Depression Identification Using EEG Signals via a Hybrid of LSTM and Spiking Neural Networks

Depression severity can be classified into distinct phases based on the Beck depression inventory (BDI) test scores, a subjective questionnaire. However, quantitative assessment of depression may be attained through the examination and categorization of electroencephalography (EEG) signals. Spiking neural networks (SNNs), as the third generation of neural networks, incorporate biologically realistic algorithms, making them ideal for mimicking internal brain activities while processing EEG signals. This study introduces a novel framework that for the first time, combines an SNN architecture and a long short-term memory (LSTM) structure to model the brain's underlying structures during different stages of depression and effectively classify individual depression levels using raw EEG signals. By employing a brain-inspired SNN model, our research provides fresh perspectives and advances knowledge of the neurological mechanisms underlying different levels of depression. The methodology employed in this study includes the utilization of the synaptic time dependent plasticity (STDP) learning rule within a 3-dimensional brain-template structured SNN model. Furthermore, it encompasses the tasks of classifying and predicting individual outcomes, visually representing the structural alterations in the brain linked to the anticipated outcomes, and offering interpretations of the findings. Notably, our method achieves exceptional accuracy in classification, with average rates of 98% and 96% for eyes-closed and eyes-open states, respectively. These results significantly outperform state-of-the-art deep learning methods.

Follow-up with Telemedicine in Early Discharge for COPD Exacerbations: Randomized Clinical Trial (TELEMEDCOPD-Trial)

The results reported by different studies on telemonitoring in patients with chronic obstructive pulmonary disease (COPD) have been contradictory, without showing clear benefits to date. The objective of this study was to ascertain whether an early discharge and home hospitalization telehealth program for patients with COPD exacerbation is as effective as and more efficient than a traditional early discharge and home hospitalization program. A prospective experimental non-inferiority study, randomized into two groups (telemedicine/control) was conducted. The telemedicine group underwent monitoring and was required to transmit data on vital constants and ECGs twice per day, with a subsequent telephone call and 2 home visits by healthcare staff (intermediate and at discharge). The control group received daily visits. The main variable was time until first exacerbation. The secondary variables were: number of exacerbations; use of healthcare resources; satisfaction; quality of life; anxiety-depression; and therapeutic adherence, measured at one and 6 months of hospital discharge. A total of 116 patients were randomized (58 to each group) without significant differences in baseline characteristics or time until first exacerbation, i.e. median 48 days (pp. 25-75:23-120) in the control group, and 47 days (pp. 25-75:19-102) in the intervention group; p = 0.52). A significant decrease in the number of visits was observed in the intervention versus the control group, 3.8 ± 1 vs 5.1 ± 2(p = 0.001), without significant differences in the number of exacerbations. In conclusion follow-up via a telemedicine program in early discharge after hospitalization is as effective as conventional home follow up, being the cost of either strategy not significantly different.

The effects of cause of death classification on prognostic assessment of patients with pulmonary embolism

BACKGROUND

Although previous studies have provided evidence that the majority of deaths following an acute pulmonary embolism (PE) directly relate to the PE, more recent registries and cohort studies suggest otherwise.

METHODS

We assessed the cause of death during the first 30 days after the diagnosis of acute symptomatic PE in a consecutive series of patients. We also assessed the prognostic characteristics of the simplified Pulmonary Embolism Severity Index (sPESI) and cardiac troponin I (cTnI) obtained at the time of PE diagnosis.

RESULTS

During the first 30 days after diagnosis, 127 of the 1291 patients died (9.8%; 95% confidence interval [CI], 8.2-11.5). Sixty patients (4.6%; 95% CI, 3.5-5.8) died from definite or possible PE, and 67 (5.2%; 95% CI, 4.0-6.4) died from other causes (cancer 25, infection 18, hemorrhage 7, heart failure 7, chronic obstructive pulmonary disease 5, renal failure 1, seizures 1, unknown 3). The sPESI predicted all-cause (odds ratio [OR], 5.97; 95% CI, 1.74-20.54; P < 0.01) and PE-associated mortality (OR, 8.79; 95% CI, 1.12-68.79; P = 0.04). cTnI only predicted PE-associated mortality (adjusted OR, 2.39; 95% CI, 1.25-4.57; P < 0.01). For all-cause mortality, the sPESI low-risk strata had a negative predictive value of 98.8% (95% CI, 97.4-100) in comparison with 91.3% (95% CI, 88.9-93.6) for the cTnI.

