The diagnosis and treatment of cancer impose a significant emotional and psychological burden on patients, families, and caregivers. Patients undergo several interventions in a hospital setting, and the increasing number of patients requiring extended care and follow-up is driving the demand for additional clinical resources to address their needs. Hospital at Home (HaH) teams have introduced home-administered oncologic therapies that represent a new model of patient-centered cancer care. This approach can be integrated with traditional models and offers benefits to both patients and healthcare professionals (HCPs). Home-administered treatment programs have been successfully piloted globally, demonstrated as a preferred option for most patients and a safe alternative that could reduce costs and hospital burden. The document aims to establish the minimum recommendations for the home administration of oncologic therapies (ODAH) based on a national expert agreement. The expert panel comprised seven leading members from diverse Spanish societies and three working areas: clinical and healthcare issues, logistical and administrative issues, and economic, social, and legal issues. The recommendations outlined in this article were obtained after a comprehensive literature review and thorough discussions. This document may serve as a basis for the future development of home-administered oncologic therapy programs in Spain. .
The COVID-19 pandemic demonstrated the need to develop strategies to control a new viral infection. However, the different characteristics of the health system and population of each country and hospital would require the implementation of self-systems adapted to their characteristics. The objective of this work was to determine predictors that should identify the most severe patients with COVID-19 infection. Given the poor situation of the hospitals in the first wave, the analysis of the data from that period with an accurate and fast technique can be an important contribution. In this regard, machine learning is able to objectively analyze data in hourly sets and is used in many fields. This study included 291 patients admitted to a hospital in Spain during the first three months of the pandemic. After screening seventy-one features with machine learning methods, the variables with the greatest influence on predicting mortality in this population were lymphocyte count, urea, FiO2, potassium, and serum pH. The XGB method achieved the highest accuracy, with a precision of >95%. Our study shows that the machine learning-based system can identify patterns and, thus, create a tool to help hospitals classify patients according to their severity of illness in order to optimize admission.
BACKGROUND: Hepatocellular carcinoma (HCC) accounts for 75% of primary liver tumors. Controlling risk factors associated with its development and implementing screenings in risk populations does not seem sufficient to improve the prognosis of these patients at diagnosis. The development of a predictive prognostic model for mortality at the diagnosis of HCC is proposed. METHODS: In this retrospective multicenter study, the analysis of data from 191 HCC patients was conducted using machine learning (ML) techniques to analyze the prognostic factors of mortality that are significant at the time of diagnosis. Clinical and analytical data of interest in patients with HCC were gathered. RESULTS: Meeting Milan criteria, Barcelona Clinic Liver Cancer (BCLC) classification and albumin levels were the variables with the greatest impact on the prognosis of HCC patients. The ML algorithm that achieved the best results was random forest (RF). CONCLUSIONS: The development of a predictive prognostic model at the diagnosis is a valuable tool for patients with HCC and for application in clinical practice. RF is useful and reliable in the analysis of prognostic factors in the diagnosis of HCC. The search for new prognostic factors is still necessary in patients with HCC.
Systemic Lupus Erythematosus (SLE) is a multifaceted autoimmune ailment that impacts multiple bodily systems and manifests with varied clinical manifestations. Early detection is considered the most effective way to save patients' lives, but detecting severe SLE activity in its early stages is proving to be a formidable challenge. Consequently, this work advocates the use of Machine Learning (ML) algorithms for the diagnosis of SLE flares in the context of infections. In the pursuit of this research, the Random Forest (RF) method has been employed due to its performance attributes. With RF, our objective is to uncover patterns within the patient data. Multiple ML techniques have been scrutinized within this investigation. The proposed system exhibited around a 7.49% enhancement in accuracy when compared to k-Nearest Neighbors (KNN) algorithm. In contrast, the Support Vector Machine (SVM), Binary Linear Discriminant Analysis (BLDA), Decision Trees (DT) and Linear Regression (LR) methods demonstrated inferior performance, with respective values around 81%, 78%, 84% and 69%. It is noteworthy that the proposed method displayed a superior area under the curve (AUC) and balanced accuracy (both around 94%) in comparison to other ML approaches. These outcomes underscore the feasibility of crafting an automated diagnostic support method for SLE patients grounded in ML systems.
