RESUMO
Hepatocellular carcinoma (HCC) is the most common primary liver tumor and is associated with high mortality rates. Approximately 80% of cases occur in cirrhotic livers, posing a significant challenge for appropriate therapeutic management. Adequate screening programs in high-risk groups are essential for early-stage detection. The extent of extrahepatic tumor spread and hepatic functional reserve are recognized as two of the most influential prognostic factors. In this retrospective multicenter study, we utilized machine learning (ML) methods to analyze predictors of mortality at the time of diagnosis in a total of 208 patients. The eXtreme gradient boosting (XGB) method achieved the highest values in identifying key prognostic factors for HCC at diagnosis. The etiology of HCC was found to be the variable most strongly associated with a poorer prognosis. The widely used Barcelona Clinic Liver Cancer (BCLC) classification in our setting demonstrated superiority over the TNM classification. Although alpha-fetoprotein (AFP) remains the most commonly used biological marker, elevated levels did not correlate with reduced survival. Our findings suggest the need to explore new prognostic biomarkers for individualized management of these patients.
Assuntos
Carcinoma Hepatocelular , Neoplasias Hepáticas , Aprendizado de Máquina , alfa-Fetoproteínas , Humanos , alfa-Fetoproteínas/química , Biomarcadores Tumorais , Carcinoma Hepatocelular/metabolismo , Carcinoma Hepatocelular/patologia , Neoplasias Hepáticas/metabolismo , Neoplasias Hepáticas/patologia , Estadiamento de Neoplasias , Estudos RetrospectivosRESUMO
Predictive tools for major bleeding (MB) using machine learning (ML) might be advantageous over traditional methods. We used data from the Registro Informatizado de Enfermedad TromboEmbólica (RIETE) to develop ML algorithms to identify patients with venous thromboembolism (VTE) at increased risk of MB during the first 3 months of anticoagulation. A total of 55 baseline variables were used as predictors. New data prospectively collected from the RIETE were used for further validation. The RIETE and VTE-BLEED scores were used for comparisons. External validation was performed with the COMMAND-VTE database. Learning was carried out with data from 49 587 patients, of whom 873 (1.8%) had MB. The best performing ML method was XGBoost. In the prospective validation cohort the sensitivity, specificity, positive predictive value and F1 score were: 33.2%, 93%, 10%, and 15.4% respectively. F1 value for the RIETE and VTE-BLEED scores were 8.6% and 6.4% respectively. In the external validation cohort the metrics were 10.3%, 87.6%, 3.5% and 5.2% respectively. In that cohort, the F1 value for the RIETE score was 17.3% and for the VTE-BLEED score 9.75%. The performance of the XGBoost algorithm was better than that from the RIETE and VTE-BLEED scores only in the prospective validation cohort, but not in the external validation cohort.
Assuntos
Embolia Pulmonar , Tromboembolia Venosa , Humanos , Tromboembolia Venosa/etiologia , Sistema de Registros , Hemorragia/induzido quimicamente , Hemorragia/complicações , Valor Preditivo dos Testes , Anticoagulantes/efeitos adversos , Embolia Pulmonar/complicaçõesRESUMO
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.
Assuntos
Neoplasias Hepáticas , Hepatopatia Gordurosa não Alcoólica , Humanos , Hepatopatia Gordurosa não Alcoólica/diagnóstico , Hepatopatia Gordurosa não Alcoólica/epidemiologia , Hepatopatia Gordurosa não Alcoólica/complicações , Estudos Retrospectivos , Estudos Transversais , Cirrose Hepática/etiologia , Fatores de Risco , HDL-Colesterol , Triglicerídeos , Neoplasias Hepáticas/patologia , Biópsia/efeitos adversos , Fígado/patologia , FibroseRESUMO
OBJECTIVES: Cognitive dysfunction in bipolar disorder has been well-established in cross-sectional studies; however, there are few data regarding the longitudinal course of cognitive performance in bipolar disorder. The aim of this study was to examine the course of cognitive function in a sample of euthymic patients with bipolar disorder during a five-year follow-up period. METHODS: Eighty euthymic outpatients with a DSM-IV diagnosis of bipolar disorder and 40 healthy control comparison subjects were neuropsychologically assessed at baseline (T1) and then at follow-up of five years (T2). A neurocognitive battery including the main cognitive domains of speed of processing, working memory, attention, verbal memory, visual memory, and executive function was used to evaluate cognitive performance. RESULTS: Repeated-measures multivariate analyses showed that progression of cognitive dysfunction in patients was not different to that of control subjects in any of the six cognitive domains examined. Only a measure from the verbal memory domain, delayed free recall, worsened more in patients with bipolar disorder. Additionally, it was found that clinical course during the follow-up period did not influence the course of cognitive dysfunction. CONCLUSIONS: Cognitive dysfunction that is characteristic of bipolar disorder is persistent and stable over time. Only dysfunction in verbal recall was found to show a progressive course that cannot be explained by clinical or treatment variables.
