Objective: To compare the effects of seasonal autoregressive integrated moving average (SARIMA) , seasonal autoregressive integrated moving average with exogenous regressors (SARIMAX) and long short-term memory neural network (LSTM) models in predicting the incidence of hand, foot, and mouth disease (HFMD). Methods: Monthly incidence data of HFMD in Kunming City from 2010 to 2019 were collected. SARIMA, SARIMAX and LSTM models were established using the monthly incidence of HFMD from 2010 to 2018 to predict the monthly incidence of HFMD from January to December 2019. The prediction performance of the three models was compared using mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). The optimal prediction model was selected based on the principle of minimizing MSE, RMSE, MAE and MAPE. Results: The HFMD cases were reported every month in Kunming City from 2010 to 2019, with the incidence fluctuating between 188.27/105 and 363.15/105. The disease exhibited a biennial high-incidence bimodal distribution. Among the four evaluation indicators for the training and testing sets, the LSTM model had the smaller values: MSE was 63.182 and 102.745, RMSE was 7.949 and 10.136, MAE was 6.535 and 7.620, and MAPE was 46.726% and 31.138%. The LSTM model performed the better, followed by the SARIMA model, while the SARIMAX model had the relatively poorest performance. Conclusion The LSTM model outperforms the SARIMA and SARIMAX models in predicting the incidence of HFMD.

Background: Psychological test reports are essential in assessing intellectual functioning, aiding in diagnosing and treating intellectual disability (ID) and attention-deficit/ hyperactivity disorder (ADHD). However, these reports can have several problems because they are diverse, unstructured, subjective, and involve human errors. Additionally, physicians often do not read the entire report, and the number of reports is lower than that of diagnoses. Methods: We developed explainable predictive models for classifying IDs and ADHDs based on written reports to address these issues. The reports of 1,475 patients with IDs and ADHDs who underwent intelligence tests were used for the models. These models were developed by analyzing reports using natural language processing (NLP) and incorporating the physician’s diagnosis for each report. We selected n-gram features from the models’ results by extracting important features using SHapley Additive exPlanations and permutation importance to make the models explainable. Developing the n-gram feature-based original text search system compensated for the lack of human readability caused by NLP and enabled the reconstruction of human-readable texts from the selected n-gram features. Results: The maximum model accuracy was 0.92, and the 80 human-readable texts were restored from four models. Conclusion The results showed that the models could accurately classify IDs and ADHDs, even with a few reports. The models were also able to explain their predictions. The explainability-enhanced model can help physicians understand the classification process of IDs and ADHDs and provide evidence-based insights.

Background: Psychological test reports are essential in assessing intellectual functioning, aiding in diagnosing and treating intellectual disability (ID) and attention-deficit/ hyperactivity disorder (ADHD). However, these reports can have several problems because they are diverse, unstructured, subjective, and involve human errors. Additionally, physicians often do not read the entire report, and the number of reports is lower than that of diagnoses. Methods: We developed explainable predictive models for classifying IDs and ADHDs based on written reports to address these issues. The reports of 1,475 patients with IDs and ADHDs who underwent intelligence tests were used for the models. These models were developed by analyzing reports using natural language processing (NLP) and incorporating the physician’s diagnosis for each report. We selected n-gram features from the models’ results by extracting important features using SHapley Additive exPlanations and permutation importance to make the models explainable. Developing the n-gram feature-based original text search system compensated for the lack of human readability caused by NLP and enabled the reconstruction of human-readable texts from the selected n-gram features. Results: The maximum model accuracy was 0.92, and the 80 human-readable texts were restored from four models. Conclusion The results showed that the models could accurately classify IDs and ADHDs, even with a few reports. The models were also able to explain their predictions. The explainability-enhanced model can help physicians understand the classification process of IDs and ADHDs and provide evidence-based insights.

