The diagnosis of hematological disorders is currently established from the combined results of different tests, including those assessing morphology (M), immunophenotype (I), cytogenetics (C), and molecular biology (M) (collectively known as the MICM classification). In this workflow, most of the results are interpreted manually (i.e., by a human, without automation), which is expertise-dependent, labor-intensive, time-consuming, and with inherent interobserver variability. Also, with advances in instruments and technologies, the data is gaining higher dimensionality and throughput, making additional challenges for manual analysis. Recently, artificial intelligence (AI) has emerged as a promising tool in clinical hematology to ensure timely diagnosis, precise risk stratification, and treatment success. In this review, we summarize the current advances, limitations, and challenges of AI models and raise potential strategies for improving their performance in each sector of the MICM pipeline. Finally, we share perspectives, highlight future directions, and call for extensive interdisciplinary cooperation to perfect AI with wise human-level strategies and promote its integration into the clinical workflow.

High mobility group box 1 (HMGB1), when released extracellularly, plays a pivotal role in the development of spinal cord synapses and exacerbates autoimmune diseases within the central nervous system. In experimental autoimmune encephalomyelitis (EAE), a condition that models multiple sclerosis, the levels of extracellular HMGB1 and interleukin-33 (IL-33) have been found to be inversely correlated. However, the mechanism by which IL-33 deficiency enhances HMGB1 release during EAE remains elusive. Our study elucidates a potential signaling pathway whereby the absence of IL-33 leads to increased binding of P300/CBP-associated factor with HMGB1 in the nuclei of astrocytes, upregulating HMGB1 acetylation and promoting its release from astrocyte nuclei in the spinal cord of EAE mice. Conversely, the addition of IL-33 counteracts the TNF-α-induced increase in HMGB1 and acetylated HMGB1 levels in primary astrocytes. These findings underscore the potential of IL-33-associated signaling pathways as a therapeutic target for EAE treatment.
Animals ; Encephalomyelitis, Autoimmune, Experimental/metabolism* ; Astrocytes/metabolism* ; Interleukin-33/metabolism* ; HMGB1 Protein/metabolism* ; Acetylation ; Mice, Knockout ; Mice, Inbred C57BL ; p300-CBP Transcription Factors/metabolism* ; Mice ; Spinal Cord/metabolism* ; Cells, Cultured ; Female ; Signal Transduction

Objective This study aimed to observe the outcomes of iRoot BP Plus full pulpotomy in primary molars with partial irreversible pulpitis retrospectively.Methods Collect 102 cases of primary molars with partial irreversible pulpitis undergoing iRoot BP Plus full pulpotomy from January 2019 to August 2023,with a follow-up period of 24-47 months.Based on the presence of irreversible pulpitis symptoms before surgery,the included cases will be divided into asymptomatic group(n=53)and symptomatic group(n=49).Observe the clinical and imaging success rates of both groups.Results Clinical success rates were 96.2%and 97.9%in asymptomatic and symptomatic groups,and ra-diographic success rates were 96.2%and 93.9%respec-tively.Conclusion iRoot BP Plus full pulpotomy can be used for the treatment of primary molars with partial irreversible pulpitis under an enhanced pulpotomy protocol.

Preserving the sustained vitality of dental pulp,maintaining the periapical tissues in a healthy state and implementing min-imally invasive therapies are key themes within the development of contemporary endodontics.The research of irreversible pulpitis is of great importance within endodontics.The application and investigation of vital pulp therapy(VPT)in the field of irreversible pulpitis is expected to facilitate the precision and minimally invasive process in diagnosis and treatment of pulpitis.This review article focuses on the application of vital pulp therapy in the diagnosis and treatment of irreversible pulpitis as well as the challenges.

Objective To establish a novel real-time quality control method for rapidly identifying the random error of sodium ion con-centration in serum using an artificial intelligence voting algorithm,and evaluate the relevant effectiveness of the model established on this basis.Methods A total of 144 754 test results of serum sodium ion rom the inpatients measured by Beckman AU5400 biochemis-try analyzer from January to May 2021 were obtained retrospectively from laboratory information system of the Department of Clinical La-boratory,Nanjing Drum Tower Hospital,and all the data were used as unbiased data for the current study.The random errors were arti-ficially introduced to generate the corresponding biased data set.Subsequently,the voting algorithm-based internal quality control model(ViQC)was established using the principles of the voting algorithm.The ViQC model and five classical PBRTQC(patient-based real-time quality control)algorithms were performed direct to each biased data.The analytical performance of the ViQC model was evaluated by using classification model criteria.The trimmed average number of patient samples until error detection(tANPed)was used to com-pare the clinical detection efficacy of the ViQC model with those of the five classical algorithms,and the error detection curves were plotted.Results Compare with all the classical algorithms,the ViQC model showed a false positive rate below 0.002 and achieved ac-curacy above 0.951 in detecting all the deviations.When the error factors were 1.5,2.5,and 3.0,the false positive rate of the ViQC model was zero.When the error factor was 2.5,its accuracy reached 0.979.Compared to the five classical PBRTQC algorithms,the ViQC model reduced the overall average tANPed by up to 34％and showed higher sensitivity for error detection.In addition,the ViQC model demonstrated the area under the ROC curve was as high as 0.989 at TEa on the test set,but the value of tANPed wasonly five.Conclusion We successfully established a real-time quality control model for the data of patients based on artificial intelligence algo-rithms,and its efficacy of clinical detection was superior to the traditional PBRTQC algorithms.

