RESUMEN
Chronic diseases have become an important public health problem for people under 70 years of age worldwide， while also causing a great economic burden. The establishment of clinical prediction models can help to predict the risk of a disease or the prognostic effect of a study subject in advance by means of index testing at the early stage of chronic diseases， and plays an increasingly important role in clinical practice. This study introduces clinical diagnostic prediction models and clinical prognostic prediction models， and reviews clinical data processing， clinical prediction model building， visualization methods and model evaluation from the perspective of the application of clinical prediction models， which contribute to the correct and reasonable use of prediction models in clinical research.
RESUMEN
The application of artificial neural network algorithm in pathological diagnosis of gastrointestinal malignant tumors has become a research hotspot. In the previous studies, the algorithm research mainly focused on the model development based on convolutional neural networks, while only a few studies used the combination of convolutional neural networks and recurrent neural networks. The research contents included classical histopathological diagnosis and molecular typing of malignant tumors, and the prediction of patient prognosis by utilizing artificial neural networks. This article reviews the research progress on artificial neural network algorithm in the pathological diagnosis and prognosis prediction of digestive tract malignant tumors.
Asunto(s)
Humanos , Redes Neurales de la Computación , Algoritmos , Pronóstico , Neoplasias Gastrointestinales/diagnósticoRESUMEN
Esophageal cancer is a tumor with high morbidity and mortality in China, which is generally diagnosed at late stage and yields poor prognosis. Early diagnosis and correct staging are the basis, and reasonable treatment is the most important. Radiomics can make use of existing imaging resources for deeper mining, and make secondary use of its potential high-throughput data through deep learning or machine learning, thereby establishing a radiomics prediction model. This may become an essential marker of tumor prognosis to predict overall survival or tumor progression, thus stratifying patients at different risk for individualized treatment. In this article, the basic concepts of radiomics, its application in prognostic prediction of esophageal cancer and its combination with clinical and genetic studies were reviewed.
RESUMEN
Background: The STarT (Subgrouping for Targeted Treatment) Back Screening Tool (SBST) is an established clinical evaluation tool that easily assesses the risk of chronic or refractory low back pain. This study aimed to examine the usefulness of acupuncture in patients with low back pain. Methods: A total of 71 outpatients with low back pain who underwent acupuncture and moxibustion at the Center for Integrative Medicine, Tsukuba University of Technology, between 2019 and 2022 were included in this study, regardless of the specific medical condition causing the pain. Survey items included the SBST and lumbar pain intensity visual analog scale (VAS). Demographic factors and contents of acupuncture treatment were collected from the medical charts. The VAS score 4 weeks after the start of treatment was used as an index of clinical outcome and was analyzed using repeated measures analysis of variance (ANOVA) and hierarchical multiple regression analysis. Results: Classification using the SBST at the first visit resulted in 36, 30, and 15 patients in the low-, medium-, and high-risk groups, respectively. Repeated-measures ANOVA showed statistically significant differences in the mean VAS values with respect to differences in time point (P < 0.01), group (P < 0.01), and interaction (P < 0.05). The VAS values after 4 weeks in the high-risk group were significantly higher than those in the other two groups (both P < 0.01). In the hierarchical multiple regression analysis, with VAS as the dependent variable, the relationship between SBST classification and VAS maintained a significant positive relationship in all models, including adjustments for interaction terms and patients’ background items. A simple slope analysis indicated that this relationship was more evident in patients with lower limb symptoms than in those without symptoms. Conclusion: The SBST could be a simple and useful tool for predicting the clinical outcomes of acupuncture.
RESUMEN
【Objective】 To develop a prognosis model based on CT images using radiomics method for patients with osteonecrosis of the femoral head (ONFH) and to investigate the additional prediction value of the imaging features of the contralateral normal femoral head regions for the prognosis prediction. 【Methods】 A total of 51 patients were included in this retrospective study. All the patients had preoperative CT images. For each patient, two regions of interest (ROIs) were involved, including the osteonecrosis region and the contralateral normal femoral head region. A total of 968 radiomics features were extracted for each patient. We made both the univariate and multivariable analyses. Three models were developed based on the features of osteonecrosis region, contralateral normal femoral head region, and both regions. The 10 times of repeated random experiments were used for model construction and validation. The average performance of the 10 times of experiments was reported as the results. 【Results】 For the features of osteonecrosis region, 37 features showed significant predictive value, with the mean AUC value of 0.708 2±0.029 9. The AUC of the constructed prediction model was 0.911 0±0.029 4 and 0.688 6±0.089 3 for the training set and validation set, respectively. For the features of contralateral normal femoral head region, 14 features showed significant predictive value, with the mean AUC value of 0.703 6±0.006 9. The AUC value of the constructed model for the training set and validation set was 0.867 2±0.039 5 and 0.669 0±0.072 6, respectively. For the models developed based on combined features, the AUC value was higher than that of the models developed based on osteonecrosis region features (training set: 0.935 8±0.016 6 vs. validation set: 0.737 9±0.090 8). 【Conclusion】 We developed a novel CT images-based radiomics method to predict postoperative prognosis in patients with ONFH. Furthermore, the features of contralateral normal femoral head region has additional prediction value. Combining the imaging features of osteonecrosis region and contralateral normal femoral head region can obtain more accurate prediction of prognosis in patients with ONFH.