CONCLUSIONS

Within the first 30 days after the diagnosis of acute symptomatic PE, death due to PE and death due to other causes occur in a similar proportion of patients. As cTnI only predicted PE-associated mortality, low-risk sPESI had a higher negative predictive value for all-cause mortality compared with cTnI.

Diagnostic and prognostic use of FDG-PET scans in Waldenstrom's macroglobulinemia

e19518

Background: Waldenstrom's macroglobulinemia (WM) is a rare lymphoplasmacytic lymphoma. More sensitive tools of tumor burden and prognosis are needed in these patients (pts). The use of FDG-PET has not been previously studied in WM but has proved an effective diagnostic and prognostic tool effective in low-grade lymphomas. Therefore the objective of this study was to determine whether FDG-PET was an effective tool in evaluating pts with WM. Methods: We included all pts enrolled on a prospective phase II clinical trial of bortezomib and rituximab for pts with upfront or relapsed/refractory (RR) WM. All pts were CD20 positive with histologically confirmed disease and underwent staging evaluation by FDG-PET in combination with CT scan before and after therapy. Patients received 6 cycles of bortezomib IV weekly at 1.6mg/m2 on days 1, 8, 15q28 and rituximab at 375 mg/m2 on days 1, 8, 15 and 22 in cycles 1 and 4. Correlation was made with the international prognostic scoring system for WM and monoclonal protein response rate. Results: 53 pts were included, of which 35 were RR and 18 pts were upfront. Median age was 63 years (range 42–81), 64% were male. Before therapy, 34 pts (64.2%) had positive FDG-PET findings with a median IgM of 2825, Beta 2 microglobulin of 3.6, and Age of 61. 36 pts showed a minor response or greater with a correlation to negative PETs after therapy. Conclusions: Over 60% of WM pts demonstrated FDG-avid disease when using FDG-PET scans, with the majority showing negative disease after therapy. This correlates with the 67.9% response rate. Positive PET images were inversely correlated to IgM level and directly related to elevated Beta-2 microglobulin and age. Significantly PET positive individuals may demonstrate a poorer prognosis. FDG-PET scans may prove an effective tool in the diagnosis and prognosis in WM.

[Table: see text]

Home environment and asthma in school children from the Edirne region in Turkey

Studies have shown that environmental factors contribute to the development of asthma. Hence, we investigated the relation between current asthma and indoor environmental factors such as exposure to pets, tobacco smoke, home dampness, number of people living in home, and stuffed toys in child's bedroom in a questionnaire based study in primary school children aged 6 to 12 years living in Edirne (Turkey). In a random sample of 4 primary schools, questionnaires were completed by parents of 1000 children. Following the evaluation of 682 of these, 85 were selected as cases of asthma of which 24 were diagnosed by a physician. When required certain laboratory tests were also performed in order to confirm the diagnosis. Logistic regression was used to investigate the associations between asthma and potential risk factors. In logistic regression analyses, the following factors were associated with asthma. Dampness in the house [(odd's ratio (O.R) = 2.61; 95% CI 1.13 to 6.81), stuffed toys in the child's bedroom (O.R = 2.18; 95% CI 1.27 to 3.74), and the crowding index (O.R = 2.73; 95% CI 1.08 to 6.82)]. In conclusion, it was found that presence of asthma was significantly associated with the presence of dampness in the house, and stuffed toys in the child's bedroom. Asthma can be prevented by improvement of the indoor environment. Therefore providing education to high-risk populations for avoidance of these risk factors is particularly important.