Objective:To investigate the value of BRAF V600E and multigene detection and stratified application for the diagnosis of thyroid nodules.Methods:A total of 1 117 patients with thyroid nodules resection at Nanjing Gulou Hospital from December 2020 to July 2022 were enrolled in the study. Fine needle aspiration (FNA) and core biopsy samplings were performed for cytopathologic examination and genetic testings; the findings were combined with BSRTC classification. The diagnostic performance of BRAF V600E and multigene detection were compared.Results:Among the 1, 117 patients who underwent thyroid nodules resection, 285 were male and 832 were female, with a median age of 46 years (range: 24-76 years). Postoperative histopathologic examination confirmed 1 040 cases of thyroid cancer and 77 cases of benign nodules. The sensitivity (87.0% vs. 80.8%, P<0.01) and diagnostic accuracy (87.9% vs. 82.1%, P<0.01) of multigene detection were significantly higher than those of BRAF V600E detection. The result of multigene detection showed that BRAF V600E mutation was the most common finding, followed by CCDC6-RET (E1-E12) fusion, ETV6-NTRK3 fusion, and KRAS mutation. Multigene detection had a higher sensitivity (81.9% vs. 72.8%, P<0.01) and lower cancer risk in wild-type (47.6% vs. 57.7%, P=0.069) than BRAF V600E detection in BSRTCⅠ-Ⅴ lesions. Compared with BRAF V600E detection, multigene had no significant difference of sensitivity in BSRTC Ⅰ lesions, but significantly higher sensitivity (86.3% vs 74.0%, P<0.01) in BSRTC Ⅲ lesions. Conclusions:Genetic detection can be used as an effective tool for the diagnosis of thyroid nodules. A stratified application of molecular markers in the diagnosis of thyroid nodules is proposed. Combined with FNA, single gene or multigene detection both can effectively assist in the diagnosis of thyroid nodules. Moreover, multigene detection is superior to single gene detection. For BSRTC Ⅲ lesion with wild-type BRAF, multigene detection can be considered with a repeated FNA.

Objective To compare the imaging quality and use convenience between hard and flexible coils,and to analyze the applicability of the two coils in clinical work.Methods Patients who underwent MRI examination of the knee joint were divided into 2 groups,group A using a hard coil and group B using a flexible coil.Differences in image signal-to-noise ratio(SNR),subjective scores,exami-nation times,and uniformity were compared between the two groups.Independent samples t-test was used and P＜0.05 was consid-ered significant.Results There were no significant statistical differences in image SNR and subjective scores between the two groups.The examination time was shorter in group A,the difference was statistically significant(P＜0.05).Image uniformity was better in group B.Conclusion The imaging effect of hard coil and flexible coil in MRI examination of the knee joint is consistent,and the examination time is shorter,which is more conducive to clinical use.

Objective:To construct the evaluation index system of core competence of extracorporeal membrane oxygenation (ECMO) specialist nurses.Methods:Through literature search and analysis, an entry pool of the core competence evaluation index system for ECMO specialist nurses was initially formed, and 20 medical and nursing experts in acute and critical care and cardiovascular fields were selected for two rounds of correspondence from September to November 2022. According to experts' opinions, the evaluation indexes of core competence of ECMO specialist nurses were modified, and the analytic hierarchy process determined the weights of indexes at all levels.Results:A total of 20 questionnaires were sent out and 20 valid questionnaires were collected during each of the two rounds of expert correspondence consultation, with effective recovery rates of 100.00%. The expert authority coefficient of the second round was 0.86, and Kendall's harmony coefficient was 0.31 ( P<0.01). Finally, the evaluation index system of core competence of ECMO specialist nurses included five primary indexes (clinical professional ability, communication and collaboration ability, nursing management ability, critical thinking ability, and professional development ability), 15 secondary indexes, and 53 tertiary indexes. Conclusions:The evaluation index system of core competence of ECMO specialist nurses constructed in this study is scientific and practical, providing a reference for evaluating ECMO specialist nurses' core competence.