The chiral-induced spin selectivity effect (CISS) is a breakthrough phenomenon that has revolutionized the field of electrocatalysis. We report the first study on the electron spin-dependent electrocatalysis for the oxygen reduction reaction, ORR, using iron phthalocyanine, FePc, a well-known molecular catalyst for this reaction. The FePc complex belongs to the non-precious catalysts group, whose active site, FeN4, emulates catalytic centers of biocatalysts such as Cytochrome c. This study presents an experimental platform involving FePc self-assembled to a gold electrode surface using chiral peptides (L and D enantiomers), i.e., chiro-self-assembled FePc systems (CSAFePc). The chiral peptides behave as spin filters axial ligands of the FePc. One of the main findings is that the peptides' handedness and length in CSAFePc can optimize the kinetics and thermodynamic factors governing ORR. Moreover, the D-enantiomer promotes the highest electrocatalytic activity of FePc for ORR, shifting the onset potential up to 1.01â V vs. RHE in an alkaline medium, a potential close to the reversible potential of the O2 /H2 O couple. Therefore, this work has exciting implications for developing highly efficient and bioinspired catalysts, considering that, in biological organisms, biocatalysts that promote O2 reduction to water comprise L-enantiomers.
The impact of SARS-CoV-2 infection remains substantial on a global scale, despite widespread vaccination efforts, early therapeutic interventions, and an enhanced understanding of the disease's underlying mechanisms. At the same time, a significant number of patients continue to develop severe COVID-19, necessitating admission to intensive care units (ICUs). This study aimed to provide evidence concerning the most influential predictors of mortality among critically ill patients with severe COVID-19, employing machine learning (ML) techniques. To accomplish this, we conducted a retrospective multicenter investigation involving 684 patients with severe COVID-19, spanning from 1 June 2020 to 31 March 2023, wherein we scrutinized sociodemographic, clinical, and analytical data. These data were extracted from electronic health records. Out of the six supervised ML methods scrutinized, the extreme gradient boosting (XGB) method exhibited the highest balanced accuracy at 96.61%. The variables that exerted the greatest influence on mortality prediction encompassed ferritin, fibrinogen, D-dimer, platelet count, C-reactive protein (CRP), prothrombin time (PT), invasive mechanical ventilation (IMV), PaFi (PaO2/FiO2), lactate dehydrogenase (LDH), lymphocyte levels, activated partial thromboplastin time (aPTT), body mass index (BMI), creatinine, and age. These findings underscore XGB as a robust candidate for accurately classifying patients with COVID-19.
COVID-19 , Humans , COVID-19/epidemiology , SARS-CoV-2 , Pandemics , Respiration, Artificial , Intensive Care Units , Retrospective Studies
Metabolic Associated Fatty Liver Disease (MASLD) is a condition that is often present in patients with a history of cholecystectomy. This is because both situations share interconnected metabolic pathways. This study aimed to establish a predictive model that allows for the identification of patients at risk of developing hepatic fibrosis following this surgery, with potential implications for surgical decision-making. A retrospective cross-sectional analysis was conducted in four hospitals using a database of 211 patients with MASLD who underwent cholecystectomy. MASLD diagnosis was established through liver biopsy or FibroScan, and non-invasive test scores were included for analysis. Various Machine Learning (ML) methods were employed, with the Adaptive Boosting (Adaboost) system selected to build the predictive model. Platelet level emerged as the most crucial variable in the predictive model, followed by dyslipidemia and type-2 diabetes mellitus. FIB-4 score proved to be the most reliable non-invasive test. The Adaboost algorithm improved the results compared to the other methods, excelling in both accuracy and area under the curve (AUC). Moreover, this system holds promise for implementation in hospitals as a valuable diagnostic support tool. In conclusion, platelet level (<150,000/dL), dyslipidemia, and type-2 diabetes mellitus were identified as primary risk factors for liver fibrosis in MASLD patients following cholecystectomy. FIB-4 score is recommended for decision-making, particularly when the indication for surgery is uncertain. This predictive model offers valuable insights into risk stratification and personalized patient management in post-cholecystectomy MASLD cases.