Assuntos
Transtorno Bipolar/complicações , Transtorno Bipolar/patologia , Transtornos Cognitivos/etiologia , Adulto , Análise de Variância , Anticonvulsivantes/uso terapêutico , Antimaníacos/uso terapêutico , Transtorno Bipolar/tratamento farmacológico , Estudos Transversais , Feminino , Humanos , Cloreto de Lítio/uso terapêutico , Estudos Longitudinais , Masculino , Pessoa de Meia-Idade , Testes Neuropsicológicos , Escalas de Graduação Psiquiátrica , Estatística como AssuntoRESUMO
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.
RESUMO
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.
RESUMO
Background: Despite advancements in vaccination, early treatments, and understanding of SARS-CoV-2, its impact remains significant worldwide. Many patients require intensive care due to severe COVID-19. Remdesivir, a key treatment option among viral RNA polymerase inhibitors, lacks comprehensive studies on factors associated with its effectiveness. Methods: We conducted a retrospective study in 2022, analyzing data from 252 hospitalized COVID-19 patients treated with remdesivir. Six machine learning algorithms were compared to predict factors influencing remdesivir's clinical benefits regarding mortality and hospital stay. Results: The extreme gradient boost (XGB) method showed the highest accuracy for both mortality (95.45%) and hospital stay (94.24%). Factors associated with worse outcomes in terms of mortality included limitations in life support, ventilatory support needs, lymphopenia, low albumin and hemoglobin levels, flu and/or coinfection, and cough. For hospital stay, factors included vaccine doses, lung density, pulmonary radiological status, comorbidities, oxygen therapy, troponin, lactate dehydrogenase levels, and asthenia. Conclusions: These findings underscore XGB's effectiveness in accurately categorizing COVID-19 patients undergoing remdesivir treatment.
RESUMO
Artificial intelligence (AI) systems are already being used in various healthcare areas. Similarly, they can offer many advantages in hospital emergency services. The objective of this work is to demonstrate that through the novel use of AI, a trained system can be developed to detect patients at potential risk of infection in a new pandemic more quickly than standardized triage systems. This identification would occur in the emergency department, thus allowing for the early implementation of organizational preventive measures to block the chain of transmission. MATERIALS AND METHODS: In this study, we propose the use of a machine learning system in emergency department triage during pandemics to detect patients at the highest risk of death and infection using the COVID-19 era as an example, where rapid decision making and comprehensive support have becoming increasingly crucial. All patients who consecutively presented to the emergency department were included, and more than 89 variables were automatically analyzed using the extreme gradient boosting (XGB) algorithm. RESULTS: The XGB system demonstrated the highest balanced accuracy at 91.61%. Additionally, it obtained results more quickly than traditional triage systems. The variables that most influenced mortality prediction were procalcitonin level, age, and oxygen saturation, followed by lactate dehydrogenase (LDH) level, C-reactive protein, the presence of interstitial infiltrates on chest X-ray, and D-dimer. Our system also identified the importance of oxygen therapy in these patients. CONCLUSIONS: These results highlight that XGB is a useful and novel tool in triage systems for guiding the care pathway in future pandemics, thus following the example set by the well-known COVID-19 pandemic.
RESUMO
Metabolic dysfunction-associated steatotic liver disease (MASLD) currently represents the predominant cause of chronic liver disease and is closely linked to a significant increase in the risk of hepatocellular carcinoma (HCC), even in the absence of liver cirrhosis. In this retrospective multicenter study, machine learning (ML) methods were employed to investigate the relationship between metabolic profile and prognosis at diagnosis in a total of 219 HCC patients. The eXtreme Gradient Boosting (XGB) method demonstrated superiority in identifying mortality predictors in our patients. Etiology was the most determining prognostic factor followed by Barcelona Clinic Liver Cancer (BCLC) and Eastern Cooperative Oncology Group (ECOG) classifications. Variables related to the development of hepatic steatosis and metabolic syndrome, such as elevated levels of alkaline phosphatase (ALP), uric acid, obesity, alcohol consumption, and high blood pressure (HBP), had a significant impact on mortality prediction. This study underscores the importance of metabolic syndrome as a determining factor in the progression of HCC secondary to MASLD. The use of ML techniques provides an effective tool to improve risk stratification and individualized therapeutic management in these patients.