BACKGROUND: Rheumatoid arthritis (RA) is a systemic autoimmune disease characterized by chronic inflammation and joint destruction. Iguratimod (IGU) is a novel conventional synthetic disease-modifying antirheumatic drugs (csDMARD) with good efficacy and safety for the treatment of active RA in China and Japan. However, the long-term effects of IGU on the progression of bone destruction or radiographic progression in patients with active RA remain unknown. We aimed to investigate the efficacy and safety of iguratimod (IGU), a combination of methotrexate (MTX) and IGU, and IGU in patients with active rheumatoid arthritis (RA) who were naïve to MTX. METHODS: This multicenter, double-blind, randomized, non-inferiority clinical trial was conducted at 28 centers for over 52 weeks in China. In total, 911 patients were randomized (1:1:1) to receive MTX monotherapy (10-15 mg weekly, n = 293), IGU monotherapy (25 mg twice daily, n = 297), or IGU + MTX (10-15 mg weekly for MTX and 25 mg twice daily for IGU, n = 305) for 52 weeks. The patients' clinical characteristics, Simplified Disease Activity Index (SDAI), Clinical Disease Activity Index (CDAI), disease activity score in 28 joints-C-reactive protein (DAS28-CRP) level, and disease activity score in 28 joints-erythrocyte sedimentation rate (DAS28-ESR) were assessed at baseline. The primary endpoints were the proportion of patients with ≥20% improvement according to the American College of Rheumatology (ACR20) response and changes in the van der Heijde-modified total Sharp score (vdH-mTSS) at week 52. RESULTS: The proportions of patients achieving an ACR20 response at week 52 were 77.44%, 77.05 %, and 65.87% for IGU monotherapy, IGU + MTX, and MTX monotherapy, respectively. The non-inferiority of IGU monotherapy to MTX monotherapy was established with the ACR20 (11.57%; 95% confidence interval [CI], 4.35-18.79%; P <0.001) and vdH-mTSS (-0.37; 95% CI, -1.22-0.47; P = 0.022). IGU monotherapy was also superior to MTX monotherapy in terms of ACR20 ( P = 0.002) but not the vdH-mTSS. The superiority of IGU + MTX over MTX monotherapy was confirmed in terms of the ACR20 (11.18%; 95% CI, 3.99-18.37%; P = 0.003), but not in the vdH-mTSS (-0.68; 95% CI, -1.46-0.11; P = 0.091). However, the difference in the incidence rates of adverse events was not statistically significant. CONCLUSIONS: IGU monotherapy/IGU + MTX showed a more favorable clinical response than did MTX monotherapy. IGU may have some clinical benefits over MTX in terms of radiographic progression, implying that IGU may be considered as an initial therapeutic option for patients with active RA. TRIAL REGISTRATION https://classic.clinicaltrials.gov/ , NCT01548001.
Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Antirheumatic Agents/therapeutic use* ; Arthritis, Rheumatoid/drug therapy* ; Chromones/adverse effects* ; Double-Blind Method ; Drug Therapy, Combination ; Methotrexate/adverse effects* ; Treatment Outcome ; Sulfonamides

Background: Psychological test reports are essential in assessing intellectual functioning, aiding in diagnosing and treating intellectual disability (ID) and attention-deficit/ hyperactivity disorder (ADHD). However, these reports can have several problems because they are diverse, unstructured, subjective, and involve human errors. Additionally, physicians often do not read the entire report, and the number of reports is lower than that of diagnoses. Methods: We developed explainable predictive models for classifying IDs and ADHDs based on written reports to address these issues. The reports of 1,475 patients with IDs and ADHDs who underwent intelligence tests were used for the models. These models were developed by analyzing reports using natural language processing (NLP) and incorporating the physician’s diagnosis for each report. We selected n-gram features from the models’ results by extracting important features using SHapley Additive exPlanations and permutation importance to make the models explainable. Developing the n-gram feature-based original text search system compensated for the lack of human readability caused by NLP and enabled the reconstruction of human-readable texts from the selected n-gram features. Results: The maximum model accuracy was 0.92, and the 80 human-readable texts were restored from four models. Conclusion The results showed that the models could accurately classify IDs and ADHDs, even with a few reports. The models were also able to explain their predictions. The explainability-enhanced model can help physicians understand the classification process of IDs and ADHDs and provide evidence-based insights.

Background: Psychological test reports are essential in assessing intellectual functioning, aiding in diagnosing and treating intellectual disability (ID) and attention-deficit/ hyperactivity disorder (ADHD). However, these reports can have several problems because they are diverse, unstructured, subjective, and involve human errors. Additionally, physicians often do not read the entire report, and the number of reports is lower than that of diagnoses. Methods: We developed explainable predictive models for classifying IDs and ADHDs based on written reports to address these issues. The reports of 1,475 patients with IDs and ADHDs who underwent intelligence tests were used for the models. These models were developed by analyzing reports using natural language processing (NLP) and incorporating the physician’s diagnosis for each report. We selected n-gram features from the models’ results by extracting important features using SHapley Additive exPlanations and permutation importance to make the models explainable. Developing the n-gram feature-based original text search system compensated for the lack of human readability caused by NLP and enabled the reconstruction of human-readable texts from the selected n-gram features. Results: The maximum model accuracy was 0.92, and the 80 human-readable texts were restored from four models. Conclusion The results showed that the models could accurately classify IDs and ADHDs, even with a few reports. The models were also able to explain their predictions. The explainability-enhanced model can help physicians understand the classification process of IDs and ADHDs and provide evidence-based insights.