RESUMEN
Objective:To analyze the predictive value of serum Nesfatin-1 combined with the Status Epilepticus Severity Scale (STESS) score on the short-term prognosis of children with status epilepticus (SE).Methods:A clinical data of 145 children with SE who were admitted to the Children′s Hospital Affiliated to Zhengzhou University, Henan Children′s Hospital, Zhengzhou Children′s Hospital, from January 2016 to January 2020 were analyzed retrospectively.After admission, the serum levels of Nesfatin-1 and the STESS score were measured.According to the Glasgow Outcome Scale (GOS) score at discharge, children with SE were divided into poor prognosis group (<5 scores) and good prognosis group (5 scores). Univariate and multivariate Logisitc regression analyses were performed to analyze influence of the serum Nesfatin-1 level and STESS score on the short-term prognosis of children with SE.Receiver operating characteristic (ROC) curve was depicted to evaluate the predictive value of serum Nesfatin-1 level combined with STESS score in the short-term prognosis of children with SE. Results:Twenty-five cases out of 145 (17.24%) children with SE were discharged with a GOS score of <5 (poor prognosis group), 120 cases were in the good prognosis group.In the poor prognosis group, the overall attack (88.00% vs.66.67%), attack time of SE > 1 h (76.00% vs.27.50%), admission to child intensive care unit(PICU) (76.00% vs.37.50%), implementation of endotracheal intubation (16.00% vs.5.00%), abnormal electroencephalogram(EEG) results (73.91% vs.41.03%), abnormal proportion of head imaging results (82.61% vs.29.49%), serum Nesfatin-1 level[(3.65±1.45) μg/L vs.(2.20±0.77) μg/L] and STESS score[(3.01±0.75) points vs.(1.80±0.60) points] were significantly higher than those in the good prognosis group (all P<0.05). Logistic regression analysis showed that the attack time of SE > 1 h, admission to PICU, abnormal EEG, abnormal proportion of head imaging results, serum Nesfatin-1 level and STESS score were independent risk factors for the poor short-term prognosis of children with SE ( OR=4.217, 3.456, 2.626, 4.109, 3.040 and 2.012, respectively, all P<0.001). The cut-off value of serum Nesfatin-1 level and STESS score was 3.01 μg/L and 2.38 points, respectively.The Youden index and AUC of the combination of serum Nesfatin-1 level and STESS scores were 0.736 and 0.921 (95% CI: 0.861-0.959), respectively, which were better than those of single detection of either serum Nesfatin-1 level [Youden index 0.447; AUC 0.795(95% CI: 0.720-0.858)] or STESS scores [Youden index 0.562; AUC 0.859(95% CI: 0.792-0.911)]. Conclusions:The abnormal increases in serum Nesfatin-1 level and STESS score are risk factors for poor prognosis of SE in children, and their combination has a high predictive value for the poor short-term prognosis.
RESUMEN
@#Objective To analyze prognostic ability of inflammation-based Glasgow prognostic score (GPS) in patients with ST-segment elevation myocardial infarction (STEMI). Methods We retrospectively analyzed the clinical data of 289 patients with STEMI admitted to the Department of Emergency in West China Hospital from April 2015 to January 2016. All study subjects were divided into three groups: a group of GPS 0 (190 patients including 150 males and 40 females aged 62.63±12.98 years), a group of GPS 1 (78 patients including 58 males and 20 females aged 66.57±15.25 years), and a group of GPS 2 (21 patients including 16 males and 5 females aged 70.95±9.58 years). Cox regression analysis was conducted to analyze the independent risk factors of predicting long-term mortality of patients with STEMI. Results There was a statistical difference in long-term mortality (9.5% vs. 23.1% vs. 61.9%, P<0.001) and in-hospital mortality (3.7% vs. 7.7% vs. 23.8%, P<0.001) among the three groups. The Global Registry of Acute Coronary Events (GRACE) scores and Gensini scores increased in patients with higher GPS scores, and the differences were statistically different (P<0.001). Multivariable Cox regression analysis showed that the GPS was independently associated with STEMI long-term all-cause mortality (1 vs. 0, HR: 2.212, P=0.037; 2 vs. 0, HR: 8.286, P<0.001). Conclusion GPS score is helpful in predicting the long-term and in-hospital prognosis of STEMI patients, and thus may guide clinical precise intervention by early risk stratification.