Cholecystectomy and Metabolic-associated steatotic liver disease (MASLD) are prevalent conditions in gastroenterology, frequently co-occurring in clinical practice. Cholecystectomy has been shown to have metabolic consequences, sharing similar pathological mechanisms with MASLD. A database of MASLD patients who underwent cholecystectomy was analysed. This study aimed to develop a tool to identify the risk of liver fibrosis after cholecystectomy. For this purpose, the extreme gradient boosting (XGB) algorithm was used to construct an effective predictive model. The factors associated with a better predictive method were platelet level, followed by dyslipidaemia and type-2 diabetes (T2DM). Compared to other ML methods, our proposed method, XGB, achieved higher accuracy values. The XGB method had the highest balanced accuracy (93.16%). XGB outperformed KNN in accuracy (93.16% vs. 84.45%) and AUC (0.92 vs. 0.84). These results demonstrate that the proposed XGB method can be used as an automatic diagnostic aid for MASLD patients based on machine-learning techniques.
Surveillance of antimicrobial resistance among gram-negative bacteria (GNB) is of critical importance, but data for Peru are not available. To fill this gap, a non-interventional hospital-based surveillance study was conducted in 15 hospitals across Peru from July 2017 to October 2019. Consecutive unique blood culture isolates of key GNB (Escherichia coli, Klebsiella pneumoniae, Pseudomonas aeruginosa, Acinetobacter spp.) recovered from hospitalized patients were collected for centralized antimicrobial susceptibility testing, along with linked epidemiological and clinical data. A total of 449 isolates were included in the analysis. Resistance to third-generation cephalosporins (3GCs) was present in 266 (59.2%) GNB isolates. Among E. coli (n = 199), 68.3% showed 3GC resistance (i.e., above the median ratio for low- and middle-income countries in 2020 for this sustainable development goal indicator). Carbapenem resistance was present in 74 (16.5%) GNB isolates, with wide variation among species (0% in E. coli, 11.0% in K. pneumoniae, 37.0% in P. aeruginosa, and 60.8% in Acinetobacter spp. isolates). Co-resistance to carbapenems and colistin was found in seven (1.6%) GNB isolates. Empiric treatment covered the causative GNB in 63.3% of 215 cases. The in-hospital case fatality ratio was 33.3% (92/276). Pseudomonas aeruginosa species and carbapenem resistance were associated with higher risk of in-hospital death. In conclusion, an important proportion of bloodstream infections in Peru are caused by highly resistant GNB and are associated with high in-hospital mortality.
Gram-Negative Bacterial Infections , Sepsis , Humans , Anti-Bacterial Agents/pharmacology , Anti-Bacterial Agents/therapeutic use , Escherichia coli , Prevalence , Peru/epidemiology , Hospital Mortality , Drug Resistance, Bacterial , Gram-Negative Bacterial Infections/drug therapy , Gram-Negative Bacterial Infections/epidemiology , Gram-Negative Bacterial Infections/microbiology , Carbapenems , Gram-Negative Bacteria , Klebsiella pneumoniae , Pseudomonas aeruginosa , Sepsis/drug therapy , Microbial Sensitivity Tests
Schizophrenia is a chronic and severe mental disorder that affects individuals in various ways, particularly in their ability to perceive, process, and respond to stimuli. This condition has a significant impact on a considerable number of individuals. Consequently, the study, analysis, and characterization of this pathology are of paramount importance. Electroencephalography (EEG) is frequently utilized in the diagnostic assessment of various brain disorders due to its non-intrusiveness, excellent resolution and ease of placement. However, the manual analysis of electroencephalogram (EEG) recordings can be a complex and time-consuming task for healthcare professionals. Therefore, the automated analysis of EEG recordings can help alleviate the burden on doctors and provide valuable insights to support clinical diagnosis. Many studies are working along these lines. In this research paper, the authors propose a machine learning (ML) method based on the eXtreme Gradient Boosting (XGB) algorithm for analyzing EEG signals. The study compares the performance of the proposed XGB-based approach with four other supervised ML systems. According to the results, the proposed XGB-based method demonstrates superior performance, with an AUC value of 0.94 and an accuracy value of 0.94, surpassing the other compared methods. The implemented system exhibits high accuracy and robustness in accurately classifying schizophrenia patients based on EEG recordings. This method holds the potential to be implemented as a valuable complementary tool for clinical use in hospitals, supporting clinicians in their clinical diagnosis of schizophrenia.