RESUMO
Non-alcoholic fatty liver disease (NAFLD) is the most common chronic liver disease worldwide, with an incidence that is exponentially increasing. Hepatocellular carcinoma (HCC) is the most frequent primary tumor. There is an increasing relationship between these entities due to the potential risk of developing NAFLD-related HCC and the prevalence of NAFLD. There is limited evidence regarding prognostic factors at the diagnosis of HCC. This study compares the prognosis of HCC in patients with NAFLD against other etiologies. It also evaluates the prognostic factors at the diagnosis of these patients. For this purpose, a multicenter retrospective study was conducted involving a total of 191 patients. Out of the total, 29 presented NAFLD-related HCC. The extreme gradient boosting (XGB) method was employed to develop the reference predictive model. Patients with NAFLD-related HCC showed a worse prognosis compared to other potential etiologies of HCC. Among the variables with the worst prognosis, alcohol consumption in NAFLD patients had the greatest weight within the developed predictive model. In comparison with other studied methods, XGB obtained the highest values for the analyzed metrics. In conclusion, patients with NAFLD-related HCC and alcohol consumption, obesity, cirrhosis, and clinically significant portal hypertension (CSPH) exhibited a worse prognosis than other patients. XGB developed a highly efficient predictive model for the assessment of these patients.
RESUMO
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.
RESUMO
Ultrasound is widely used for tendon assessment due to its safety, affordability, and portability, but its subjective nature poses challenges. This study aimed to develop a new quantitative analysis tool based on artificial intelligence to identify statistical patterns of healthy and pathological tendons. Furthermore, we aimed to validate this new tool by comparing it to experts' subjective assessments. A pilot database including healthy controls and patients with patellar tendinopathy was constructed, involving 14 participants with asymptomatic (n = 7) and symptomatic (n = 7) patellar tendons. Ultrasonographic images were assessed twice, utilizing both the new quantitative tool and the subjective scoring method applied by an expert across five regions of interest. The database contained 61 variables per image. The robustness of the clinical and quantitative assessments was tested via reliability analyses. Lastly, the prediction accuracy of the quantitative features was tested via cross-validated generalized linear mixed-effects logistic regressions. These analyses showed high reliability for quantitative variables related to "Bone" and "Quality", with ICCs above 0.75. The ICCs for "Edges" and "Thickness" varied but mostly exceeded 0.75. The results of this study show that certain quantitative variables are capable of predicting an expert's subjective assessment with generally high cross-validated AUC scores. A new quantitative tool for the ultrasonographic assessment of the tendon was designed. This system is shown to be a reliable and valid method for evaluating the patellar tendon structure.
RESUMO
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.
Assuntos
COVID-19 , Humanos , COVID-19/epidemiologia , SARS-CoV-2 , Pandemias , Respiração Artificial , Unidades de Terapia Intensiva , Estudos RetrospectivosRESUMO
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.
Assuntos
Lúpus Eritematoso Sistêmico , Humanos , Teorema de Bayes , Lúpus Eritematoso Sistêmico/diagnóstico , Aprendizado de Máquina , AlgoritmosRESUMO
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.
RESUMO
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.
RESUMO
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.
RESUMO
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.
RESUMO
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.
RESUMO
BACKGROUND: Patients with pulmonary embolism (PE) who prematurely discontinue anticoagulant therapy (<90 days) are at an increased risk for death or recurrences. METHODS: We used the data from the RIETE (Registro Informatizado de Pacientes con Enfermedad TromboEmbólica) registry to compare the prognostic ability of five machine-learning (ML) models and logistic regression to identify patients at increased risk for the composite of fatal PE or recurrent venous thromboembolism (VTE) 30 days after discontinuation. ML models included decision tree, k-nearest neighbors algorithm, support vector machine, Ensemble, and neural network [NN]. A "full" model with 70 variables and a "reduced" model with 23 were analyzed. Model performance was assessed by confusion matrix metrics on the testing data for each model and a calibration plot. RESULTS: Among 34,447 patients with PE, 1,348 (3.9%) discontinued therapy prematurely. Fifty-one (3.8%) developed fatal PE or sudden death and 24 (1.8%) had nonfatal VTE recurrences within 30 days after discontinuation. ML-NN was the best method for identification of patients experiencing the composite endpoint, predicting the composite outcome with an area under receiver operating characteristic (ROC) curve of 0.96 (95% confidence interval [CI]: 0.95-0.98), using either 70 or 23 variables captured before discontinuation. Similar numbers were obtained for sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. The discrimination of logistic regression was inferior (area under ROC curve, 0.76 [95% CI: 0.70-0.81]). Calibration plots showed similar deviations from the perfect line for ML-NN and logistic regression. CONCLUSION: The ML-NN method very well predicted the composite outcome after premature discontinuation of anticoagulation and outperformed traditional logistic regression.