Intraoperative cell salvage (IOCS) has been widely applied as an important blood conservation measure in surgical operations. However, there is currently a lack of clinical practice guidelines for the implementation of IOCS in patients with malignant tumors. This report aims to provide clinicians with recommendations on the use of IOCS in patients with malignant tumors based on the review and assessment of the existed evidence. Data were derived from databases such as PubMed, Embase, the Cochrane Library and Wanfang. The guideline development team formulated recommendations based on the quality of evidence, balance of benefits and harms, patient preferences, and health economic assessments. This study constructed seven major clinical questions. The main conclusions of this guideline are as follows: 1) Compared with no perioperative allogeneic blood transfusion (NPABT), perioperative allogeneic blood transfusion (PABT) leads to a more unfavorable prognosis in cancer patients (Recommended); 2) Compared with the transfusion of allogeneic blood or no transfusion, IOCS does not lead to a more unfavorable prognosis in cancer patients (Recommended); 3) The implementation of IOCS in cancer patients is economically feasible (Recommended); 4) Leukocyte depletion filters (LDF) should be used when implementing IOCS in cancer patients (Strongly Recommended); 5) Irradiation treatment of autologous blood to be reinfused can be used when implementing IOCS in cancer patients (Recommended); 6) A careful assessment of the condition of cancer patients (meeting indications and excluding contraindications) should be conducted before implementing IOCS (Strongly Recommended); 7) Informed consent from cancer patients should be obtained when implementing IOCS, with a thorough pre-assessment of the patient's condition and the likelihood of blood loss, adherence to standardized internally audited management procedures, meeting corresponding conditions, and obtaining corresponding qualifications (Recommended). In brief, current evidence indicates that IOCS can be implemented for some malignant tumor patients who need allogeneic blood transfusion after physician full evaluation, and LDF or irradiation should be used during the implementation process.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

ObjectiveTo analyze the characteristic expression patterns of six neurotransmitters including 5-hydroxytryptamine （5-HT）， dopamine （DA）， acetylcholine （ACh）， norepinephrine （NE）， inhibitory neurotransmitter （INH）， and excitatory neurotransmitter （EXC） in the whole brain and different brain regions of depression patients by Search of Encephalo Telex （SET）， providing new ideas for the study of heterogeneous etiology of depression. Methods（1） A retrospective study was conducted on supra-slow signals of EEG fluctuations in 1 028 patients with depression. The SET system was used to obtain the expression information of six neurotransmitters in the whole brain and 12 brain regions： left frontal region （F3）， right frontal region （F4）， left central region （C3）， right central region （C4）， left parietal region （P3）， right parietal region （P4）， left occipital region （O1）， right occipital region （O2）， left anterior temporal region （F7）， right anterior temporal region （F8）， left posterior temporal region （T5）， and right posterior temporal region （T6）. The expression information of each neurotransmitter was compared with the normal model， and it was found that single neurotransmitter was in one of three states： increased， decreased， or normal expression. The simultaneous expression states of six neurotransmitters