Objective To investigate the screening results and factors affecting abnormal detection rates among high-risk groups of esophageal cancer and to explore effective intervention measures. Methods We investigated and collected the information on gender, education level, age, marital status, symptoms of reflux esophagitis (heartburn, acid reflux, belching, hiccup, foreign body sensation in the pharynx, and difficulty swallowing), consumption of pickled vegetables, salt use, and esophageal cancer incidence of villagers in a natural village in Wenfeng District, Anyang City, Henan Province. Changes in reflux esophagitis symptoms in the high-incidence area of esophageal cancer before and after 16 years were observed, and the relationship of such changes with esophageal cancer was analyzed. Results In 2008, 711 cases were epidemiologically investigated, including 213 cases with one of the symptoms of reflux esophagitis such as heartburn, acid reflux, belching, hiccups, foreign body sensation in the pharynx, and difficulty swallowing (sorted in accordance with the abovementioned symptoms; if there are multiple symptoms, then the former is taken); 55 cases with at least two related symptoms, among which the most symptom was heartburn in 108 cases (15.1%); followed by acid reflux, belching, etc. In 2024, the same group of people was investigated, and eight people were missing because of relocation. A total of 703 people were successfully investigated, of which 189 cases (26.8%) had one of the symptoms of reflux esophagitis, such as heartburn (sorted in accordance with relevant symptoms, if there are multiple symptoms, then the former will be selected); 167 cases (23.7%) had at least two related symptoms, among which the most symptom was heartburn in 139 cases (19.7%); followed by acid reflux. Over 16 years, among the 703 people investigated, 45 cases had esophageal cancer and they had one or more of the abovementioned symptoms. No significant differences in the reflux esophagitis-like symptoms were found between 2008 and 2024 (P=0.26); no significant differences in the composition of reflux esophagitis-like symptoms were found between 2008 and 2024 (P=0.299). Conclusion The detection rate of reflux esophagitis-related symptoms in the population in a high-risk area of esophageal cancer has not decreased in the past 16 years, and the high-risk factors still exist. Esophageal cancer is closely related to reflux esophagitis, and clinical practice can provide early diagnosis and treatment for high-risk population.

Objective To understand the disease spectrum of a natural village in an area with high incidence of esophageal cancer to provide a reference for precise prevention and control. Methods From 2008 to 2024, 711 asymptomatic people over the age of 35 years in a natural village with high incidence of esophageal cancer in China were surveyed, and 171 of them were subjected to gastroscopy, biopsy, and pathological examination. All participants were followed up for a long time, and their disease history was recorded. Results A total of 16 years of follow-up were performed, and 703 people were effectively followed up. In 2008, 171 people underwent gastroscopy, and 160 people had biopsy and pathological results in endoscopic screening. By 2024, 76 people had been diagnosed with malignant tumors of 12 different types, and among these people, 45 had esophageal cancer. Conclusion Esophageal cancer remains a significant cause of morbidity and mortality from malignant tumors in this region. Biopsy and pathological examination should be strengthened during gastroscopy, and follow-ups and regular check-ups should be given high importance to reduce the incidence and mortality rates of esophageal cancer.

ObjectiveTo characterize the seasonal patterns of influenza in Kunming City, Yunnan Province before, during, and after the COVID-19 pandemic, and provide scientific evidence for optimizing influenza prevention and control strategies. MethodsInfluenza-like illness (ILI) and etiological surveillance data for influenza from the 14^th week of 2010 to the 13^th week of 2024 in Kunming City of Yunnan Province were collected. Harmonic regression models were constructed to analyze the epidemic characteristics and seasonal patterns of influenza before (2010/2011‒2019/2020 influenza seasons), during (2020/2021‒2022/2023 influenza seasons), and after (2023/2024 influenza season) the COVID-19 pandemic. ResultsBefore the COVID-19 pandemic, influenza in Kunming City mainly exhibited an annual cyclic pattern without a significant semi-annual periodicity, peaking from December to February of the next year, with an epidemic duration of 20‒30 weeks. During the pandemic, influenza seasonality shifted, with an increase in semi-annual periodicity and an approximate one month delay in annual peaks. However, after the pandemic, the annual amplitude of influenza increased compared with that before the pandemic, and the epidemic duration extended by about one month. Although the annual peak largely reverted to the pre-pandemic levels, the annual peaks for different influenza subtypes/lineages had not fully recovered. ConclusionInfluenza seasonality in Kunming City underwent substantial alterations following the COVID-19 pandemic and has not yet fully reverted to pre-pandemic levels. Continuous surveillance on different subtypes/lineages of influenza viruses remains essential, and prevention and control strategies should be adjusted and optimized in a timely manner based on current epidemic trends.

This case report presents a 16-year-old male patient with deficiency of adenosine deaminase 2(DADA2). The patient had a history of Raynaud′s phenomenon with digital ulcers since childhood. As the disease progressed, the patient developed retinal vasculitis, intracranial hemorrhage, skin necrosis, severe malnutrition, refractory hypertension, and gastrointestinal bleeding. Genetic testing revealed compound heterozygous mutations in the ADA2 gene (paternal c.1072G > A pathogenic mutation + maternal c.1065C > A variant of unknown clinical significance). ADA2 enzyme activity was significantly reduced (0.1 U/L). A multidisciplinary treatment team developed an individualized plan to address key issues, including nutritional support, blood pressure control, rehabilitation, pain management, and balancing anticoagulation/bleeding risks. After systematic intervention, the patient′s condition showed partial improvement. This case reveals clinical challenges such as anticoagulation decisions and nutritional support of DADA2. It also emphasizes the importance of early molecular diagnosis, tumor necrosis factor-α inhibitor targeted therapy, and multidisciplinary collaboration in management, underlining the core value of precision medicine in rare disease management.