AIM: Nonalcoholic fatty liver disease (NAFLD) is a silent epidemy that has become the most common chronic liver disease worldwide. Nonalcoholic steatohepatitis (NASH) is an advanced stage of NAFLD, which is linked to a high risk of cirrhosis and hepatocellular carcinoma. The aim of this study is to develop a predictive model to identify the main risk factors associated with the progression of hepatic fibrosis in patients with NASH. METHODS: A database from a multicenter retrospective cross-sectional study was analyzed. A total of 215 patients with NASH biopsy-proven diagnosed were collected. NAFLD Activity Score and Kleiner scoring system were used to diagnose and staging these patients. Noninvasive tests (NITs) scores were added to identify which one were more reliable for follow-up and to avoid biopsy. For analysis, different Machine Learning methods were implemented, being the eXtreme Gradient Booster (XGB) system the proposed algorithm to develop the predictive model. RESULTS: The most important variable in this predictive model was High-density lipoprotein (HDL) cholesterol, followed by systemic arterial hypertension and triglycerides (TG). NAFLD Fibrosis Score (NFS) was the most reliable NIT. As for the proposed method, XGB obtained higher results than the second method, K-Nearest Neighbors, in terms of accuracy (95.05 vs. 90.42) and Area Under the Curve (0.95 vs. 0.91). CONCLUSIONS: HDL cholesterol, systemic arterial hypertension, and TG were the most important risk factors for liver fibrosis progression in NASH patients. NFS is recommended for monitoring and decision making.
Liver Neoplasms , Non-alcoholic Fatty Liver Disease , Humans , Non-alcoholic Fatty Liver Disease/diagnosis , Non-alcoholic Fatty Liver Disease/epidemiology , Non-alcoholic Fatty Liver Disease/complications , Retrospective Studies , Cross-Sectional Studies , Liver Cirrhosis/etiology , Risk Factors , Cholesterol, HDL , Triglycerides , Liver Neoplasms/pathology , Biopsy/adverse effects , Liver/pathology , Fibrosis
Background: Hopelessness is a risk factor for depression and suicide. There is little information on this phenomenon among patients with relapsing-remitting multiple sclerosis (RRMS), one of the most common causes of disability and loss of autonomy in young adults. The aim of this study was to assess state hopelessness and its associated factors in early-stage RRMS. Methods: A multicenter, non-interventional study was conducted. Adult patients with a diagnosis of RRMS, a disease duration ≤ 3 years, and an Expanded Disability Status Scale (EDSS) score of 0-5.5 were included. The State-Trait Hopelessness Scale (STHS) was used to measure patients´ hopelessness. A battery of patient-reported and clinician-rated measurements was used to assess clinical status. A multivariate logistic regression analysis was conducted to determine the association between patients' characteristics and state hopelessness. Results: A total of 189 patients were included. Mean age (standard deviation-SD) was 36.1 (9.4) years and 71.4% were female. Median disease duration (interquartile range-IQR) was 1.4 (0.7, 2.1) years. Symptom severity and disability were low with a median EDSS (IQR) score of 1.0 (0, 2.0). A proportion of 65.6% (n=124) of patients reported moderate-to-severe hopelessness. Hopelessness was associated with older age (p=0.035), depressive symptoms (p=<0.001), a threatening illness perception (p=0.001), and psychological and cognitive barriers to workplace performance (p=0.029) in the multivariate analysis after adjustment for confounders. Conclusion: Hopelessness was a common phenomenon in early-stage RRMS, even in a population with low physical disability. Identifying factors associated with hopelessness may be critical for implementing preventive strategies helping patients to adapt to the new situation and cope with the disease in the long term.
