving a higher level of digitalization requires ...careful management and resource planning. To this end, the concept of digital maturity provides a useful description of an organization current level of digitalization, allowing for a more effective digital transformation process. The literature concerning business studies and information technology developed highly detailed surveys to assess digital maturity levels within organizations, the so-called digital maturity models. Nevertheless, while many of them are manufacturing-based, very few are wide-spectrum models allowing for a generic assessment of digital maturity. This paper provides a preliminary descriptive analysis on the aptitude of Italian and Campania GLAMs for deploying digital facilities and services, thus suggesting the need to elaborate a specific digital maturity model for GLAM organizations.
IgA nephropathy has variable clinical presentation and progression. Its definitive diagnosis and prognosis require renal biopsy. The identification of new biomarkers allowing noninvasive diagnosis ...and monitoring of disease activity would be advantageous. This study analyzed the urine proteome of IgA nephropathy patients at an early stage of disease.
Urine from 49 IgA nephropathy patients, 42 CKD patients, and 40 healthy individuals was analyzed by surface-enhanced laser desorption/ionization time of flight/mass spectrometry. Differentially excreted proteins were identified by matrix-enhanced laser desorption/ionization time of flight/mass spectrometry, confirmed by immunologic methods, and validated in an independent set of patients (14 IgA nephropathy and 24 CKD). All patients were recruited at the Division of Nephrology of the University of Foggia from January of 2005 to March of 2007.
Two proteins, with 21,598 and 23,458 m/z, were significantly decreased in IgA nephropathy and identified as Perlecan laminin G-like 3 peptide and Ig κ light chains, respectively. Western blot analysis confirmed the lower urinary excretion of laminin G-like 3 in IgA nephropathy patients compared with CKD patients and healthy individuals. Immunonephelometry analysis confirmed the lower urinary excretion of free κ light chains in IgA nephropathy patients compared with CKD patients and healthy individuals. Immunohistochemistry analysis justified the urinary excretion profile of such proteins in IgA nephropathy. Finally, urinary free κ light chains and laminin G-like 3 concentration inversely correlated with severity of clinical and histologic features of our IgA nephropathy cohort.
Laminin G-like 3 and free κ light chains can contribute to the noninvasive assessment of IgA nephropathy disease activity.
LPS-induced sepsis is a leading cause of acute kidney injury (AKI) in critically ill patients. LPS may induce CD80 expression in podocytes with subsequent onset of proteinuria, a risk factor for ...progressive chronic kidney disease (CKD) frequently observed after AKI. This study aimed to investigate the therapeutic efficacy of LPS removal in decreasing albuminuria through the reduction of podocyte CD80 expression. Between January 2015 and December 2017, 70 consecutive patients with Gram-negative sepsis-induced AKI were randomized to either have coupled plasma filtration and adsorption (CPFA) added to the standard care ( n = 35) or not ( n = 35). To elucidate the possible relationship between LPS-induced renal damage, proteinuria, and CD80 expression in Gram sepsis, a swine model of LPS-induced AKI was set up. Three hours after LPS infusion, animals were treated or not with CPFA for 6 h. Treatment with CPFA significantly reduced serum cytokines, C-reactive protein, procalcitonin, and endotoxin levels in patients with Gram-negative sepsis-induced AKI. CPFA significantly lowered also proteinuria and CD80 urinary excretion. In the swine model of LPS-induced AKI, CD80 glomerular expression, which was undetectable in control pigs, was markedly increased at the podocyte level in LPS-exposed animals. CPFA significantly reduced LPS-induced proteinuria and podocyte CD80 expression in septic pigs. Our data indicate that LPS induces albuminuria via podocyte expression of CD80 and suggest a possible role of timely LPS removal in preventing the maladaptive repair of the podocytes and the consequent increased risk of CKD in sepsis-induced AKI.
