BACKGROUND: Delayed platelet engraftment is a common complication after umbilical cord blood transplantation (UCBT), and there is no standard therapy. Avatrombopag (AVA) is a second-generation thrombopoietin (TPO) receptor agonist (TPO-RA) that has shown efficacy in immune thrombocytopenia (ITP). However, few reports have focused on its efficacy in patients diagnosed with thrombocytopenia after allogeneic hematopoietic stem cell transplantation (allo-HSCT). METHODS: We conducted a retrospective study at the First Affiliated Hospital of the University of Science and Technology of China to evaluate the efficacy of AVA as a first-line TPO-RA in 65 patients after UCBT; these patients were compared with 118 historical controls. Response rates, platelet counts, megakaryocyte counts in bone marrow, bleeding events, adverse events and survival rates were evaluated in this study. Platelet reconstitution differences were compared between different medication groups. Multivariable analysis was used to explore the independent beneficial factors for platelet implantation. RESULTS: Fifty-two patients were given AVA within 30 days post-UCBT, and the treatment was continued for more than 7 days to promote platelet engraftment (AVA group); the other 13 patients were given AVA for secondary failure of platelet recovery (SFPR group). The median time to platelet engraftment was shorter in the AVA group than in the historical control group (32.5 days vs . 38.0 days, Z  = 2.095, P  = 0.036). Among the 52 patients in the AVA group, 46 achieved an overall response (OR) (88.5%), and the cumulative incidence of OR was 91.9%. Patients treated with AVA only had a greater 60-day cumulative incidence of platelet engraftment than patients treated with recombinant human thrombopoietin (rhTPO) only or rhTPO combined with AVA (95.2% vs . 84.5% vs . 80.6%, P  <0.001). Patients suffering from SFPR had a slightly better cumulative incidence of OR (100%, P  = 0.104). Patients who initiated AVA treatment within 14 days post-UCBT had a better 60-day cumulative incidence of platelet engraftment than did those who received AVA after 14 days post-UCBT (96.6% vs . 73.9%, P  = 0.003). CONCLUSION Compared with those in the historical control group, our results indicate that AVA could effectively promote platelet engraftment and recovery after UCBT, especially when used in the early period (≤14 days post-UCBT).
Humans ; Female ; Male ; Thrombocytopenia/etiology* ; Adult ; Retrospective Studies ; Cord Blood Stem Cell Transplantation/adverse effects* ; Middle Aged ; Adolescent ; Young Adult ; Thiazoles/adverse effects* ; Platelet Count ; Receptors, Thrombopoietin/agonists* ; Child ; Thiophenes

To address the challenges in blood cell recognition caused by diverse morphology, dense distribution, and the abundance of small target information, this paper proposes a blood cell detection algorithm - the "You Only Look Once" model based on hybrid mixing attention and deep over-parameters (HADO-YOLO). First, a hybrid attention mechanism is introduced into the backbone network to enhance the model's sensitivity to detailed features. Second, the standard convolution layers with downsampling in the neck network are replaced with deep over-parameterized convolutions to expand the receptive field and improve feature representation. Finally, the detection head is decoupled to enhance the model's robustness for detecting abnormal cells. Experimental results on the Blood Cell Counting Dataset (BCCD) demonstrate that the HADO-YOLO algorithm achieves a mean average precision of 90.2% and a precision of 93.8%, outperforming the baseline YOLO model. Compared with existing blood cell detection methods, the proposed algorithm achieves state-of-the-art detection performance. In conclusion, HADO-YOLO offers a more efficient and accurate solution for identifying various types of blood cells, providing valuable technical support for future clinical diagnostic applications.
Algorithms ; Humans ; Blood Cells/cytology* ; Blood Cell Count/methods* ; Neural Networks, Computer ; Deep Learning ; Detection Algorithms

This study used machine learning techniques combined with routine blood cell analysis parameters to build preliminary prediction models, helping differentiate patients with depression from healthy controls, or patients with anxiety. A multicenter study was performed by collecting blood cell analysis data of Beijing Chaoyang Hospital and the First Hospital of Hebei Medical University from 2020 to 2021. Machine learning techniques, including support vector machine, decision tree, naïve Bayes, random forest and multi-layer perceptron were explored to establish a prediction model of depression. The results showed that based on the blood cell analysis results of healthy controls and depression group, the accuracy of prediction model reached as high as 0.99, F1 was 0.975. Receiver operating characteristic curve area and average accuracy were 0.985 and 0.967, respectively. Platelet parameters contributed mostly to depression prediction model. While, to random forest differential diagnosis model based on the data from depression and anxiety groups, prediction accuracy reached 0.68 and AUC 0.622. Age, platelet parameters, and average volume of red blood cells contributed the most to the model. In conclusion, the study researched on the prediction model of depression by exploring blood cell analysis parameters, revealing that machine learning models were more objective in the evaluation of mental illness.
Humans ; Depression ; Bayes Theorem ; Machine Learning ; Support Vector Machine ; Blood Cell Count