Systemic lupus erythematosus (SLE) is a complex autoimmune disease that affects several organs and causes variable clinical symptoms. Early diagnosis is currently the most effective way to save the lives of patients with SLE. But it is very difficult to detect in the early stages of the disease. Because of this, this study proposes a machine learning system to help diagnose patients with SLE. To carry out the research, the extreme gradient boosting method has been implemented due to its performance characteristics, as it allows high performance, scalability, accuracy, and low computational load. From this method we try to recognize patterns in the data obtained from patients, which allow the classification of SLE patients with high accuracy and differentiate these patients from controls. Several machine learning methods have been analyzed in this study. The proposed method achieves a higher prediction value of patients who may suffer from SLE than the rest of the compared systems. The proposed algorithm achieved an improvement in accuracy of 4.49% over k-Nearest Neighbors. As for the Support Vector Machine and Gaussian Naive Bayes (GNB) methods, they achieved a lower performance than the proposed one, reaching values of 83% and 81%, respectively. It should be noted that the proposed system showed a higher area under the curve (90%) and a balanced accuracy (90%) than the other machine learning methods. This study shows the usefulness of ML techniques for identifying and predicting SLE patients. These results demonstrate the possibility of developing automatic diagnostic support systems for SLE patients based on machine learning techniques.
Lupus Erythematosus, Systemic , Humans , Bayes Theorem , Lupus Erythematosus, Systemic/diagnosis , Machine Learning , Algorithms
KEY MESSAGE: We identified marker-trait associations for key faba bean agronomic traits and genomic signatures of selection within a global germplasm collection. Faba bean (Vicia faba L.) is a high-protein grain legume crop with great potential for sustainable protein production. However, little is known about the genetics underlying trait diversity. In this study, we used 21,345 high-quality SNP markers to genetically characterize 2678 faba bean genotypes. We performed genome-wide association studies of key agronomic traits using a seven-parent-MAGIC population and detected 238 significant marker-trait associations linked to 12 traits of agronomic importance. Sixty-five of these were stable across multiple environments. Using a non-redundant diversity panel of 685 accessions from 52 countries, we identified three subpopulations differentiated by geographical origin and 33 genomic regions subjected to strong diversifying selection between subpopulations. We found that SNP markers associated with the differentiation of northern and southern accessions explained a significant proportion of agronomic trait variance in the seven-parent-MAGIC population, suggesting that some of these traits were targets of selection during breeding. Our findings point to genomic regions associated with important agronomic traits and selection, facilitating faba bean genomics-based breeding.
Fabaceae , Vicia faba , Vicia faba/genetics , Genome-Wide Association Study , Plant Breeding , Phenotype , Fabaceae/genetics
Accidents involving snakes from Bothrops spp. and Crotalus spp. constitute the most important cause of envenomation in Brazil and Argentina. Musa spp. (banana) have been reported to be used in popular medicine against snakebite by the members of the Canudos Settlement, located in Goiás. In this way, the aim of this work was to evaluate the antivenom effect of the Ouro (AA), Prata (AAB), Prata-anã (AAB) and Figo (ABB) cultivars against in vitro (phospholipase, coagulation and proteolytic) and in vivo (lethality and toxicity) activities caused by the venoms and toxicity (Artemia salina nauplii and Danio rerio embryos) of Musa spp. as well as the annotation of chemical compounds possibly related to these activities. From the in vitro antiophidic tests with the sap, we observed 100% inhibition of the phospholipase and coagulant activities with the cultivars Prata-anã and Figo against the venoms of B. alternatus and C. d. collineatus, B. diporus and B. pauloensis, respectively, and neutralisation of the lethality against the B. diporus venom. It was observed that the cultivars of Musa spp. did not show toxicity against Artemia salina nauplii and Danio rerio embryos. The sap analysis via HPLC-MS/MS allowed the annotation of the 13 compounds: abscisic acid, shikimic acid, citric acid, quinic acid, afzelechin, Glp-hexose, glucose, sucrose, isorhamnetin-3-O-galactoside-6-raminoside, kaempferol-3-glucoside-3-raminoside, myricetin-3-O-rutinoside, procyanidin B1 and rutin. Therefore, it can be seen that Musa spp. is a potential therapeutic agent that can act to neutralise the effects caused by snakebites.