RESUMEN
Objective To observe the clinical effect of Qingre-Jiangni-Zhixue decoction combined with omeprazole sodium on acute non-variceal upper gastrointestinal bleeding. Methods A total of 64 patients with acute non-variceal upper gastrointestinal bleeding were divided into the observation group and control group according to random number table method, with 32 cases in each group. The control group was given the routine clinical treatment combined with omeprazole sodium, and the observation group was given Qingre-Jiangni-Zhixue decoction on the basis of the control group. After 7 days of continuous treatment, the basic clinical indexes (hemostasis time, blood transfusion volume, hospitalization time, 72 hours hemostasis rate, rebleeding rate), oxidative stress indexes (cortisol, malondialdehyde, antidiuretic hormone, blood glucose) and serum inflammatory factors (hs-CRP, TNF-α, IL-1β) were observed before and after treatment, and the clinical efficacy were evaluated. Results The total effective rate of the observation group was 90.6% (29/32), which was significantly higher than that of the control group 71.9% (23/32), with statistically significant (χ2=4.730, P=0.029). After treatment, the hemostasis time (18.86 ± 2.97 h vs. 29.12 ± 4.07 h, t=7.354),blood transfusion volume (559.32 ± 67.17 ml vs. 612.73 ± 75.81 ml, t=11.032),hospitalization time (5.43 ± 0.67 d vs. 9.26 ± 1.15 d, t=5.871) of the observation group were significantly lower than those of the control group (P<0.05). The 72 h hemostasis rate of the observation group was 3.1%, which was significantly lower than that of the control group 21.9%, with statistically significant (χ2=5.143, P<0.05). The rebleeding rate of the observation group was 96.9%, which was significantly higher than that of the control group 81.3% (χ2=4.010, P=0.045). After treatment, the cortisol level, the malondialdehyde level, blood glucose, antidiuretic hormone of the observation group were lower than those of the control group (t were 8.106, 4.976, 4.842, 5.093, all Ps<0.01). After treatment, the hs-CRP, serum TNF-α, serum IL-1β of the observation group were lower than those of the control group (t were 5.506, 4.983, 7.962, all Ps<0.01). Conclusions The application of Qingre-Jiangni-Zhixue decoction combined with omeprazole sodium can inhibit the expression of serum inflammatory cytokines in patients with acute non-variceal upper gastrointestinal bleeding, reduce the oxidative stress injury caused by bleeding, and improve the hemostatic efficiency.
RESUMEN
OBJECTIVE: Although early intervention from the beginning of a psychotic episode is essential for a better prognosis, biomarkers predictive of symptomatic and functional improvement in early psychotic disorders are lacking. This study aimed to investigate whether the spectral power of resting-state electroencephalography (EEG) can be used as a predictive marker of the 1-year prognosis in patients with first-episode psychosis (FEP). METHODS: Twenty-four patients with FEP and matched healthy control (HC) subjects were examined with resting-state EEG at baseline. The symptomatic severity and functional status of FEP patients were assessed at baseline and reassessed after 1 year of usual treatment. Repeated measures analysis of variance was conducted to compare EEG spectral powers across the groups. Multiple regression analysis revealed EEG spectral powers predictive of symptomatic and functional improvement in FEP patients at the 1-year follow-up. RESULTS: Delta band power in the frontal and posterior regions was significantly higher in patients with FEP than in HCs. Higher delta band power in the posterior region predicted later improvement of positive symptoms and general functional status. Lower delta band power in the frontal region predicted improvement of negative symptoms and general functioning after 1 year. CONCLUSION: These results suggest that increased delta absolute power is observed from the beginning of psychotic disorders. Furthermore, decreased delta power in the frontal region and increased delta power in the posterior region might be used as a predictive marker of a better prognosis of FEP, which would aid early intervention in clinical practice.