OBJECTIVE: To evaluate the expression level of melatonin and its effects on immune function in aplastic anemia (AA) patients. METHODS: The enzyme-linked immunosorbent assay (ELISA) was used to detect the plasma levels of melatonin in AA patients, and the correlation between melatonin levels and laboratory indexs was analyzed. The activation, proliferation, and apoptosis of T cells from AA patients were analyzed by flow cytometry with or without melatonin in vitro. RESULTS: The plasma levels of melatonin in AA patients were significantly lower compared with healthy controls (HC) (12.23 pg/ml vs 20.04 pg/ml, P < 0.01), while the plasma melatonin levels of AA patients in remission group after immunosuppressive therapy (IST) were significantly higher than those in non-remission group (29.16 pg/ml vs 11.73 pg/ml, P =0.04). Moreover, the melatonin levels were positively correlated with platelets (r =0.49), the absolute reticulocyte count (r =0.45), and the percentage of neutrophils (r =0.43). Meanwhile, there was a negative correlation between melatonin levels and the percentages of lymphocytes (r =-0.45). The expressions of CD25 and CD69 in both CD4⁺ and CD8⁺ T cells from AA patients were remarkably inhibited by melatonin in vitro (all P < 0.05). When cultured with melatonin, the proliferation rates of both CD4⁺ and CD8⁺ T cells from AA patients were markedly suppressed (P =0.01 andP < 0.01). CONCLUSION The plasma levels of melatonin were decreased in AA patients, which might play an important role in the mechanism of immunological abnormalities. The hyperimmune status of AA patients could be partially ameliorated by melatonin in vitro.
Humans ; Anemia, Aplastic ; CD8-Positive T-Lymphocytes ; Melatonin ; Blood Cell Count

OBJECTIVE: To investigate the predictive value of complete blood count (CBC) and inflammation marker on the recurrence risk in children with Henoch-Schönlein purpura (HSP). METHODS: One hundred and thirty-three children with HSP admitted to Cangzhou Central Hospital from February 2017 to March 2019 were enrolled. The clinical data of the children were collected, at the time of admission CBC and C-reactive protein (CRP) were detected. After discharge, the children were followed up for 1 year, the clinical data of children with and without recurrence were compared, and multivariate logistic regression was used to analyze the risk factors affecting HSP recurrence. Receiver operating characteristic (ROC) curve should be drawn and the predictive value of CBC and CRP on HSP recurrence should be analyzed. RESULTS: In the follow-up of 133 children, 8 cases were lost and 39 cases recurred, with a recurrence rate of 31.20% (39/125). The age, skin rash duration, proportion of renal damage at the initial onset, percentage of neutrophils, percentage of lymphocytes, platelet count (PLT), mean platelet volume (MPV) and neutrophil/lymphocyte ratio (NLR), platelet/lymphocyte ratio (PLR), MPV/PLT ratio (MPR), and CRP level of patients with recurrence were statistically different from those without recurrence (P <0.05). Multivariate logistic regression analysis showed that long skin rash duration, renal damage at the initial onset, increased PLR, high PLT, increased MPV and elevated CRP level were independent risk factors for recurrence in children with HSP (P <0.05). The ROC curve analysis showed that the area under the curve (AUC) of the combination of the four blood and inflammation marker (PLT, MPV, PLR and CPR) in the early prediction of HSP recurrence was 0.898, which was higher than the initial renal damage (AUC=0.687) and persistent skin rash time (AUC=0.708), with a sensitivity of 84.62% and a specificity of 83.72%. CONCLUSION Observation of CBC and CPR can predict the risk of HSP recurrence early and guide early clinical intervention.
Humans ; Child ; IgA Vasculitis ; Blood Cell Count ; Inflammation ; C-Reactive Protein ; Lymphocytes ; Neutrophils ; Exanthema ; Retrospective Studies