Bothrops , Crotalid Venoms , Musa , Snake Bites , Animals , Crotalus , Tandem Mass Spectrometry , Zebrafish , Snake Venoms , Crotalid Venoms/toxicity , Crotalid Venoms/chemistry , Antivenins/pharmacology , Antivenins/therapeutic use , Snake Bites/drug therapy , Phospholipases
ETHNOPHARMACOLOGICAL RELEVANCE: Lauraceae family includes Nectandra angustifolia a species widely used in the folk medicine of South America against various maladies. It is commonly used to treat different types of processes like inflammation, pain, and snakebites. Snakes of the Bothrops genus are responsible for about 97% of the ophidic accidents in northeastern Argentina. AIM OF THE STUDY: To evaluate the anti-snake activity of the phytochemicals present in N. angustifolia extracts, identify the compounds, and evaluate their inhibitory effect on phospholipase A2 (PLA2) with in vitro and in silico assays. METHODS: Seasonal variations in the alexiteric potential of aqueous, ethanolic and hexanic extracts were evaluated by inhibition of coagulant, haemolytic, and cytotoxic effects of B. diporus venom. The chemical identity of an enriched fraction obtained by bio-guided fractioning was established by UPLC-MS/MS analysis. Molecular docking studies were carried out to investigate the binding mechanisms of the identified compounds to PLA2 enzyme from snake venom. RESULTS: All the extracts inhibited venom coagulant activity. However, spring ethanolic extract achieved 100% inhibition of haemolytic activity. Bio-guide fractioning led to an enriched fraction (F4) with the highest haemolytic inhibition. Five flavonoids were identified in this fraction; molecular docking and Molecular Dynamics (MD) simulations indicated the binding mechanisms of the identified compounds. The carbohydrates present in some of the compounds had a critical effect on the interaction with PLA2. CONCLUSION: This study shows, for the first time, which compounds are responsible for the anti-snake activity in Nectandra angustifolia based on in vitro and in silico assays. The results obtained in this work support the traditional use of this species as anti-snake in folk medicine.
Bothrops , Crotalid Venoms , Lauraceae , Animals , Flavonoids/pharmacology , Molecular Docking Simulation , Chromatography, Liquid , Plant Extracts/therapeutic use , Tandem Mass Spectrometry , Bothrops/physiology , Phospholipases A2/metabolism
BACKGROUND AND AIMS: Spondyloarthritis (SpA) is a group of autoinflammatory disorders, of which the primary extra-articular manifestation is inflammatory bowel disease (IBD). The oral cavity being a part of gastrointestinal tract, is significantly compromised in IBD, and in many cases, it is the first site of clinical manifestations of IBD. This study aimed to identify changes in the oral mucosa associated with the onset of IBD and their association with endoscopic/histological findings. MATERIALS AND METHODS: The study assessed 80 patients with SpA and 52 healthy controls. Oral, rheumatological, and gastroenterological assessments were performed. The ileocolonoscopy was performed via digital magnification chromoendoscopy. The statistical analysis consisted of Chi-square, Fisher's exact, and multiple correspondence discriminant analysis tests. RESULTS: From the disease cohort, 63.0% patients showed oral lesions (p = 0.050). These manifestations ranged from gingivitis (55.0%, p = 0.001), aphthous stomatitis (3.8%, p = 0.091), angular cheilitis (2.6%, p = 0.200), and perioral erythema with scaling (1.3%, p = 0.300). All patients who presented with alterations in colonic mucosa also had oral lesions associated with IBD (p = 0.039), specifically gingivitis/aphthous stomatitis (p = 0.029). CONCLUSION: The patients with SpA without IBD present significant oral signs and symptoms. Gingivitis seems to be the most relevant because of its associations with early endoscopic and histological findings. CLINICAL RELEVANCE: An integral approach to the diagnostic tests that includes evaluations of oral, rheumatological and gastroenterological tissues may favor timely attention and improve patients' quality of life.