in the brain space were referred to as the expression pattern of multiple neurotransmitters. （2） A MySQL database was established to analyze the actual expression patterns of different neurotransmitters in the whole brain of patients with depression. （3） Factor analysis was conducted to further analyze the characteristic rules of 78 variables of neurotransmitters in the whole brain and 12 brain regions in depression patients. Results（1） The expression of single neurotransmitters in the whole brain and different brain regions of the total depression population showed one of three expression states （increased/decreased/normal）， being normal in the majority. The decreased and increased expression of 5-HT， ACh， DA， INH， EXC， and NE in the whole brain occurred in 6% and 25%， 31% and 17%， 36% and 9%， 15% and 31%， 32% and 14%， and 22% and 22%， respectively. （2） The antagonizing pairs of neurotransmitters （EXC/INH， DA/5-HT， and ACh/NE） showed significant antagonistic relationships in the whole brain and different brain regions， with a strong negative correlation between EXC and INH （P<0.01， |r| values ranging from 0.69 to 0.76）， a strong negative correlation between DA and 5-HT （P<0.01， |r| values ranging from 0.83 to 0.90）， and a moderate negative correlation between ACh and NE （P<0.01， with |r| values ranging from 0.56 to 0.66）. Meanwhile， non-antagonizing pairs of neurotransmitters in the whole brain and different brain regions also showed correlations， with DA/NE （P<0.01， |r| values ranging from 0.38 to 0.46） and NE/EXC （P<0.01， |r| values ranging from 0.56 to 0.61） showing weak and moderate negative correlations， respectively， and DA/EXC showing a weak positive correlation （P<0.01， |r| values ranging from 0.38 to 0.47）. （3） The six neurotransmitters in the 1 028 patients with depression presented a total of 170 expression patterns in the whole brain. The top 30 expression patterns were reported in this paper， with a cumulative rate of 60.60%， including patterns ① INH+/5-HT-/ACh+/DA+/NE-/EXC- （9.05%）， ② INH+/5-HT-/ACh↓/DA+/NE-/EXC- （4.57%）， and ③ INH+/5-HT-/ACh+/DA+/NE↓/EXC- （3.31%）. That is， the proportion of depression patients with normal levels of all the six neurotransmitters was 9.05%， and the patients with at least one neurotransmitter abnormality accounted for 91.95%. （4） The factor analysis extracted 22 common factors from 78 variables in the whole brain and different brain regions. These common factors showed the absolute values of loadings ranging from 0.32 to 0.86 and the eigenvalues （F） ranging from 1.03 to 13.43， with a cumulative contribution rate of 76.82%. The characteristic expression patterns included ① ACh_P3↓/ACh_W↓/ACh_C3↓/ACh_F3↓/ACh_O1↓/ACh_T5↓/ACh_F7↓/NE_P3↑/NE_W↑/NE_C3↑/NE_F3↑/NE_O1↑/NE_T5↑/NE_F7↑ （F=13.43， whole brain）， ② 5-HT_O2↑/DA_O2↓/5-HT_P4↑/DA_P4↓/5-HT_W↑/DA_W↓/5-HT_C4↑/DA_C4↓ （F=5.94）， and ③ EXC_F4↓/DA_F4↓/NE_F4↑/INH_F4↑/5-HT_F4↑/ACh_F4↓ （F=5.33）. ConclusionThe actual 170 expression patterns of 6 neurotransmitters in the whole brain of 1 028 depression patients indicate that depression is a heterogeneous disease with individualized characteristics. The 22 characteristic expression patterns in the whole brain and 12 brain regions verify the pathogenesis hypothesis of multi-neurotransmitters oscillation imbalance in brains of depression patients. In summary， this study provides new guidance for the etiology， diagnosis， and treatment of depression and establishes a methodological foundation for the effectiveness evaluation of individualized treatment of depression by traditional Chinese medicine based on the objective biological markers.