INTRODUCTION: Complete blood count (CBC) and cell population data (CPD) are hematologic parameters used in several clinical scenarios including infection and neoplastic processes. In the setting of COVID-19 infection, there is relative paucity of data in their use as possible prognostic markers. OBJECTIVE: We aim to evaluate the utility of the baseline CBC and CPD as prognostic markers for in-hospital mortality among COVID-19 patients admitted in Philippine General Hospital from March 2020 to January 2022. METHODOLOGY: This is a case-control study. Expired patients served as cases, and recovered patients served as controls. Data from eligible patients including age, sex, admitting COVID diagnosis with severity, final disposition, baseline CBC and CPD results were collected from the hospital medical records and hematology section of the Department of Laboratories. Statistical analyses were done to determine the prognostic value of these parameters for in-hospital mortality. RESULTS: Among the different CBC and CPD parameters, the study shows total white blood cell (WBC) count, absolute neutrophil count (ANC), absolute eosinophil count (AEC), and neutrophil-lymphocyte ratio (NLR) were statistically significant predictors for in-hospital mortality. For total WBC count, at a cut off 9.9 x 10 9 /L, the sensitivity and specificity is 70.9% and 66.2%, respectively. For ANC, at a cut off of 7.3 x 10 9 /L, the specificity is 76.4% and the specificity is 68.2%. At a cut off of 7.62, the NLR shows a sensitivity of 76.4% and specificity of 70.1%. For AEC, at a cut off of 0.006 x 10 9 /L, the sensitivity is 53.3% and the specificity is 87.3%. AEC predicts towards the direction of survival rather than to the direction of in-hospital mortality. CONCLUSION The total WBC count, ANC, and NLR were statistically significant predictors for in-hospital mortality, while AEC predicts towards the direction of survival. The sensitivities and specificities of the cut off for these parameters were less than ideal. Correlation with clinical and other laboratory parameters is still recommended. For future studies, the authors recommend monitoring CBC and CPD parameters at different time points during the patients’ hospital course.
COVID-19 ; hematology ; blood cell count ; complete blood count ; prognosis

This study used machine learning techniques combined with routine blood cell analysis parameters to build preliminary prediction models, helping differentiate patients with depression from healthy controls, or patients with anxiety. A multicenter study was performed by collecting blood cell analysis data of Beijing Chaoyang Hospital and the First Hospital of Hebei Medical University from 2020 to 2021. Machine learning techniques, including support vector machine, decision tree, naïve Bayes, random forest and multi-layer perceptron were explored to establish a prediction model of depression. The results showed that based on the blood cell analysis results of healthy controls and depression group, the accuracy of prediction model reached as high as 0.99, F1 was 0.975. Receiver operating characteristic curve area and average accuracy were 0.985 and 0.967, respectively. Platelet parameters contributed mostly to depression prediction model. While, to random forest differential diagnosis model based on the data from depression and anxiety groups, prediction accuracy reached 0.68 and AUC 0.622. Age, platelet parameters, and average volume of red blood cells contributed the most to the model. In conclusion, the study researched on the prediction model of depression by exploring blood cell analysis parameters, revealing that machine learning models were more objective in the evaluation of mental illness.
Humans ; Depression ; Bayes Theorem ; Machine Learning ; Support Vector Machine ; Blood Cell Count

Background and Objectives: Early detection of ovarian neoplasms confer a better outcome and prognosis for patients. Although newer diagnostic modalities have been recently developed, the availability and accessibility of complete blood count parameters specifically, neutrophil-lymphocyte ratio (NLR) and platelet-lymphocyte ratio (PLR) make it a convenient and cost-effective marker to aid as a pre-operative predictor of epithelial ovarian neoplasms. We aim to determine the significance and relationship of preoperative NLR and PLR in predicting a diagnosis of malignant surface epithelial ovarian tumor. Methodology: We gathered surgical pathology reports and complete blood count parameters of service patients with benign and malignant surface epithelial ovarian neoplasms. Diagnostic accuracy of NLR and PLR was determined by using receiver operating curve (ROC) plots. Optimal cutoff points were set using the Youden index. Results: We have included 351 cases of ovarian surface epithelial neoplasms, 209 of which were benign and 142 of which were malignant. The ROC curve for PLR had an area under curve (AUC) of 0.6629 [0.6043, 0.7215]. The optimal cut-off point of was set at 195.99 with the maximal Youden index of 0.295 [9.193, 0.396]. The corresponding sensitivity of this test to determine malignancy at this point was 56.5% [47.8, 64.6] while the specificity was at 73.2% [66.7, 79.1]. The ROC curve for NLR had an AUC of 0.6616 [0.6051, 0.7180]. The optimal cut-off point of was set at 2.60 with the maximal Youden index of 0.316 [0.219, 0.413]. The corresponding sensitivity of this test to determine malignancy at this point was 76.1% [68.2, 82.8] while the specificity was at 55.5% [48.5, 62.4]. Conclusion The utility of CBC parameters such as PLR and NLR are cost-effective tools which may have some diagnostic value but, they cannot be used as a stand-alone predictor of malignancy and must be correlated with other clinical, laboratory and radiologic studies.
Ovarian Neoplasms ; Blood Cell Count ; Lymphocytes ; Neutrophils ; Blood Platelets