Background and objective Invasive mucinous adenocarcinoma(IMA)was a rare and specific type of lung adenocarcinoma,which was often characterized by fewer lymphatic metastases.Therefore,it was difficult to evaluate the prognosis of these tumors based on the existing tumor-node-metastasis(TNM)staging.So,this study aimed to develop Nomo-grams to predict outcomes of patients with pathologic N0 in resected IMA.Methods According to the inclusion criteria and exclusion criteria,IMA patients with pathologic N0 in The Affiliated Lihuili Hospital of Ningbo University(training cohort,n=78)and Ningbo No.2 Hospital(validation cohort,n=66)were reviewed between July 2012 and May 2017.The prognostic value of the clinicopathological features in the training cohort was analyzed and prognostic prediction models were established,and the performances of models were evaluated.Finally,the validation cohort data was put in for external validation.Results Univariate analysis showed that pneumonic type,larger tumor size,mixed mucinous/non-mucinous component,and higher overall stage were significant influence factors of 5-year progression-free survival(PFS)and overall survival(OS).Multivariate analysis further indicated that type of imaging,tumor size,mucinous component were the independent prognostic factors for poor 5-year PFS and OS.Moreover,the 5-year PFS and OS rates were 62.82％and 75.64％,respectively.In subgroups,the sur-vival analysis also showed that the pneumonic type and mixed mucinous/non-mucinous patients had significantly poorer 5-year PFS and OS compared with solitary type and pure mucinous patients,respectively.The C-index of Nomograms with 5-year PFS and OS were 0.815(95％CI:0.741-0.889)and 0.767(95％CI:0.669-0.865).The calibration curve and decision curve analysis(DCA)of both models showed good predictive performances in both cohorts.Conclusion The Nomograms based on clinicopathological characteristics in a certain extent,can be used as an effective prognostic tool for patients with pathologic N0 after IMA resection.

OBJECTIVE To study the ameliorative effect and potential mechanism of curcumin on diabetes model rats with depression based on cAMP response element binding protein （CREB）/brain-derived neurotrophic factor （BDNF） signaling pathway. METHODS The diabetes model rat with depression was established by high fat and high sugar diet+intraperitoneal injection of streptozotocin+chronic unpredictable stress-induced depression. The successfully modeled rats were randomly divided into model group， positive control group （0.18 g/kg metformin and 1.8 mg/kg fluoxetine， gavage）， curcumin low-dose and high-dose groups （30， 60 mg/kg， gavage） and curcumin high-dose+CREB inhibitor group [60 mg/kg curcumin （gavage）+5 mg/kg CREB inhibitor 666-15 （intraperitoneal injection）]， with 12 rats in each group. Another 12 healthy rats were selected as the normal group. Each group was given a corresponding intervention for 4 weeks， the fasting blood glucose level of rats was detected， and the depression of rats was assessed. The levels of corticosterone （CORT） and inflammatory factors [tumor necrosis factor-α （TNF-α）， interleukin- 1β （IL-1β）， IL-6] in serum， and the levels of norepinephrine （NE） and 5-hydroxytryptamine （5-HT） in hippocampal tissue were determined. The pathological changes and neuronal apoptosis were observed in the hippocampal tissue of rats in each group； the expression levels of CREB， BDNF mRNA and protein in hippocampal tissue were detected. RESULTS Compared with the normal group， the hippocampal tissue of rats in the model group was severely damaged， and neurons were scattered， while the fasting blood glucose， the forced swimming immobility time， the tail suspension immobility time， serum levels of CORT， TNF-α， IL-1β and IL-6， and neuron apoptosis indexes were all increased or prolonged significantly （P＜0.05）. The levels of NE and 5-HT， the number of surviving neurons， and the expression levels of CREB and BDNF mRNA and protein in hippocampal tissue were decreased significantly （P＜0.05）. Compared with the 的model group， the damage to hippocampal tissue was relieved in the positive control group and curcumin groups， while the above indexes were improved significantly （P＜0.05）. The improvement effect of curcumin high-dose group was better than that of curcumin low-dose group （P＜0.05）. CREB inhibitor could significantly reverse the ameliorative effect of high-dose curcumin on the model rats （P＜0.05）. CONCLUSIONS Curcumin can improve the depression of diabetes model rats with depression， and relieve neuronal damage and inflammatory response， the mechanism of which may be associated with activating CREB/BDNF signaling pathway.