ObjectiveTo analyze the characteristic expression patterns of six neurotransmitters including 5-hydroxytryptamine （5-HT）， dopamine （DA）， acetylcholine （ACh）， norepinephrine （NE）， inhibitory neurotransmitter （INH）， and excitatory neurotransmitter （EXC） in the whole brain and different brain regions of depression patients by Search of Encephalo Telex （SET）， providing new ideas for the study of heterogeneous etiology of depression. Methods（1） A retrospective study was conducted on supra-slow signals of EEG fluctuations in 1 028 patients with depression. The SET system was used to obtain the expression information of six neurotransmitters in the whole brain and 12 brain regions： left frontal region （F3）， right frontal region （F4）， left central region （C3）， right central region （C4）， left parietal region （P3）， right parietal region （P4）， left occipital region （O1）， right occipital region （O2）， left anterior temporal region （F7）， right anterior temporal region （F8）， left posterior temporal region （T5）， and right posterior temporal region （T6）. The expression information of each neurotransmitter was compared with the normal model， and it was found that single neurotransmitter was in one of three states： increased， decreased， or normal expression. The simultaneous expression states of six neurotransmitters in the brain space were referred to as the expression pattern of multiple neurotransmitters. （2） A MySQL database was established to analyze the actual expression patterns of different neurotransmitters in the whole brain of patients with depression. （3） Factor analysis was conducted to further analyze the characteristic rules of 78 variables of neurotransmitters in the whole brain and 12 brain regions in depression patients. Results（1） The expression of single neurotransmitters in the whole brain and different brain regions of the total depression population showed one of three expression states （increased/decreased/normal）， being normal in the majority. The decreased and increased expression of 5-HT， ACh， DA， INH， EXC， and NE in the whole brain occurred in 6% and 25%， 31% and 17%， 36% and 9%， 15% and 31%， 32% and 14%， and 22% and 22%， respectively. （2） The antagonizing pairs of neurotransmitters （EXC/INH， DA/5-HT， and ACh/NE） showed significant antagonistic relationships in the whole brain and different brain regions， with a strong negative correlation between EXC and INH （P<0.01， |r| values ranging from 0.69 to 0.76）， a strong negative correlation between DA and 5-HT （P<0.01， |r| values ranging from 0.83 to 0.90）， and a moderate negative correlation between ACh and NE （P<0.01， with |r| values ranging from 0.56 to 0.66）. Meanwhile， non-antagonizing pairs of neurotransmitters in the whole brain and different brain regions also showed correlations， with DA/NE （P<0.01， |r| values ranging from 0.38 to 0.46） and NE/EXC （P<0.01， |r| values ranging from 0.56 to 0.61） showing weak and moderate negative correlations， respectively， and DA/EXC showing a weak positive correlation （P<0.01， |r| values ranging from 0.38 to 0.47）. （3） The six neurotransmitters in the 1 028 patients with depression presented a total of 170 expression patterns in the whole brain. The top 30 expression patterns were reported in this paper， with a cumulative rate of 60.60%， including patterns ① INH+/5-HT-/ACh+/DA+/NE-/EXC- （9.05%）， ② INH+/5-HT-/ACh↓/DA+/NE-/EXC- （4.57%）， and ③ INH+/5-HT-/ACh+/DA+/NE↓/EXC- （3.31%）. That is， the proportion of depression patients with normal levels of all the six neurotransmitters was 9.05%， and the patients with at least one neurotransmitter abnormality accounted for 91.95%. （4） The factor analysis extracted 22 common factors from 78 variables in the whole brain and different brain regions. These common factors showed the absolute values of loadings ranging from 0.32 to 0.86 and the eigenvalues （F） ranging from 1.03 to 13.43， with a cumulative contribution rate of 76.82%. The characteristic expression patterns included ① ACh_P3↓/ACh_W↓/ACh_C3↓/ACh_F3↓/ACh_O1↓/ACh_T5↓/ACh_F7↓/NE_P3↑/NE_W↑/NE_C3↑/NE_F3↑/NE_O1↑/NE_T5↑/NE_F7↑ （F=13.43， whole brain）， ② 5-HT_O2↑/DA_O2↓/5-HT_P4↑/DA_P4↓/5-HT_W↑/DA_W↓/5-HT_C4↑/DA_C4↓ （F=5.94）， and ③ EXC_F4↓/DA_F4↓/NE_F4↑/INH_F4↑/5-HT_F4↑/ACh_F4↓ （F=5.33）. ConclusionThe actual 170 expression patterns of 6 neurotransmitters in the whole brain of 1 028 depression patients indicate that depression is a heterogeneous disease with individualized characteristics. The 22 characteristic expression patterns in the whole brain and 12 brain regions verify the pathogenesis hypothesis of multi-neurotransmitters oscillation imbalance in brains of depression patients. In summary， this study provides new guidance for the etiology， diagnosis， and treatment of depression and establishes a methodological foundation for the effectiveness evaluation of individualized treatment of depression by traditional Chinese medicine based on the objective biological markers.

