[Control study of the intelligent calculation method and the traditional calculation method in risk assessments of hospitalization].

OBJECTIVE: To explore the accuracy of intelligent calculation (IC) method for risk assessment of hospitalization for patients, aiming to build a more advantageous risk assessment system. METHODS: The "Search Engine" program was developed based on hospital information system (HIS) of the Fifth Center Hospital in Tianjin, which automatically captured patient information and generated nutritional risk screening 2002 (NRS 2002) score, Caprini thrombosis risk assessment model and Padua thrombosis risk assessment model for venous thromboembolism (VTE), the CHA2DS2-VASc for predicting stroke risk stratification in atrial fibrillation and the HAS-BLED for predicting bleeding risk in anticoagulated patients with atrial fibrillation. A randomized controlled trial was conducted. According to the applicable conditions of each risk assessment, 100 risk scores from "Search Engine" program belonged to each risk assessment were randomly selected, defined as the IC group. Manual scoring with the data of the same case at the same time, defined as the traditional calculation (TC) group, compared the consistency of the scores and the difference in time-consuming between the two groups. RESULTS: The Bland-Altman plots showed that the 95% limits of agreement (95%LoA) of NRS 2002 score, Caprini score, Padua score, CHA2DS2-VASc score and HAS-BLED score was -0.46 to 0.41, -0.49 to 0.52, -0.50 to 0.41, -0.67 to 0.60, -0.44 to 0.43, respectively, all P > 0.05. In this study, the Bland-Altman plot showed that 95%, 96%, 97%, 97%, 95% plots fell within the 95%LoA in NRS 2002 score, Caprini score, Padua score, wwCHA2DS2-VASc score and HAS-BLED score by the two methods, respectively. The all plots of 95%LoA were within the clinically acceptable range (-0.5 to 0.5 scores). The time-consuming of NRS 2002 score, Caprini score, Padua score, CHA2DS2-VASc score and HAS-BLED score in IC group were significantly shorter than those in TC group [0.72 (0.71, 0.73) seconds vs. 361.02 (322.41, 361.02) seconds, 0.72 (0.72, 0.73) seconds vs. 196.68 (179.99, 291.20) seconds, 0.72 (0.72, 0.73) seconds vs. 105.75 (92.32, 114.70) seconds, 0.72 (0.71, 0.72) seconds vs. 72.66 (56.24, 84.20) seconds, 0.72 (0.71, 0.72) seconds vs. 51.30 (38.88, 57.15) seconds, respectively, all P < 0.001]. CONCLUSION: For the above five risk assessments, the TC method and IC method has good consistency in scores, and the IC method is faster, which has good application prospect for clinical application.

[Study of hospitalization risk indicators for intensive care unit patients evaluated by intelligent calculation method].

OBJECTIVE: To explore the characteristics of the changes in risk score for intensive care unit (ICU) patients during hospitalization by the intelligent calculation method, and to provide evidence for the risk prevention. METHODS: In this retrospective study, ICU patients of the Fifth Central Hospital in Tianjin from November 3, 2021 to March 28, 2022 were enrolled and divided into ≥ 14 days group, 10-13 days group, 7-9 days group, and 3-6 days group according to the ICU length of stay. Risk scores assessed by the intelligent calculation method of the ICU patients were collected, including nutritional risk screening 2002 (NRS 2002), Caprini score and Padua score. NRS 2002 score for all patients, Caprini score for surgical patients and Padua score for internal medicine patients were selected. Trends in change of each score were compared between patients admitted to ICU 1, 3, 7 (if necessary), 10 (if necessary), and 14 days (if necessary). RESULTS: A total of 138 patients were involved, including 79 males and 59 females, with an average age of (61.71±18.86) years and an average hospital stay of [6.00 (4.00, 9.25)] days. (1) in the group with ICU length of stay ≥ 14 days (21 cases): there was no significant change in the NRS 2002 scores of the patients within 10 days, but the NRS 2002 score was significantly decreased in 14 days as compared with 1 day [3.00 (2.50, 3.50) vs. 4.00 (3.00, 5.00), P < 0.05]; both Caprini and Padua score were increased with prolonged hospital stay and compared with 1 day, the scores at the other time points were significantly increased, especially at 14 days [Caprini score: 5.00 (3.25,7.00) vs. 2.50 (1.25, 5.50), Padua score: 6.00 (6.00, 7.00) vs. 3.00 (1.00, 3.00), both P < 0.05]. (2) in the group with ICU length of stay from 10-13 days (15 cases): with the prolonged hospital stay, there was no significant change in NRS 2002 score, but both Caprini and Padua score were increased at 3, 7, 10 days, especially at 10 days [Caprini score: 3.00 (2.00, 4.75) vs. 2.00 (0.25, 2.75), Padua score: 5.00 (3.50, 6.00) vs. 2.00 (0.50, 4.00), both P < 0.05]. (3) in the group with ICU length of stay from 7-9 days (23 cases): compared with 1 day, the NRS 2002 score at 3 days and7 days were decreased, but the Caprini and Padua score were increased, especially at 7 days [NRS 2002 score: 2.00 (1.00, 4.00) vs. 2.00 (2.00, 4.00), Caprini score: 3.00 (2.00, 5.50) vs. 2.00 (0.25, 3.00), Padua score: 5.00 (4.00, 6.00) vs. 2.00 (0,2.00),all P < 0.05]. (4) in the group with ICU length of stay from 3-6 days (79 cases): compared with 1 day, the NRS 2002 score at 3 days was decreased [NRS 2002 score: 2.00 (1.00, 3.00) vs. 2.00 (1.00, 3.00), P < 0.05], Caprini and Padua score were significantly increased [Caprini score: 3.00 (2.00, 4.00) vs. 2.00 (1.00, 3.00), Padua score: 5.00 (4.00, 5.00) vs. 2.00 (1.00, 3.00), both P < 0.05]. CONCLUSIONS: Based on dynamic assessment of intelligent calculation methods, the risk of thrombosis in ICU patients increased with hospital length of stay, and the nutritional risk was generally flat or reducing in different hospitalization periods.

New insights on super-high resolution for video-based heart rate estimation with a semi-blind source separation method.

Remote photoplethysmography (rPPG), a non-contact technique to estimate heart rates (HR) from video recordings, has attracted much attention from researchers in recent years. It is well-known that rPPG signals can be extracted from low-resolution videos. However, the measurement quality may degrade due to camera quantization noise if only a small number of pixels are within the skin region of interest. The purpose of this paper is to comprehensively investigate the benefit of using a super-high resolution for the rPPG-based HR estimation under various shooting distances. A new semi-blind source separation (semi-BSS) rPPG method, which is proposed to combine the advantages of BSS and model-based methods, is fully tested on both the public UBFC-RPPG and self-collected video datasets. The experimental results demonstrate that the new semi-BSS method outperforms several existing techniques. A consistent and remarkable improvement on the rPPG signal quality has been observed with the super-high resolution when the shooting distance is no less than 1.0 m. This indicates that selecting an appropriate resolution based on a given shooting distance also plays a crucial role to improve the quality of rPPG measurements.