Background: The COVID-19 pandemic is probably the greatest health catastrophe of the modern era. Spain’s health care system has been exposed to uncontrollable numbers of patients over a short period, causing the system to collapse. Given that diagnosis is not immediate, and there is no effective treatment for COVID-19, other tools have had to be developed to identify patients at the risk of severe disease complications and thus optimize material and human resources in health care. There are no tools to identify patients who have a worse prognosis than others. Objective: This study aimed to process a sample of electronic health records of patients with COVID-19 in order to develop a machine learning model to predict the severity of infection and mortality from among clinical laboratory parameters. Early patient classification can help optimize material and human resources, and analysis of the most important features of the model could provide more detailed insights into the disease. Methods: After an initial performance evaluation based on a comparison with several other well-known methods, the extreme gradient boosting algorithm was selected as the predictive method for this study. In addition, Shapley Additive Explanations was used to analyze the importance of the features of the resulting model. Results: After data preprocessing, 1823 confirmed patients with COVID-19 and 32 predictor features were selected. On bootstrap validation, the extreme gradient boosting classifier yielded a value of 0.97 (95% CI 0.96-0.98) for the area under the receiver operator characteristic curve, 0.86 (95% CI 0.80-0.91) for the area under the precision-recall curve, 0.94 (95% CI 0.92-0.95) for accuracy, 0.77 (95% CI 0.72-0.83) for the F-score, 0.93 (95% CI 0.89-0.98) for sensitivity, and 0.91 (95% CI 0.86-0.96) for specificity. The 4 most relevant features for model prediction were lactate dehydrogenase activity, C-reactive protein levels, neutrophil counts, and urea levels. Conclusions: Our predictive model yielded excellent results in the differentiating among patients who died of COVID-19, primarily from among laboratory parameter values. Analysis of the resulting model identified a set of features with the most significant impact on the prediction, thus relating them to a higher risk of mortality.

Background: Neurofilament light chain levels (NfL) have emerged as a biomarker for early diagnosis and follow-up of hereditary transthyretin variant amyloidosis (ATTRv). We evaluated the most accurate technique for NfL quantifying in ATTRv healthy carriers and symptomatic patients in real-life practice, and assessed whether NfL may represent a reliable biomarker of disease onset and progression.Methods: Serum NfL were measured using ELISA and the single-molecule array (SIMoA) technique. Disease severity was assessed with a polyneuropathy disability score (PND).Results: Seventy-five subjects with pathogenic transthyretin variant (40 ATTRv healthy carriers and 35 ATTRv patients) were enrolled. We observed a significant correlation between ELISA and SIMoA assay (Pearson’s R2-value = 0.9899). Compared to healthy carriers, patients with symptomatic ATTRv had statistically higher serum NfL levels (p < 0.001). We propose a NfL cut-off of 7.9 pg./mL to distinguish between healthy carriers and ATTRv patients with high diagnostic accuracy (AUC = 0.847; p < 0.001; sensitivity = 90.0%; specificity = 55.0%), whereas the NfL threshold of 18.4 pg./mL discriminated the transition from patients with PND I to PND ≥ II (AUC = 0.695; p < 0.001; sensitivity = 67.0%, specificity = 86%).Conclusion: Serum NfL can be accurately quantified using both ELISA and SIMoA array, and it seems to be a reliable biomarker to detect the transition from presymptomatic to symptomatic disease onset and to monitor disease progression.

Postpartum Depression affects a considerable number of women worldwide. This condition inflicts severe consequences to mother and child health. Thus far, available treatments have low response and high relapse rates. We designed this trial to evaluate a safe and more efficacious innovative therapy. To report a feasible and ethical study design to assess the safety and efficacy of a high frequency repetitive Transcranial Magnetic Stimulation 10 Hz (rTMS) compared to sham rTMS in women with moderate to severe Post-Partum Depression using standard treatment (sertraline).To conduct an ancillary, exploratory, randomized, active controlled, double blind study with a hypothesis to assess the safety and efficacy of 10 Hz rTMS compared to sertraline. A multicenter, parallel arm, randomized, placebo-controlled, double-blind design to assess safety and efficacy of 10 Hz rTMS compared to sham.An ancillary study will be conducted with parallel arm, randomized, active controlled and double dummy design to assess safety and efficacy of 10 Hz rTMS compared to sertraline.