Purpose: The aim of this study was to investigate the feasibility of an intelligent handheld ultrasound (US) device for assisting non-expert general practitioners (GPs) in detecting carotid plaques (CPs) in community populations. Methods: This prospective parallel controlled trial recruited 111 consecutive community residents. All of them underwent examinations by non-expert GPs and specialist doctors using handheld US devices (setting A, setting B, and setting C). The results of setting C with specialist doctors were considered the gold standard. Carotid intima-media thickness (CIMT) and the features of CPs were measured and recorded. The diagnostic performance of GPs in distinguishing CPs was evaluated using a receiver operating characteristic curve. Inter-observer agreement was compared using the intragroup correlation coefficient (ICC). Questionnaires were completed to evaluate clinical benefits. Results: Among the 111 community residents, 80, 96, and 112 CPs were detected in settings A, B, and C, respectively. Setting B exhibited better diagnostic performance than setting A for detecting CPs (area under the curve, 0.856 vs. 0.749; P<0.01). Setting B had better consistency with setting C than setting A in CIMT measurement and the assessment of CPs (ICC, 0.731 to 0.923). Moreover, measurements in setting B required less time than the other two settings (44.59 seconds vs. 108.87 seconds vs. 126.13 seconds, both P<0.01). Conclusion Using an intelligent handheld US device, GPs can perform CP screening and achieve a diagnostic capability comparable to that of specialist doctors.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Purpose: The aim of this study was to investigate the feasibility of an intelligent handheld ultrasound (US) device for assisting non-expert general practitioners (GPs) in detecting carotid plaques (CPs) in community populations. Methods: This prospective parallel controlled trial recruited 111 consecutive community residents. All of them underwent examinations by non-expert GPs and specialist doctors using handheld US devices (setting A, setting B, and setting C). The results of setting C with specialist doctors were considered the gold standard. Carotid intima-media thickness (CIMT) and the features of CPs were measured and recorded. The diagnostic performance of GPs in distinguishing CPs was evaluated using a receiver operating characteristic curve. Inter-observer agreement was compared using the intragroup correlation coefficient (ICC). Questionnaires were completed to evaluate clinical benefits. Results: Among the 111 community residents, 80, 96, and 112 CPs were detected in settings A, B, and C, respectively. Setting B exhibited better diagnostic performance than setting A for detecting CPs (area under the curve, 0.856 vs. 0.749; P<0.01). Setting B had better consistency with setting C than setting A in CIMT measurement and the assessment of CPs (ICC, 0.731 to 0.923). Moreover, measurements in setting B required less time than the other two settings (44.59 seconds vs. 108.87 seconds vs. 126.13 seconds, both P<0.01). Conclusion Using an intelligent handheld US device, GPs can perform CP screening and achieve a diagnostic capability comparable to that of specialist doctors.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Purpose: The aim of this study was to investigate the feasibility of an intelligent handheld ultrasound (US) device for assisting non-expert general practitioners (GPs) in detecting carotid plaques (CPs) in community populations. Methods: This prospective parallel controlled trial recruited 111 consecutive community residents. All of them underwent examinations by non-expert GPs and specialist doctors using handheld US devices (setting A, setting B, and setting C). The results of setting C with specialist doctors were considered the gold standard. Carotid intima-media thickness (CIMT) and the features of CPs were measured and recorded. The diagnostic performance of GPs in distinguishing CPs was evaluated using a receiver operating characteristic curve. Inter-observer agreement was compared using the intragroup correlation coefficient (ICC). Questionnaires were completed to evaluate clinical benefits. Results: Among the 111 community residents, 80, 96, and 112 CPs were detected in settings A, B, and C, respectively. Setting B exhibited better diagnostic performance than setting A for detecting CPs (area under the curve, 0.856 vs. 0.749; P<0.01). Setting B had better consistency with setting C than setting A in CIMT measurement and the assessment of CPs (ICC, 0.731 to 0.923). Moreover, measurements in setting B required less time than the other two settings (44.59 seconds vs. 108.87 seconds vs. 126.13 seconds, both P<0.01). Conclusion Using an intelligent handheld US device, GPs can perform CP screening and achieve a diagnostic capability comparable to that of specialist doctors.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.