BACKGROUND: Lung cancer is the leading cause of cancer-related death, of which non-small cell lung cancer (NSCLC) is the most common type. Immune checkpoint inhibitors (ICIs) have now become one of the main treatments for advanced NSCLC. This paper retrospectively investigated the effect of peripheral blood inflammatory indexes on the efficacy of immunotherapy and survival of patients with advanced non-small cell lung cancer, in order to find strategies to guide immunotherapy in NSCLC. METHODS: Patients with advanced non-small cell lung cancer who were hospitalized in The Affiliated Cancer Hospital of Nanjing Medical University from October 2018 to August 2019 were selected to receive anti-PD-1 (pembrolizumab, sintilimab or toripalimab) monotherapy or combination regimens. And were followed up until 10 December 2020, and the efficacy was evaluated according to RECIST1.1 criteria. Progression-free survival (PFS) and overall survival (OS) were followed up for survival analysis. A clinical prediction model was constructed to analyze the predictive value of neutrophil-to-lymphocyte ratio (NLR) based on NLR data at three different time points: before treatment, 6 weeks after treatment and 12 weeks after treatment (0w, 6w and 12w), and the accuracy of the model was verified. RESULTS: 173 patients were finally included, all of whom received the above treatment regimen, were followed up for a median of 19.7 months. The objective response rate (ORR) was 27.7% (48/173), the disease control rate (DCR) was 89.6% (155/173), the median PFS was 8.3 months (7.491-9.109) and the median OS was 15.5 months (14.087-16.913). The chi-square test and logistic multi-factor analysis showed that NLR6w was associated with ORR and NLR12w was associated with ORR and DCR. Further Cox regression analysis showed that NLR6w and NLR12w affected PFS and NLR0w, NLR6w and NLR12w were associated with OS. CONCLUSIONS In patients with advanced non-small cell lung cancer, NLR values at different time points are valid predictors of response to immunotherapy, and NLR <3 is often associated with a good prognosis.
Aged ; Antibodies, Monoclonal, Humanized/therapeutic use* ; Antineoplastic Agents, Immunological/therapeutic use* ; Biomarkers/blood* ; Carcinoma, Non-Small-Cell Lung/pathology* ; Female ; Humans ; Immunotherapy/methods* ; Inflammation/blood* ; Leukocyte Count ; Lung Neoplasms/pathology* ; Lymphocytes ; Male ; Middle Aged ; Neutrophils ; Predictive Value of Tests ; Prognosis ; Retrospective Studies ; Survival Analysis ; Treatment Outcome

OBJECTIVE: To identify the key biochemical indicators that affect the clinical type and outcomes of COVID-19 patients and explore the application of neutrophil/lymphocyte ratio (NLR) in COVID-19. METHODS: Ninety-three patients with confirmed diagnosis of COVID-19 admitted in Ezhou Central Hospital from February to April in 2020 were analyzed. Among them, 43 patients were selected from Intensive Care Unit (ICU) with the diagnosis of critical type of COVID-19, and 50 cases of common type were selected from the Department of Respiratory Medicine. The baseline data, blood routine test and biochemical indexes of the patients were collected on the first day of admission. NLRs of the patients were calculated, and COX survival analysis according to the NLR 4-category method was performed. The patients' outcomes were analyzed with receiver operating curves (ROCs). The patients were divided into two groups according to NLR cutoff value for comparison of the biochemical indexes. Based on the patients' outcomes, NLR cutoff value classification and clinical classification, multiple binary logistics regression was performed to screen the key variables and explore their significance in COVID-19. RESULTS: The NLR four-category method was not applicable for prognostic evaluation of the patients. The cut-off value of NLR for predict the prognosis of COVID-19 was 11.26, with a sensitivity of 0.903 and a specificity of 0.839; the laboratory indicators of the patients with NLR < 11.26 were similar to those in patients of the common type; the indicators were also similar between patients with NLR≥11.26 and those with critical type COVID-19. NLR, WBC, NEUT, PCT, DD, BUN, TNI, BNP, and LDH had significant effects on the clinical classification and outcome of the patients ( < 0.05); Cr, Ca, PH, and Lac had greater impact on the outcome of the patients ( < 0.05), while Na, PCO had greater impact on the clinical classification of the patients ( < 0.05). CONCLUSIONS NLR can be used as an important reference for clinical classification, prognostic assessment, and biochemical abnormalities of COVID-19. Patients of critical type more frequently have bacterial infection with more serious inflammatory reactions, severer heart, lung and kidney damages, and much higher levels of DD and LDH than those of the common type. NLR, NEUT, DD, TNI, BNP, LDH, Ca, PCT, PH, and Lac have obvious influence on the prognosis of COVID-19 and should be observed dynamically.
Betacoronavirus ; Blood Cell Count ; standards ; Coronavirus Infections ; blood ; diagnosis ; physiopathology ; Humans ; Lymphocytes ; cytology ; Neutrophils ; cytology ; Pandemics ; Pneumonia, Viral ; blood ; diagnosis ; physiopathology ; Prognosis ; ROC Curve ; Retrospective Studies ; Severity of Illness Index