Dynamic Nomogram for Predicting the Risk of Perioperative Neurocognitive Disorders in Adults.

BACKGROUND: Simple and rapid tools for screening high-risk patients for perioperative neurocognitive disorders (PNDs) are urgently needed to improve patient outcomes. We developed an online tool with machine-learning algorithms using routine variables based on multicenter data. METHODS: The entire dataset was composed of 49,768 surgical patients from 3 representative academic hospitals in China. Surgical patients older than 45 years, those undergoing general anesthesia, and those without a history of PND were enrolled. When the patient's discharge diagnosis was PND, the patient was in the PND group. Patients in the non-PND group were randomly extracted from the big data platform according to the surgical type, age, and source of data in the PND group with a ratio of 3:1. After data preprocessing and feature selection, general linear model (GLM), artificial neural network (ANN), and naive Bayes (NB) were used for model development and evaluation. Model performance was evaluated by the area under the receiver operating characteristic curve (ROCAUC), the area under the precision-recall curve (PRAUC), the Brier score, the index of prediction accuracy (IPA), sensitivity, specificity, etc. The model was also externally validated on the multiparameter intelligent monitoring in intensive care (MIMIC) Ⅳ database. Afterward, we developed an online visualization tool to preoperatively predict patients' risk of developing PND based on the models with the best performance. RESULTS: A total of 1051 patients (242 PND and 809 non-PND) and 2884 patients (6.2% patients with PND) were analyzed on multicenter data (model development, test [internal validation], external validation-1) and MIMIC Ⅳ dataset (external validation-2). The model performance based on GLM was much better than that based on ANN and NB. The best-performing GLM model on validation-1 dataset achieved ROCAUC (0.874; 95% confidence interval [CI], 0.833-0.915), PRAUC (0.685; 95% CI, 0.584-0.786), sensitivity (72.6%; 95% CI, 61.4%-81.5%), specificity (84.4%; 95% CI, 79.3%-88.4%), Brier score (0.131), and IPA (44.7%), and of which the ROCAUC (0.761, 95% CI, 0.712-0.809), the PRAUC (0.475, 95% CI, 0.370-0.581), Brier score (0.053), and IPA (76.8%) on validation-2 dataset. Afterward, we developed an online tool (https://pnd-predictive-model-dynnom.shinyapps.io/ DynNomapp/) with 10 routine variables for preoperatively screening high-risk patients. CONCLUSIONS: We developed a simple and rapid online tool to preoperatively screen patients' risk of PND using GLM based on multicenter data, which may help medical staff's decision-making regarding perioperative management strategies to improve patient outcomes.

A new, feasible, and convenient method based on semantic segmentation and deep learning for hemoglobin monitoring.

Objective: Non-invasive methods for hemoglobin (Hb) monitoring can provide additional and relatively precise information between invasive measurements of Hb to help doctors' decision-making. We aimed to develop a new method for Hb monitoring based on mask R-CNN and MobileNetV3 with eye images as input. Methods: Surgical patients from our center were enrolled. After image acquisition and pre-processing, the eye images, the manually selected palpebral conjunctiva, and features extracted, respectively, from the two kinds of images were used as inputs. A combination of feature engineering and regression, solely MobileNetV3, and a combination of mask R-CNN and MobileNetV3 were applied for model development. The model's performance was evaluated using metrics such as R2, explained variance score (EVS), and mean absolute error (MAE). Results: A total of 1,065 original images were analyzed. The model's performance based on the combination of mask R-CNN and MobileNetV3 using the eye images achieved an R2, EVS, and MAE of 0.503 (95% CI, 0.499-0.507), 0.518 (95% CI, 0.515-0.522) and 1.6 g/dL (95% CI, 1.6-1.6 g/dL), which was similar to that based on MobileNetV3 using the manually selected palpebral conjunctiva images (R2: 0.509, EVS:0.516, MAE:1.6 g/dL). Conclusion: We developed a new and automatic method for Hb monitoring to help medical staffs' decision-making with high efficiency, especially in cases of disaster rescue, casualty transport, and so on.

Serum Soluble Vascular Endothelial Growth Factor Receptor 1 as a Potential Biomarker of Hepatopulmonary Syndrome.

Background and Aims: The results of basic research implicate the vascular endothelial growth factor (VEGF) family as a potential target of hepatopulmonary syndrome (HPS). However, the negative results of anti-angiogenetic therapy in clinical studies have highlighted the need for markers for HPS. Therefore, we aimed to determine whether VEGF family members and their receptors can be potential biomarkers for HPS through clinical and experimental studies. Methods: Clinically, patients with chronic liver disease from two medical centers were enrolled and examined for HPS. Patients were divided into HPS, intrapulmonary vascular dilation [positive contrast-enhanced echocardiography (CEE) and normal oxygenation] and CEE-negative groups. Baseline information and perioperative clinical data were compared between HPS and non-HPS patients. Serum levels of VEGF family members and their receptors were measured. In parallel, HPS rats were established by common bile duct ligation. Liver, lung and serum samples were collected for the evaluation of pathophysiologic changes, as well as the expression levels of the above factors. Results: In HPS rats, all VEGF family members and their receptors underwent significant changes; however, only soluble VEGFR1 (sFlt-1) and the sFlt-1/ placental growth factor (PLGF) ratio were changed in almost the same manner as those in HPS patients. Furthermore, through feature selection and internal and external validation, sFlt-1 and the sFlt-1/PLGF ratio were identified as the most important variables to distinguish HPS from non-HPS patients. Conclusions: Our results from animal and human studies indicate that sFlt-1 and the sFlt-1/PLGF ratio in serum are potential markers for HPS.

Assessment of acute lung injury/acute respiratory distress syndrome using B-type brain natriuretic peptide.

OBJECTIVES: To investigate the clinical value of B-type natriuretic peptide (BNP) in the assessment of severity and prognosis in acute lung injury/acute respiratory distress syndrome (ALI/ARDS). METHODS: Plasma BNP level, arterial blood gases, serum C-reactive protein level, alveolar-arterial oxygen tension difference and oxygenation index were measured in patients with and without ALI/ARDS within 24 h of admission to an intensive care unit. Patients with ALI/ARDS were divided into mild, moderate or severe groups according to the degree of hypoxaemia. Survival >28 days was recorded. RESULTS: A total of 59 patients with ALI/ARDS and 14 patients without ALI/ARDS were included in the study. Of the patients with ALI/ARDS, 18 had mild hypoxaemia, 20 had moderate hypoxaemia and 21 had severe hypoxaemia. The mean ± SD BNP level was significantly higher in all three ALI/ARDS groups (92.41 ± 28.19 pg/ml, 170.64 ± 57.34 pg/ml and 239.06 ± 59.62 pg/ml, respectively, in the mild, moderate and severe groups) than in the non-ALI/ARDS group (47.27 ± 19.63 pg/ml); the increase in BNP level with increasing severity was also statistically significant. When divided according to outcome, the BNP level in the death group (267.07 ± 45.06 pg/ml) was significantly higher than in the survival group (128.99 ± 45.42 pg/ml). CONCLUSIONS: The BNP level may be of value in evaluating severity and prognosis in patients with ALI/ARDS.