We developed an artificial intelligence (AI) model that can predict five-year survival in patients with stage IV metastatic breast cancer, mainly based on host factors and sarcopenia. From a prospectively built breast cancer registry, a total of 210 metastatic breast cancer patients were selected in a consecutive manner using inclusion/exclusion criteria. The patients’ data were divided into two categories: a group that survived for more than 5 years and a group that did not survive for 5 years. For the AI model input, 11 features were considered, including age, body mass index, skeletal muscle area (SMA), height-relative SMA (H-SMI), height square-relative SMA (H2-SMA), weight-relative SMA (W-SMA), muscle mass, anticancer chemotherapy, radiation therapy, and comorbid diseases such as hypertension and mellitus. For the feature importance analysis, we compared classifiers using six different machine learning algorithms and found that extreme gradient boosting (XGBoost) provided the best accuracy. Subsequently, we performed the feature importance analysis based on XGBoost and proposed a 4-layer deep neural network, which considered the top 10 ranked features. Our proposed 4-layer deep neural network provided high sensitivity (75.00%), specificity (78.94%), accuracy (78.57%), balanced accuracy (76.97%), and an area under receiver operating characteristics of 0.90. We generated a web application for anyone to easily access and use this AI model to predict five-year survival. We expect this web application to be helpful for patients to understand the importance of host factors and sarcopenia and achieve survival gain.

Background Respiratory distress syndrome (RDS) is a disease that commonly affects premature infants whose lungs are not fully developed. RDS results from a lack of surfactant in the lungs. The more premature the infant is, the greater is the likelihood of having RDS. However, even though not all premature infants have RDS, preemptive treatment with artificial pulmonary surfactant is administered in most cases. Objective We aimed to develop an artificial intelligence model to predict RDS in premature infants to avoid unnecessary treatment. Methods In this study, 13,087 very low birth weight infants who were newborns weighing less than 1500 grams were assessed in 76 hospitals of the Korean Neonatal Network. To predict RDS in very low birth weight infants, we used basic infant information, maternity history, pregnancy/birth process, family history, resuscitation procedure, and test results at birth such as blood gas analysis and Apgar score. The prediction performances of 7 different machine learning models were compared, and a 5-layer deep neural network was proposed in order to enhance the prediction performance from the selected features. An ensemble approach combining multiple models from the 5-fold cross-validation was subsequently developed. Results Our proposed ensemble 5-layer deep neural network consisting of the top 20 features provided high sensitivity (83.03%), specificity (87.50%), accuracy (84.07%), balanced accuracy (85.26%), and area under the curve (0.9187). Based on the model that we developed, a public web application that enables easy access for the prediction of RDS in premature infants was deployed. Conclusions Our artificial intelligence model may be useful for preparations for neonatal resuscitation, particularly in cases involving the delivery of very low birth weight infants, as it can aid in predicting the likelihood of RDS and inform decisions regarding the administration of surfactant.

BACKGROUND Respiratory distress syndrome (RDS) is a disease that commonly affects premature infants whose lungs are not fully developed. It results from a lack of surfactant in the lungs. The more premature the infant, the greater the likelihood of having RDS. However, even though not all premature infants have RDS, preemptive treatment with artificial pulmonary surfactant is administered in most cases. OBJECTIVE We aimed to develop an artificial intelligence (AI) model to predict RDS in premature infants to avoid unnecessary treatment. METHODS This study was conducted for the evaluation of 13,087 very low birth weight infants (VLBWIs) who were newborns weighing less than 1,500g (n=76 hospitals). To predict RDS in VLBWIs, we used basic infant information, maternity history, pregnancy/birth process, family history, resuscitation procedure, and test results at birth such as blood gas analysis and Apgar score. A comparison of the prediction performances from seven different machine learning models was performed, and a 5-layer deep neural network (DNN) was then proposed in order to enhance the prediction performance from the selected features. An ensemble approach combining multiple models from 5-fold cross-validation was subsequently developed. RESULTS Our proposed ensemble 5-layer DNN including the top-20 features provided high sensitivity (83.03%), specificity (87.50%), accuracy (84.07%), balanced accuracy (85.26%), and an area under the curve (0.9187). Based on the model that we developed, a public web application that enables easy access for the prediction of RDS in premature was deployed. CONCLUSIONS This AI may find it useful to incorporate the use of this tool in their preparations for neonatal resuscitation, particularly in cases involving the delivery of very low birth weight infants, as it can aid in predicting the likelihood of respiratory distress syndrome and inform decisions regarding the administration of surfactant.