Nasu-Hakola Disease (NHD) is a recessively inherited systemic leukodystrophy disorder characterized by a combination of frontotemporal presenile dementia and lytic bone lesions. NHD is known to be ...genetically related to a structural defect of TREM2 and DAP12, two genes that encode for different subunits of the membrane receptor signaling complex expressed by microglia and osteoclast cells. Because of its rarity, molecular or proteomic studies on this disorder are absent or scarce, only case reports based on neuropsychological and genetic tests being reported. In light of this, the aim of this paper is to provide evidence on the potential of a label-free proteomic platform based on the Multidimensional Protein Identification Technology (MudPIT), combined with in-house software and on-line bioinformatics tools, to characterize the protein expression trends and the most involved pathways in NHD. The application of this approach on the Lymphoblastoid cells from a family composed of individuals affected by NHD, healthy carriers and control subjects allowed for the identification of about 3000 distinct proteins within the three analyzed groups, among which proteins anomalous to each category were identified. Of note, several differentially expressed proteins were associated with neurodegenerative processes. Moreover, the protein networks highlighted some molecular pathways that may be involved in the onset or progression of this rare frontotemporal disorder. Therefore, this fully automated MudPIT platform which allowed, for the first time, the generation of the whole protein profile of Lymphoblastoid cells from Nasu-Hakola subjects, could be a valid approach for the investigation of similar neurodegenerative diseases.
OBJECTIVE: Chronic renal insufficiency and/or proteinuria in type 2 diabetes may stem from chronic renal diseases (CKD) other than classic diabetic nephropathy in more than one-third of patients. We ...interrogated urine proteomic profiles generated by surface-enhanced laser desorption/ionization-time of flight/mass spectrometry with the aim of isolating a set of biomarkers able to reliably identify biopsy-proven diabetic nephropathy and to establish a stringent correlation with the different patterns of renal injury. RESEARCH DESIGN AND METHODS: Ten micrograms of urine proteins from 190 subjects (20 healthy subjects, 20 normoalbuminuric, and 18 microalbuminuric diabetic patients and 132 patients with biopsy-proven nephropathy: 65 diabetic nephropathy, 10 diabetic with nondiabetic CKD nd-CKD, and 57 nondiabetic with CKD) were run using a CM10 ProteinChip array and analyzed by supervised learning methods (Classification and Regression Tree analysis). RESULTS: The classification model correctly identified 75% of patients with normoalbuminuria, 87.5% of those with microalbuminuria, and 87.5% of those with diabetic nephropathy when applied to a blinded testing set. Most importantly, it was able to reliably differentiate diabetic nephropathy from nd-CKD in both diabetic and nondiabetic patients. Among the best predictors of the classification model, we identified and validated two proteins, ubiquitin and β₂-microglobulin. CONCLUSIONS: Our data suggest the presence of a specific urine proteomic signature able to reliably identify type 2 diabetic patients with diabetic glomerulosclerosis.
Introduction
Perinatal depression (PD) is a cluster of clinical depressive symptoms occurring globally during pregnancy or after childbirth, with a prevalence of 11.9%. Risk factors for PD among ...pregnant women may include personality traits of neuroticism, low personal resilience, higher anxiety, avoidance in close relationships, as well as dysfunctional coping strategies.
Methods
We report on descriptive findings of a screening/prevention program aimed to detect depressive symptoms and associated risk factors in a large sample of women (
N
= 1,664) accessing the gynecological departments of the Regione Puglia (South of Italy) from July to November 2020. Pregnant women were assessed in their third trimester of pregnancy (T0), after childbirth (T1), and those at risk for PD within 1 year from delivery (T2–T4); The Edinburgh Postnatal Depression Scale (EPDS) has been employed for the screening of PD over time as well as other standardized measures for neuroticism, resilience, coping strategies, and quality of life.
Results
Of 1,664,
n
= 1,541 were tested at T1, and 131 scored ≥ 12 at EPDS (14.6 ± 2.95), showing a higher risk for PD. They were followed over time at 1, 6, and 12 months after childbirth (T2–T4), and 15 of them scored ≥ 12 (EPDS) at T4. Women with a higher risk of PD also reported higher levels of neuroticism, lower levels of personal resilience, more anxiety and avoidance in close relationships, higher employment of dysfunctional coping strategies (e.g., denial, self-blame, etc.), and lower quality of life (0.0008 <
all p
< 0.0001).
Conclusion
This study confirmed the benefit of screening programs for the early detection of PD among pregnant women. We may suggest a set of risk factors to be considered in the clinical assessment of PD risk as well as the promotion of similar programs to improve depressive outcomes and pathways to care for PD on the basis of a more accurate assessment and referral.
PDF