Since the emergence of COVID-19, most health systems around the world have experienced a series of spikes in the number of infected patients, leading to collapse of the health systems in many countries. The use of clinical laboratory tests can serve as a discriminatory method for disease severity, defining the profile of patients with a higher risk of mortality. In this paper, we study the results of applying predictive models to data regarding COVID-19 outcome, using three datasets after age stratification of patients. The extreme gradient boosting (XGBoost) algorithm was employed as the predictive method, yielding excellent results. The area under the receiving operator characteristic curve (AUROC) value was 0.97 for the subgroup of patients up to 65 years of age. In addition, SHAP (Shapley additive explanations) was used to analyze the feature importance in the resulting models.

A 55-year-old woman presented at the emergency room suffering from dyspnea. Her medical history was notable for deafness, taking metformin for 30 years to treat type 2 diabetes, and depression. An analysis of the patient revealed an increase in lactate concentration (91 mg/dL, reference levels 4–20 mg/dL) and glucose (169 mg/dL). All other measurements were typical or within the reference range, including the presence of autoantibodies and insulin concentration. A chest x-ray showed cardiomegaly, and an echocardiography revealed systolic dysfunction with a severely depressed left ventricular ejection fraction with generalized hypokinesis. From this, the cardiologist diagnosed nonischemic dilated cardiomyopathy. The patient's family history was revealing (Fig. 1, Table 1): her grandmother (I) and mother (II), both dead, suffered from deafness; the latter also had type 2 diabetes. Her brother (IIIb) had been diagnosed with type 2 diabetes at age 30 years after taking an oral glucose tolerance test. The patient has 2 children. The son (IVb) is deaf and has worn a hearing aid since age 20; he has been diagnosed with Wolff-Parkinson-White syndrome. Her daughter (IVa) has also been diagnosed with diabetes, which emerged during pregnancy after taking an oral glucose tolerance test. The family's history, therefore, reveals a pattern of diabetes, deafness, and cardiac abnormalities. All these pathologies had …

BACKGROUND The COVID-19 pandemic is probably the greatest health catastrophe of the modern era. Spain’s health care system has been exposed to uncontrollable numbers of patients over a short period, causing the system to collapse. Given that diagnosis is not immediate, and there is no effective treatment for COVID-19, other tools have had to be developed to identify patients at the risk of severe disease complications and thus optimize material and human resources in health care. There are no tools to identify patients who have a worse prognosis than others. OBJECTIVE This study aimed to process a sample of electronic health records of patients with COVID-19 in order to develop a machine learning model to predict the severity of infection and mortality from among clinical laboratory parameters. Early patient classification can help optimize material and human resources, and analysis of the most important features of the model could provide more detailed insights into the disease. METHODS After an initial performance evaluation based on a comparison with several other well-known methods, the extreme gradient boosting algorithm was selected as the predictive method for this study. In addition, Shapley Additive Explanations was used to analyze the importance of the features of the resulting model. RESULTS After data preprocessing, 1823 confirmed patients with COVID-19 and 32 predictor features were selected. On bootstrap validation, the extreme gradient boosting classifier yielded a value of 0.97 (95% CI 0.96-0.98) for the area under the receiver operator characteristic curve, 0.86 (95% CI 0.80-0.91) for the area under the precision-recall curve, 0.94 (95% CI 0.92-0.95) for accuracy, 0.77 (95% CI 0.72-0.83) for the F-score, 0.93 (95% CI 0.89-0.98) for sensitivity, and 0.91 (95% CI 0.86-0.96) for specificity. The 4 most relevant features for model prediction were lactate dehydrogenase activity, C-reactive protein levels, neutrophil counts, and urea levels. CONCLUSIONS Our predictive model yielded excellent results in the differentiating among patients who died of COVID-19, primarily from among laboratory parameter values. Analysis of the resulting model identified a set of features with the most significant impact on the prediction, thus relating them to a higher risk of mortality.