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 analyze the acupoint selection law of acupuncture and moxibustion for postherpetic neuralgia(PHN)with R language data mining technology.Methods The clinical research literature on acupuncture and moxibustion treatment of PHN included in CNKI,Wanfang Data,VIP and CBM from January 1,2010 to July 1,2023 was retrieved,and the database was established by Excel 2016.R language was used to statistically analyze the frequency of acupoint usage,meridians,locations,specific acupoints,etc.Through association rule analysis and clustering analysis,the characteristics and law of acupoint selection for acupuncture and moxibustion treatment of PHN were obtained.Results A total of 198 articles were included,including 83 acupoints,with a total frequency of 714 times.The high-frequency acupoints include Ashi acupoint,Jiaji acupoint and Yanglingquan.The commonly used meridians were gallbladder meridian,spleen meridian and large intestine meridiam.The acupoints were mostly in the upper and lower limbs,with the Wushu acupoints,Yuan acupoints and Xiahe acupoints being the most common.The core acupoint was Ashi acupoint,Jiaji acupoint,Hegu,Quchi,and 9 sets of association rules and 5 effective clusters were obtained.Conclusion The most commonly used acupoints for acupuncture and moxibustion treatment of PHN are Ashi acupoint,Jiaji acupoint,Hegu and Quchi,which mainly follow the principle of combining local acupoint selection with distal acupoint selection.

Objective To analyze the acupoint selection law of acupuncture and moxibustion for postherpetic neuralgia(PHN)with R language data mining technology.Methods The clinical research literature on acupuncture and moxibustion treatment of PHN included in CNKI,Wanfang Data,VIP and CBM from January 1,2010 to July 1,2023 was retrieved,and the database was established by Excel 2016.R language was used to statistically analyze the frequency of acupoint usage,meridians,locations,specific acupoints,etc.Through association rule analysis and clustering analysis,the characteristics and law of acupoint selection for acupuncture and moxibustion treatment of PHN were obtained.Results A total of 198 articles were included,including 83 acupoints,with a total frequency of 714 times.The high-frequency acupoints include Ashi acupoint,Jiaji acupoint and Yanglingquan.The commonly used meridians were gallbladder meridian,spleen meridian and large intestine meridiam.The acupoints were mostly in the upper and lower limbs,with the Wushu acupoints,Yuan acupoints and Xiahe acupoints being the most common.The core acupoint was Ashi acupoint,Jiaji acupoint,Hegu,Quchi,and 9 sets of association rules and 5 effective clusters were obtained.Conclusion The most commonly used acupoints for acupuncture and moxibustion treatment of PHN are Ashi acupoint,Jiaji acupoint,Hegu and Quchi,which mainly follow the principle of combining local acupoint selection with distal acupoint selection.

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.

In the context of "New Era" and "New Medicine", the teaching team of laboratory diagnostics proposed a new teaching method of PDCA (Plan, Do, Check, Action) cycle to innovate the instructional design and implementation of laboratory diagnosis on the base of traditional teaching model. Through optimizing the curriculum system, integrating superior resources, taking full advantage of information technology, mobilizing the virtual simulation laboratory, implementing moral education and multiple comprehensive evaluation results, the self-learning enthusiasm, innovation and development ability of students were improved significantly, accompanied with high humanistic care spirit. Moreover, the enthusiasm of participating in scientific research activities and professional competitions was enhanced obviously. Therefore, we believe that the PDCA cycle, with notable successes, deserves high promotion value and wide application.

Objective:To conduct a scoping review of the application of mobile health applications (MHA) in the care of patients with colorectal cancer, summarizing the development process, the functions achieved, as well as the evaluation metrics, to provide references for MHA practice and related research.Methods:Following the scoping review framework, a comprehensive search was conducted across both domestic and international databases, including the China Biomedical Literature Database, Wanfang Database, China National Knowledge Infrastructure (CNKI), VIP Database, Cochrane Library, PubMed, Embase, CINAHL, Web of Science, and Scopus. The search period was from the database inception to February, 2024.Results:A total of 16 studies were included. The development of MHA involved multiple methods including literature reviews, qualitative interviews, consultations with multidisciplinary teams, and guidance from theoretical models. The functions of MHA include health education, peer support, guided feedback, monitoring, and reminder features. Evaluation metrics for MHA comprise usability, adherence, and effectiveness.Conclusions:MHA has demonstrated positive effects in enhancing patients' knowledge and alleviating symptoms such as fatigue and vomiting in colorectal cancer patients. However, it is still in its early stages, and further high-quality studies are needed to scientifically develop MHA that meets patients' needs.

