A new risk predictive scoring system of vasovagal reactions in patients with preoperative autologous blood donation.

BACKGROUND AND OBJECTIVES: Vasovagal response (VVR) is the most common adverse reaction during blood donation and it is the main element for the safety of the patients with preoperative autologous blood donation (PABD). Accurate identification high-risk group is of great significance for PABD. Our study aimed to establish a scoring system based on the nomogram to screen the high-risk population and provide evidence for preventing the occurrence of VVRs. MATERIALS AND METHODS: A number of 4829 patients underwent PABD between July 2017 and June 2020 in the first medical center of Chinese PLA Hospital were recruited, 3387 of whom were included in the training group (70 %; 108 VVRs patients vs 3279 Non-VVRs patients), 1442 were included in the validation group (30 %; 46 VVRs patients vs 1396 Non-VVRs patients). The data were analyzed by univariate and multivariate logistic regression. The nomogram of the scoring system was created by using the RMS tool in R software. RESULTS: Seven variables including BMI, hematocrit, pre-phlebotomy heart rate and systolic blood pressure, history of blood donation, age group and primary disease were selected to build the nomogram, which was shown as prediction model. And the score was 0-1 for BMI, 0-2 for hematocrit, systolic blood pressure, heart rate and no blood donation history, 0-10 for age, 0-3 for primary disease. When the total cutoff score was 11, the predictive system for identifying VVRs displayed higher diagnostic accuracy. The area under the curve, specificity, and sensitivity of the training group were 0.942, 82.41 % and 97.17 %, respectively, whereas those of the validation group were 0.836, 78.26 % and 78.15 %, respectively. CONCLUSION: A risk predictive scoring system was successfully developed to identify high-risk VVRs group form PABD patients that performed well.

Cross-Hospital Sepsis Early Detection via Semi-Supervised Optimal Transport With Self-Paced Ensemble.

Leveraging machine learning techniques for Sepsis early detection and diagnosis has attracted increasing interest in recent years. However, most existing methods require a large amount of labeled training data, which may not be available for a target hospital that deploys a new Sepsis detection system. More seriously, as treated patients are diversified between hospitals, directly applying a model trained on other hospitals may not achieve good performance for the target hospital. To address this issue, we propose a novel semi-supervised transfer learning framework based on optimal transport theory and self-paced ensemble for Sepsis early detection, called SPSSOT, which can efficiently transfer knowledge from the source hospital (with rich labeled data) to the target hospital (with scarce labeled data). Specifically, SPSSOT incorporates a new optimal transport-based semi-supervised domain adaptation component that can effectively exploit all the unlabeled data in the target hospital. Moreover, self-paced ensemble is adapted in SPSSOT to alleviate the class imbalance issue during transfer learning. In a nutshell, SPSSOT is an end-to-end transfer learning method that automatically selects suitable samples from two domains (hospitals) respectively and aligns their feature spaces. Extensive experiments on two open clinical datasets, MIMIC-III and Challenge, demonstrate that SPSSOT outperforms state-of-the-art transfer learning methods by improving 1-3% of AUC.

[Efficacy assessment of acupuncture and moxibustion on tear secretion in xerophthalmia].

OBJECTIVE: To compare the efficacy differences between acupuncture-moxibustion and medication in xerophthalmia. METHODS: Eighty cases of xerophthalmia were randomly divided into an acupuncture-moxibustion group and a medication group, 40 cases in each group. In acupuncture-moxibustion group, acupuncture was applied to the local and distal points, such as Jingming (BL 1), Cuanzhu (BL 2), Taiyang (EX-HN 5) and Quchi (LI 11) etc., combined with non-smoking moxibustion. In medication group, Sodium Hyaluronate eye drops were administered, three times per day, 1 drop each time. Before and after treatment, tear secretion volume (Schirmer's test), break-up time (BUT), symptom score, visual function score and tear film grade were observed. RESULTS: The total effective rate was 73.1% (57/78) in acupuncture-moxibustion group, and was 37.2% (29/78) in medication group, indicating significant statistical difference in comparison (P < 0.05). There was a significant difference in statistics in tear secretion volume between two groups after treatment (P < 0.05), in which, the result in acupuncture-moxibustion group was superior to that in medication group. The significant statistical differences presented in tear secretion volume, BUT, symptom score, visual function score and tear film grade in comparison before and after treatment in acupuncture-moxibustion group (all P < 0.05). The significant statistical difference presented in symptom score and tear film grade before and after treatment in medication group (both P < 0.05). CONCLUSION: Acupuncture-moxibustion apparently relieves the symptoms of xerophthalmia, promotes tear secretion and improves the life quality of patients.