Gingivitis , Inflammatory Bowel Diseases , Oral Ulcer , Rheumatic Diseases , Spondylarthritis , Stomatitis, Aphthous , Humans , Stomatitis, Aphthous/complications , Quality of Life , Spondylarthritis/complications , Inflammatory Bowel Diseases/complications , Chronic Disease , Rheumatic Diseases/complications
Among the IL-6 inhibitors, tocilizumab is the most widely used therapeutic option in patients with SARS-CoV-2-associated severe respiratory failure (SRF). The aim of our study was to provide evidence on predictors of poor outcome in patients with COVID-19 treated with tocilizumab, using machine learning (ML) techniques. We conducted a retrospective study, analyzing the clinical, laboratory and sociodemographic data of patients admitted for severe COVID-19 with SRF, treated with tocilizumab. The extreme gradient boost (XGB) method had the highest balanced accuracy (93.16%). The factors associated with a worse outcome of tocilizumab use in terms of mortality were: baseline situation at the start of tocilizumab treatment requiring invasive mechanical ventilation (IMV), elevated ferritin, lactate dehydrogenase (LDH) and glutamate-pyruvate transaminase (GPT), lymphopenia, and low PaFi [ratio between arterial oxygen pressure and inspired oxygen fraction (PaO2/FiO2)] values. The factors associated with a worse outcome of tocilizumab use in terms of hospital stay were: baseline situation at the start of tocilizumab treatment requiring IMV or supplemental oxygen, elevated levels of ferritin, glutamate-oxaloacetate transaminase (GOT), GPT, C-reactive protein (CRP), LDH, lymphopenia, and low PaFi values. In our study focused on patients with severe COVID-19 treated with tocilizumab, the factors that were weighted most strongly in predicting worse clinical outcome were baseline status at the start of tocilizumab treatment requiring IMV and hyperferritinemia.
BACKGROUND: In general, transthoracic echocardiography (TTE) is the first diagnostic test used for patients with bacteremia or candidemia and clinical signs of Infective Endocarditis (IE). Point-of-care ultrasound (POCUS) may be used in addition to physical examination for the detection of structural heart disease and valve abnormalities. OBJECTIVE: To determine the diagnostic accuracy of POCUS for the detection of signs suggestive of IE, including vegetation, valvular regurgitation, structural heart disease, hepatomegaly, splenomegaly and septic embolisms, in patients with bacteremia or candidemia. DESIGN: Observational, cross-sectional, multicenter study using convenience sampling. SETTING: Six Spanish academic hospitals. PATIENTS: Adult patients with bacteremia or candidemia between 1 February 2018 and 31 December 2020. MEASUREMENTS: The reference test, to evaluate vegetation, valvular regurgitation and structural heart disease, was transesophageal echocardiography (TEE). For patients who did not undergo TEE, transthoracic echocardiography (TTE) was considered the reference test. POCUS was performed by internists, while conventional echocardiography procedures were performed by cardiologists. RESULTS: In 258 patients, for the detection of valvular vegetation, POCUS had sensitivity, specificity, and positive and negative predictive values of 77%, 94%, 82% and 92%, respectively. For valvular regurgitation (more than mild), sensitivity was ≥76% and specificity ≥85%. Sensitivity values for the detection of hepatomegaly and splenomegaly were 92% and 92%, respectively, while those for specificity were 96% and 98%. CONCLUSION: POCUS could be a valuable tool, as a complement to physical examination, at the hospital bedside for patients with bacteremia or candidemia, helping to identify signs suggestive of IE.
Different demographic, clinical and laboratory variables have been related to the severity and mortality following SARS-CoV-2 infection. Most studies applied traditional statistical methods and in some cases combined with a machine learning (ML) method. This is the first study to date to comparatively analyze five ML methods to select the one that most closely predicts mortality in patients admitted with COVID-19. The aim of this single-center observational study is to classify, based on different types of variables, adult patients with COVID-19 at increased risk of mortality. SARS-CoV-2 infection was defined by a positive reverse transcriptase PCR. A total of 203 patients were admitted between March 15 and June 15, 2020 to a tertiary hospital. Data were extracted from the electronic medical record. Four supervised ML algorithms (k-nearest neighbors (KNN), decision tree (DT), Gaussian naïve Bayes (GNB) and support vector machine (SVM)) were compared with the eXtreme Gradient Boosting (XGB) method proposed to have excellent scalability and high running speed, among other qualities. The results indicate that the XGB method has the best prediction accuracy (92%), high precision (>0.92) and high recall (>0.92). The KNN, SVM and DT approaches present moderate prediction accuracy (>80%), moderate recall (>0.80) and moderate precision (>0.80). The GNB algorithm shows relatively low classification performance. The variables with the greatest weight in predicting mortality were C reactive protein, procalcitonin, glutamyl oxaloacetic transaminase, glutamyl pyruvic transaminase, neutrophils, D-dimer, creatinine, lactic acid, ferritin, days of non-invasive ventilation, septic shock and age. Based on these results, XGB is a solid candidate for correct classification of patients with COVID-19.
