Objective:To develop an artificial intelligence (AI)-based platelet review strategy to identify abnormal platelet histograms with no significant difference between initial impedance platelet count (PLT-I) and PLT-F results.Methods:This study included 5 119 routine blood analysis in Nanfang Hospital of Southern Medical University and its Ganzhou branch from July 2023 and March 2024. Specimens exhibiting abnormal platelet histograms and an initial platelet count >40×10?/L underwent review using the fluorescent platelet count (PLT-F) channel. Consistency of the results was defined as a difference between impedance platelet count (PLT-I) and PLT-F less than ±20% of the PLT-F results. A deep learning model was developed using platelet and red blood cell histogram data from a training set of 3 807 specimens. The model′s diagnostic performance was evaluated on an independent external validation set ( n=805) using receiver operating characteristic (ROC) curve analysis. Changes in the number of reviewed samples and sample turnaround time were analyzed to assess its clinical utility. Results:The deep learning model based on platelet and red blood cell histograms achieved an area under the ROC curve (AUC) of 0.854 in the training set. At a cutoff value of 0.1, the sensitivity was 0.954 and specificity was 0.358. The model could reduce review by 16.80% (190/1 131). In the validation set, the AUC was 0.805, with a sensitivity of 0.955 and specificity of 0.307, corresponding to a reduction of 17.41% (47/270) in reviewed specimens.Conclusion:The platelet review prediction model developed based on deep learning technology can efficiently identify samples with consistent results before and after review, reducing unnecessary reviews and shortening specimen testing time, thereby improving the efficiency of platelet test.

Objective:To develop an artificial intelligence (AI)-based platelet review strategy to identify abnormal platelet histograms with no significant difference between initial impedance platelet count (PLT-I) and PLT-F results.Methods:This study included 5 119 routine blood analysis in Nanfang Hospital of Southern Medical University and its Ganzhou branch from July 2023 and March 2024. Specimens exhibiting abnormal platelet histograms and an initial platelet count >40×10?/L underwent review using the fluorescent platelet count (PLT-F) channel. Consistency of the results was defined as a difference between impedance platelet count (PLT-I) and PLT-F less than ±20% of the PLT-F results. A deep learning model was developed using platelet and red blood cell histogram data from a training set of 3 807 specimens. The model′s diagnostic performance was evaluated on an independent external validation set ( n=805) using receiver operating characteristic (ROC) curve analysis. Changes in the number of reviewed samples and sample turnaround time were analyzed to assess its clinical utility. Results:The deep learning model based on platelet and red blood cell histograms achieved an area under the ROC curve (AUC) of 0.854 in the training set. At a cutoff value of 0.1, the sensitivity was 0.954 and specificity was 0.358. The model could reduce review by 16.80% (190/1 131). In the validation set, the AUC was 0.805, with a sensitivity of 0.955 and specificity of 0.307, corresponding to a reduction of 17.41% (47/270) in reviewed specimens.Conclusion:The platelet review prediction model developed based on deep learning technology can efficiently identify samples with consistent results before and after review, reducing unnecessary reviews and shortening specimen testing time, thereby improving the efficiency of platelet test.

Objective: To study the effects and safety of Shixinyatong buccal tablets in the treatment of gastropyretic toothache (perico-ronitis). Methods: Randemized, double-blinded, double-imitated, parallel-controlled and multi-center clinical study was employed. 120 cases of gastropyretic toothache (pericoronitis) was enrolled in the experimental group( SBT group) and another 120 in control group(CBD group). Pericoronal pocket rinsing was performed for each case at the first visit, then the patients in SBT group were treated by Shixin buccal tablets(SBT) , 0. 6 g×2, 4/d and oral adiministration of the vehicle of cow-bezoare detoxicating tablets,0.3 g×3, 3/ d. The patients in CBD group were treated by oral adiministration of cow-bezoare detoxicating tablets ( SBD), 0. 3 g×3, 3/d and the vehicle of SBT, 0.6 g ×2, 4/d respectively. Pain, gingiva contagious tumefaction, pyorrhea of periocoronal pocket and limitation of mouth opening were scored by 0, 2, 4 and 6 as the major physical signs and symptoms(MAS); periocoronal flap and pocket, facial swelling, hot and foul breath, costipation, lymphadenectasis, thirsty and desire of cold drinks, fever by 0, 1,2 and 3 as the minor (MIS). Treatment was continued for 5 days and data were statistically analysed with SAS6. 12 software. Significant effectiveness was i-dentified by the decrease of total score of all the physical signs and symptoms(TS) ≥70% .effectiveness 30%～69% and ineffectiveness ≤29%. Routine examinations of blood, urine and stool, function of liver and kidney and electrocardiogram were conducted before and after treatment. Adverse events(AE) were observed. Results: 3 cases divorced from SBT group and 2 from CBD group. The demographic data and all the scores before treatment were not statistically different between groups (P>0.05). 3 and 5 days after treatment theTS, TSMA and TSMI were decreased(P= 0.000) in both groups, in SBT group decreased more than in CBD(P<0.001). Significant effectiveness ratio of SBT group was higher than that of CBD (P=0. 000). 5 days after treatment TS of MASs and the scores of each MAS in SBT group decreased more than in CBD( P<0.05). Vital signs were in normal range and not statisticaly different between groups(P>0.05). The clinical lab examinations showed no abnormal changes. Drug-related AE were observed in 3 cases, 1 with moderate AE in SBT group recovered after drug withdrawal, 2 with mild AE in CBD group recovered without aditional treatment. Conclusion; Shixinyatong buccal tablet is more effective in the treatment of gastropyretic toothache (pericoronitis) than cow-bezoare detoxicating tablets and with similar safety.

0.05). However,Simo Decoction can ameliorate the symptoms,such as epigastric pain,early satiety,etc.,better than Domperidone tablets(P

Objective:To investigate the clinical effects and main pharmacological actions of Pingantongluo Granules (Radix Paeoniae Alba, Rhizoma Gastrodiae, Radix Salviae Miltiorrhizae, Rhizoma Chuanxiong, Concha Haliotidis, etc.) for migraine with liver wind and blood stasis symptom. Methods: Randomized controlled trail, double blind and double dummy method were applied. Yuntongding Tablets was used as a control drug in clinical investigation and Routunding Tablets as a control drug in pharmacological experiment study. Results: The total effective rates of the treatment group and the control group were 95.0% and 83.3% for migraine and 80.0% and 61.6% for the liver wind and blood stasis symptom, respectively. Pinggantongluo Granules began to act on migraine in ( 11.75 ? 6.70 )h, and the control drug did in ( 18.30 ? 8.22 )h. There were a significant difference between two groups ( P