RESUMO
Objective: This study aims to develop a predictive model using artificial intelligence to estimate the ICU length of stay (LOS) for Congenital Heart Defects (CHD) patients after surgery, improving care planning and resource management. Design: We analyze clinical data from 2240 CHD surgery patients to create and validate the predictive model. Twenty AI models are developed and evaluated for accuracy and reliability. Setting: The study is conducted in a Brazilian hospital's Cardiovascular Surgery Department, focusing on transplants and cardiopulmonary surgeries. Participants: Retrospective analysis is conducted on data from 2240 consecutive CHD patients undergoing surgery. Interventions: Ninety-three pre and intraoperative variables are used as ICU LOS predictors. Measurements and main results: Utilizing regression and clustering methodologies for ICU LOS (ICU Length of Stay) estimation, the Light Gradient Boosting Machine, using regression, achieved a Mean Squared Error (MSE) of 15.4, 11.8, and 15.2 days for training, testing, and unseen data. Key predictors included metrics such as "Mechanical Ventilation Duration", "Weight on Surgery Date", and "Vasoactive-Inotropic Score". Meanwhile, the clustering model, Cat Boost Classifier, attained an accuracy of 0.6917 and AUC of 0.8559 with similar key predictors. Conclusions: Patients with higher ventilation times, vasoactive-inotropic scores, anoxia time, cardiopulmonary bypass time, and lower weight, height, BMI, age, hematocrit, and presurgical oxygen saturation have longer ICU stays, aligning with existing literature.
RESUMO
BACKGROUND: Congenital heart disease accounts for almost a third of all major congenital anomalies. Congenital heart defects have a significant impact on morbidity, mortality and health costs for children and adults. Research regarding the risk of pre-surgical mortality is scarce. OBJECTIVES: Our goal is to generate a predictive model calculator adapted to the regional reality focused on individual mortality prediction among patients with congenital heart disease undergoing cardiac surgery. METHODS: Two thousand two hundred forty CHD consecutive patients' data from InCor's heart surgery program was used to develop and validate the preoperative risk-of-death prediction model of congenital patients undergoing heart surgery. There were six artificial intelligence models most cited in medical references used in this study: Multilayer Perceptron (MLP), Random Forest (RF), Extra Trees (ET), Stochastic Gradient Boosting (SGB), Ada Boost Classification (ABC) and Bag Decision Trees (BDT). RESULTS: The top performing areas under the curve were achieved using Random Forest (0.902). Most influential predictors included previous admission to ICU, diagnostic group, patient's height, hypoplastic left heart syndrome, body mass, arterial oxygen saturation, and pulmonary atresia. These combined predictor variables represent 67.8% of importance for the risk of mortality in the Random Forest algorithm. CONCLUSIONS: The representativeness of "hospital death" is greater in patients up to 66 cm in height and body mass index below 13.0 for InCor's patients. The proportion of "hospital death" declines with the increased arterial oxygen saturation index. Patients with prior hospitalization before surgery had higher "hospital death" rates than who did not required such intervention. The diagnoses groups having the higher fatal outcomes probability are aligned with the international literature. A web application is presented where researchers and providers can calculate predicted mortality based on the CgntSCORE on any web browser or smartphone.
Assuntos
Inteligência Artificial , Cardiopatias Congênitas/mortalidade , Cardiopatias Congênitas/cirurgia , Período Pré-Operatório , Medição de Risco/métodos , Feminino , Humanos , Masculino , Projetos Piloto , Sistema de Registros , Estudos RetrospectivosAssuntos
Doenças Cardiovasculares/terapia , Telemedicina/normas , Síndrome Coronariana Aguda/economia , Síndrome Coronariana Aguda/epidemiologia , Síndrome Coronariana Aguda/terapia , Brasil , Doenças Cardiovasculares/economia , Doenças Cardiovasculares/epidemiologia , Humanos , Telemedicina/métodos , Telemedicina/organização & administração , Resultado do TratamentoRESUMO
OBJECTIVE: To assess the care provided to patients with congenital heart diseases and ischemic heart diseases undergoing cardiac surgery according to the fast-track recovery protocol compared with those undergoing the conventional procedure. METHODS: The transfer of patients from one hospital unit to another was assessed for 175 patients, 107 (61%) men and 68 (39%) women, with ages ranging from 0.3 to 81 years. RESULTS: The discharge rate from the different hospital units per unit of time of the patients with congenital heart diseases treated according to the fast-track recovery protocol compared with that of patients conventionally treated was as follows: a) 11.3 times faster than the discharge rate of patients treated according to the conventional protocol, in regard to the time spent in the operating room; b) 6.3 times faster in regard to the duration of the surgical intervention; c) 6.8 times faster in regard to the duration of anesthesia; d) 1.5 times faster in regard to the duration of perfusion; e) 2.8 times faster in regard to the stay in the postoperative recovery I unit; f) 6.7 times faster in regard to hospital stay (time period between hospital admission and hospital discharge); g) 2.8 times faster in regard to the stay in the preoperative unit; h) 2.1 times faster in regard to the stay in the admission unit after discharge from postoperative recovery; i) associated with reduced costs. The difference was not significant for patients with ischemic heart disease. CONCLUSION: A reduction in the length of hospital stay and costs for the care of patients undergoing cardiac surgery according to the fast-track protocol was observed.
Assuntos
Cardiopatias Congênitas/cirurgia , Tempo de Internação/estatística & dados numéricos , Isquemia Miocárdica/cirurgia , Cuidados Pós-Operatórios/economia , Sala de Recuperação/economia , Adolescente , Adulto , Idoso , Idoso de 80 Anos ou mais , Criança , Pré-Escolar , Protocolos Clínicos , Feminino , Humanos , Lactente , Masculino , Pessoa de Meia-Idade , Transferência de Pacientes , Complicações Pós-Operatórias , Risco , Resultado do TratamentoRESUMO
OBJETIVO: Avaliar o atendimento de cardiopatas congênitos e cardiopatas isquêmicos submetidos à cirurgia cardíaca no protocolo de atendimento na via rápida (fast-track recovery) em relação ao convencional. MÉTODOS: Avaliada a movimentação de 175 pacientes, 107 (61 por cento) homens e 68 (39 por cento) mulheres, idades entre 0,3-81 anos nas diferentes unidades hospitalares. RESULTADOS: A taxa de alta das diferentes unidades hospitalares por unidade de tempo, dos cardiopatas congênitos atendidos no protocolo da via rápida em relação ao convencional foi: a) 11,3 vezes a taxa de alta quando assistidos no protocolo da via convencional, quanto ao tempo de permanência no centro cirúrgico; b) 6,3 vezes quanto à duração da intervenção cirúrgica; c) 6,8 vezes quanto à duração da anestesia; d) 1,5 vezes quanto à duração da perfusão; e) 2,8 vezes quanto à permanência na unidade de recuperação pós-operatória I; f) 6,7 vezes quanto à permanência no hospital (período de tempo entre a data da internação e a data da alta); g) 2,8 vezes quanto à permanência na unidade de internação pré-operatória; h) 2,1 vezes quanto à permanência na unidade de internação após a alta da recuperação pós-operatória; i) associada com redução de despesas pré e pós-operatórias. A diferença não foi significativa nos portadores de cardiopatia isquêmica. CONCLUSAO: Verificou-se redução do período de internação e de despesas no atendimento dos pacientes submetidos à intervenção cirúrgica cardíaca no protocolo da via rápida.