Identifying the Risk of Sepsis in Patients With Cancer Using Digital Health Care Records: Machine Learning-Based Approach.

BACKGROUND: Sepsis is diagnosed in millions of people every year, resulting in a high mortality rate. Although patients with sepsis present multimorbid conditions, including cancer, sepsis predictions have mainly focused on patients with severe injuries. OBJECTIVE: In this paper, we present a machine learning-based approach to identify the risk of sepsis in patients with cancer using electronic health records (EHRs). METHODS: We utilized deidentified anonymized EHRs of 8580 patients with cancer from the Samsung Medical Center in Korea in a longitudinal manner between 2014 and 2019. To build a prediction model based on physical status that would differ between sepsis and nonsepsis patients, we analyzed 2462 laboratory test results and 2266 medication prescriptions using graph network and statistical analyses. The medication relationships and lab test results from each analysis were used as additional learning features to train our predictive model. RESULTS: Patients with sepsis showed differential medication trajectories and physical status. For example, in the network-based analysis, narcotic analgesics were prescribed more often in the sepsis group, along with other drugs. Likewise, 35 types of lab tests, including albumin, globulin, and prothrombin time, showed significantly different distributions between sepsis and nonsepsis patients (P<.001). Our model outperformed the model trained using only common EHRs, showing an improved accuracy, area under the receiver operating characteristic (AUROC), and F1 score by 11.9%, 11.3%, and 13.6%, respectively. For the random forest-based model, the accuracy, AUROC, and F1 score were 0.692, 0.753, and 0.602, respectively. CONCLUSIONS: We showed that lab tests and medication relationships can be used as efficient features for predicting sepsis in patients with cancer. Consequently, identifying the risk of sepsis in patients with cancer using EHRs and machine learning is feasible.

Automated Classification of Normal Control and Early-Stage Dementia Based on Activities of Daily Living (ADL) Data Acquired from Smart Home Environment.

With the global trend toward an aging population, the increasing number of dementia patients and elderly living alone has emerged as a serious social issue in South Korea. The assessment of activities of daily living (ADL) is essential for diagnosing dementia. However, since the assessment is based on the ADL questionnaire, it relies on subjective judgment and lacks objectivity. Seven healthy seniors and six with early-stage dementia participated in the study to obtain ADL data. The derived ADL features were generated by smart home sensors. Statistical methods and machine learning techniques were employed to develop a model for auto-classifying the normal controls and early-stage dementia patients. The proposed approach verified the developed model as an objective ADL evaluation tool for the diagnosis of dementia. A random forest algorithm was used to compare a personalized model and a non-personalized model. The comparison result verified that the accuracy (91.20%) of the personalized model was higher than that (84.54%) of the non-personalized model. This indicates that the cognitive ability-based personalization showed encouraging performance in the classification of normal control and early-stage dementia and it is expected that the findings of this study will serve as important basic data for the objective diagnosis of dementia.

Encapsulation of Lactobacillus rhamnosus GG Using Milk Protein-Based Delivery Systems: Effects of Reaction Temperature and Holding Time on Their Physicochemical and Functional Properties.

Microencapsulation is a protective process for materials that are sensitive to harsh conditions encounted during food manufacture and storage. The objectives of this research were to manufacture a milk protein-based delivery system (MPDS) containing Lactobacillus rhamnosus GG (LGG) using skim milk powder and to investigate the effects of manufacturing variables, such as reaction temerpature and holding time, on the physiccohemical properties of MPDS and viability of LGG under dairy food processing and storage conditions. MPDS was prepared using chymosin at varing reaction temperatures from 25°C to 40°C for 10 min and holding times from 5 to 30 min at 25°C. The morphological and physicochemical properties of MPDS were evaluated using a confocal laser scanning microscope and a particle size analyzer, respectively. The number of viable cells were determined using the standard plate method. Spherical-shaped MPDS particles were successfully manufactured. The particle size of MPDS was increased with a decrease in reaction temperature and an increase in holding time. As reaction temperature and holding time were increased, the encapsulation efficiency of LGG in MPDS was increased. During pasteurization, the use of MPDS resulted in an increase in the LGG viability. The encapsulation of LGG in MPDS led to an increase in the viability of LGG in simulated gastric fluid. In addition, the LGG viability was enhanced with an increase in reaction temperature and holding time. In conclusions, the encapsulation of LGG in MPDS could be an effective way of improving the viability of LGG during pasturization process in various foods.