ObjectiveTo study the brain network during balance control tasks in older adults. MethodsFrom January to April, 2022, 22 healthy young adults and 20 healthy older adults were recruited from the Fifth Affiliated Hospital of Guangzhou Medical University and communities. They were asked to finish standing tasks on the plantar pressure plate with eyes opening and closing, while the functional connectivities (FC) of prefrontal cortex (PFC) and primary motor cortex (PMC) were measured with functional near-infrared spectroscopy. ResultsCompared with the young adults, the area of the ellipse (Z = -2.884, P < 0.01) and the maximum swing (Z = -2.481, P < 0.05) increased in the older adults as eyes closing. During the standing task, the intra-FC of left (t = 2.978, P < 0.01) and right (Z = -3.123, P < 0.01) PFC decreased in the older adults, and the inter-FC of right PMC to left PFC (t = 2.087, P < 0.05) and right PFC to left PFC (t = 3.471, P < 0.001) decreased, too. ConclusionThe FC of PFC decreased in healthy older adults during balance control tasks, which may be a indicator for aging brain.

Digital therapeutics(DTs)refers to a non-drug intervention method that uses electronic devices such as computers,smartphones,and wearable devices to evaluate and intervene through software programs and Internet technologies.It has been confirmed that there is a good therapeutic effect on a variety of mental disorders.Digital therapeutics can improve the insomnia problems of insomniacs,enhance the attention and work memory ability of patients with attention deficit hyperactivity disorder,and can also alleviate symptoms such as depression and anxiety disorder.Digital therapy will develop towards personalized treatment,popular treatment,fragmented treatment,and entertainment treatment in the future and have broad development prospects.

Objective To explore the effect and mechanism of miR-581 on the autophagy of ovarian cancer SKOV3 cells. Methods miR-581 mimics and miR-581 NC were transfected into SKOV3 cells, and the transfection efficiency was detected by qRT-PCR. After successful transfection, Western blot was used to detect autophagy-related proteins expression in SKOV3 cells. TargetScanHuman database predicted miR-581 target genes, and Western blot verified the role of miR-581 and target genes. Results Overexpression of miR-581 significantly inhibited the expression of autophagy-related proteins LC3 Ⅱ and Beclin1 (P < 0.01); miR-581 negatively regulated FOXO1 expression (P < 0.01) and FOXO1 promoted autophagy of SKOV3 cells (P < 0.01). Conclusion miR-581 affects the autophagy of ovarian cancer SKOV3 cells by regulating the expression of FOXO1.

Objective:To compare the effects between improved catheter extubation method and the traditional one on urination pain, urinary retention, first urination time and first urination volume, and to evaluate the advantage of the improved method.Methods:144 patients with indwelling catheters after operation in our department were randomly divided into observation group and control group, with 72 cases in each group. The control group returned to the ward after surgery and began to clamp the urinary tube to train the bladder function, the catheter was removed by traditional method. Observation group: urination reflex was evaluated before extubation, according to more than 250 ml urine in the urine bag. Pumping the saline of the gas bag and injecting back 0.5ml to keep the wall of the bag smooth, eventually the catheter was excreted when urinating. Urethral pain, urinary retention, first micturition time and first micturition volume of two groups were analyzed.Results:Urethral pain, urinary retention, first micturition time in observation group and control group were 1.47±1.48, (20.44±12.98) min, 95.8% (69/72) and 3.11±1.98, (28.03±27.00) min, 83.3% (60/72), respectively, and the difference between the two groups was statistically significant ( t value was -5.644, -2.148, χ2 value was 6.628, all P<0.05). The first micturition volume in observation group and control group were (258.6±41.57) ml and (248.14±48.82) ml, respectively, and there was no significant difference between the two groups ( t value was 1.377, P>0.05). Conclusion:The improved catheter extubation method could significantly reduce the urethral pain, shorten the time of the first urination, and improve the success rate of self-urination, which of clinical promotion.