Saturday, March 2, 2024
BestWooCommerceThemeBuilttoBoostSales-728x90

Development of a deep learning model that predicts critical events of pediatric patients admitted to general wards – Scientific Reports


Study setting and data source

This retrospective cross-sectional observational study was conducted at a tertiary children’s hospital with about 350 beds. The subjects were patients under the age of 18 who had been admitted to the general ward of the children’s hospital between January 2020 and December 2022. The pseudonymized data used for analysis were collected from the clinical data warehouse of the hospital information system. The measurements of Systolic BP (SBP), diastolic BP (DBP), HR, RR, body temperature (BT), and the oxygen saturation measured with pulse oximetry (SpO2) were recorded in the general ward. Measurements from the emergency department or ICU were excluded. Recorded time, sex, age (in months), admission date, discharge date, and pseudonymized study-specific identification code were collected.

This study was approved for exemption from review by the Institutional Review Board of Seoul National University Hospital because it used only pseudonymized information and did not collect personally identifiable information (H-2209-001-1032). Since only information that could not identify the research subjects was used, the above committee confirmed that it was impossible to obtain consent from specific subjects. Moreover, the study was conducted in accordance with the principles of the Declaration of Helsinki.

Data preprocessing

The pseudonymized identification code and hospitalization date were combined to create a unique classification code according to each individual hospitalization date, which was defined as the individual hospitalization identification code (IHID). The collected data were classified according to IHID, sorted in ascending order of vital sign measurement time, and missing values among SBP, DBP, HR, RR, BT, and SpO2 were replaced with the immediately preceding values. In addition, the interval of vital sign measurement time was calculated within the same IHID (each vital sign measurement time—previous measurement time, in minutes), and this was defined as the measurement interval. Since the normal ranges of BP, HR, and RR in children differ according to age, z-scores for each age were calculated and used for analysis. Centile charts of vital signs for each age developed in a previous study were used for z-score conversion17.

Critical events were defined as cases where CPR occurred in the general ward, unexpected transfers to the ICU, and cases of mortality (results of CPR or discontinuation of life-sustaining treatment)18,19. Critical records were defined as the data measured from 6 h before the occurrence of the critical event to the time of occurrence in the case of unexpected ICU transfer or mortality, and in the case of CPR, it was defined as the data measured from 6 h before the occurrence to 30 min after the occurrence (from 6 h before CPR until death in the case of mortality after CPR). In order to perform deep learning on critical records, the total records were divided into two groups: critical group and non-critical group. Since the records of individuals who experienced a critical event will have a mixture of critical records and non-critical records, IHID’s non-critical records with critical events were excluded from the non-critical group. In addition, since it is expected to be an imbalanced dataset in which the size of the non-critical group is substantially larger than the sample size of the critical group, only the last records for each IHID among the non-critical groups were used for deep learning. In general, it is common sense that vital sign records measured during hospitalization for each IHID are not limited to just one occurrence but rather numerous. Therefore, we anticipated that retaining only the last record per IHID among the vital sign records in the non-critical group, and utilizing all records in the critical group, would relatively alleviate the imbalance between the two groups. R version 4.3.1 (R Foundation for statistical computing, Vienna, Austria; https://www.r-project.org) was used for data preprocessing, and open packages such as the generalized additive models for location scale and shape and sitar were used in this process20,21,22.

Deep learning and data analysis

The preprocessed dataset was divided into a training set and a test set at a ratio of 8:2, and each was used for model training and testing. A simple artificial neural network (ANN) algorithm based on the multilayer perceptron was used for deep learning. Nine parameters used for learning were age, sex, z-score of SBP, z-score of DBP, z-score of HR, z-score of RR, BT, SpO2, and the measurement interval. The above features were normalized to a value between 0 and 1. The ANN model was composed of 3 hidden layers (each with node counts of 128, 128, and 64, respectively), and a 30% dropout was applied after each layer. The Adam optimizer and rectified linear unit activator were used in the process23. It was trained for 10,000 epochs with a learning rate of 0.0001 using Python version 3.8.10 (Python Software Foundation, Beaverton, OR, USA; https://www.python.org). Scikit-learn library was used for normalization24, PyTorch was used for model training and test25, and matplotlib and Shapley additive explanation (SHAP) library were used for visualization26. Since the measurement interval value of the first record for each IHID cannot be calculated (missing value), the average value of all measurement intervals was imputed. Continuous variables were described as median (interquartile range) and categorical variables as number (%).

Outcomes

The primary outcome of this study was the overall predictive performance of the developed model. Accuracy, AUROC, and area under the precision-recall curve (AUPRC) were used to evaluate the predictive performance of the model. The secondary outcomes included subdividing critical events into CPR occurrence, unexpected ICU transfer, and mortality, respectively, and evaluating the performance of the developed model for each. Additionally, based on the time elapsed before a critical incident occurred, measurements were divided into six subgroups: 0–1 h, 1–2 h, 2–3 h, 3–4 h, 4–5 h, and 5–6 h. For each subgroup, the predictive performance of the model was included. It also included an assessment of the importance of the prediction process for each feature used in learning and the correlation between features.



Source link

Related Articles

Leave a Reply

[td_block_social_counter facebook="beingmedicos1" twitter="being_medicos" youtube="beingmedicosgroup" style="style8 td-social-boxed td-social-font-icons" tdc_css="eyJhbGwiOnsibWFyZ2luLWJvdHRvbSI6IjM4IiwiZGlzcGxheSI6IiJ9LCJwb3J0cmFpdCI6eyJtYXJnaW4tYm90dG9tIjoiMzAiLCJkaXNwbGF5IjoiIn0sInBvcnRyYWl0X21heF93aWR0aCI6MTAxOCwicG9ydHJhaXRfbWluX3dpZHRoIjo3Njh9" custom_title="Stay Connected" block_template_id="td_block_template_8" f_header_font_family="712" f_header_font_transform="uppercase" f_header_font_weight="500" f_header_font_size="17" border_color="#dd3333"]
- Advertisement -spot_img

Latest Articles