Asunto(s)
Humanos , Biomarcadores , Intervención Educativa Precoz , Electroencefalografía , Estudios de Seguimiento , Politetrafluoroetileno , Pronóstico , Trastornos PsicóticosRESUMEN
Objective To retrospectively analyze the emergency treatment in 141 patients with high-risk of acute upper gastrointestinal bleeding(AUGIB) in order to improve the effi cacy of treatment. In addition, to evaluate the predictive values in accuracy terms of AIMS65, Glasgow-Blachford(GBS) and Pre-Rockall scores for risk stratifi cation in AUGIB by comparison among them. Methods Data of 141 patients with AUGIB admitted from Nov.1,2013 to May 31,2017 in our emergency department(ED) were retrospectively analyzed. All patients at fi rst were treated with pharmacologic therapy in emergency room, and some of them underwent endoscopic remedy, intervention or surgery as a last resort. The scores of AIMS65, Glasgow-Blachford(GBS) and Pre-Rockall scores were calculated respectively, and the in-hospital 30-day death and re-bleeding were taken as the study endpoints. Comparison of clinical value among the three scores was carried out by plotting their ROC and calculating the AUC. Results Of them, 65.25% patients underwent endoscopy, and the leading cause of bleeding was peptic ulcer (64.12%). Endoscopic hemostatic clips were used in 8 cases, endoscopic sclerotic therapy in 4 cases, balloon tamponade in 4 cases, TEA (therapeutic embolization approach) in 9 cases, TIPS (trans-internal jugular vein for making hepatic portal vein shunt by stent) in 3 cases, and surgical intervention in 2 cases. Re-bleeding rate was 14.18%, death rate 11.35%. AIMS65 and Pre-Rockall were better than GBS in predicting in-hospital 30-day mortality. There was no difference in predicting re-bleeding among these three scores. Conclusions Medicines combined with endoscopy, various interventions and surgical operation can effectively treat high-risk patients with AUGIB. Both AIMS65 and Pre-Rockall are able to predict mortality accurately with easy practice. Both are suitable in ED to stratify the risk of AUGIB.
RESUMEN
<p>Object: We validated the adequacy of using Palliative Prognostic Index (PPI) as a prognostic method for medical oncology patients. Method: PPI was measured for patients with advanced cancer admitted to our department from May 2015 to June 2016.Result: There were 45 patients analyzed. When classified into three groups according to the score of PPI, there was a tendency for survival curves to separate according to risk. Especially, there was a statistical difference in survival time between the high-risk group (PPI: ≥6.5) and the low-risk group (PPI: ≤4.0) (median survival time: 11 days vs 39 days, p=0.0048, HR: 2.75, 95%CI: 1.32-5.84). Prognostic accuracy of the PPI≥6.5 is similar to other reports. There is no difference in the accuracy of the prognostic prediction depending on the period from drug therapy to PPI evaluation. It was suggested that the influence of drug therapy on PPI evaluation is small. Discussion: We showed that it is appropriate to use PPI for the prognostic prediction of medical oncology patients.</p>
RESUMEN
OBJECTIVE: To evaluate the prognostic value of volume-based metabolic parameters measured with 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) in patients with clinically node-negative (cN0) oral tongue squamous cell carcinoma (OTSCC) as compared with other prognostic factors. MATERIALS AND METHODS: In this study, we included a total of 57 patients who had been diagnosed with cN0 tongue cancer by radiologic, 18F-FDG PET/CT, and physical examinations. The maximum standardized uptake value (SUVmax), average SUV (SUVavg), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) for primary tumors were measured with 18F-FDG PET. The prognostic significances of these parameters and other clinical variables were assessed by Cox proportional hazards regression analysis. RESULTS: In the univariate analysis, pathological node (pN) stage, American Joint Committee on Cancer (AJCC) stage, SUVmax, SUVavg, MTV, and TLG were significant predictors for survival. On a multivariate analysis, pN stage (hazard ratio = 10.555, p = 0.049), AJCC stage (hazard ratio = 13.220, p = 0.045), and MTV (hazard ratio = 2.698, p = 0.033) were significant prognostic factors in cN0 OTSCC patients. The patients with MTV > or = 7.78 cm3 showed a worse prognosis than those with MTV < 7.78 cm3 (p = 0.037). CONCLUSION: The MTV of primary tumor as a volumetric parameter of 18F-FDG PET, in addition to pN stage and AJCC stage, is an independent prognostic factor for survival in cN0 OTSCC.