Establishment and Application of Early Risk Stratification Method for Acute Abdominal Pain in Adults

Machine learning based prediction models for analyzing risk factors in patients with acute abdominal pain: a retrospective study

Background

Acute abdominal pain (AAP) is a common symptom presented in the emergency department (ED), and it is crucial to have objective and accurate triage. This study aims to develop a machine learning-based prediction model for AAP triage. The goal is to identify triage indicators for critically ill patients and ensure the prompt availability of diagnostic and treatment resources.

Methods

In this study, we conducted a retrospective analysis of the medical records of patients admitted to the ED of Wuhan Puren Hospital with acute abdominal pain in 2019. To identify high-risk factors, univariate and multivariate logistic regression analyses were used with thirty-one predictor variables. Evaluation of eight machine learning triage prediction models was conducted using both test and validation cohorts to optimize the AAP triage prediction model.

Results

Eleven clinical indicators with statistical significance (p < 0.05) were identified, and they were found to be associated with the severity of acute abdominal pain. Among the eight machine learning models constructed from the training and test cohorts, the model based on the artificial neural network (ANN) demonstrated the best performance, achieving an accuracy of 0.9792 and an area under the curve (AUC) of 0.9972. Further optimization results indicate that the AUC value of the ANN model could reach 0.9832 by incorporating only seven variables: history of diabetes, history of stroke, pulse, blood pressure, pale appearance, bowel sounds, and location of the pain.

Conclusion

The ANN model is the most effective in predicting the triage of AAP. Furthermore, when only seven variables are considered, including history of diabetes, etc., the model still shows good predictive performance. This is helpful for the rapid clinical triage of AAP patients and the allocation of medical resources.

[Epidemiology, initial diagnosis, and therapy of unexplained abdominal pain in the emergency department]

BACKGROUND

Abdominal pain is one of the most common symptoms of patients who present to the emergency department (ED). The aim of this study was to collect current epidemiological data, the frequency of these findings, and the measures that derived from them.

METHODS

We performed a retrospective analysis in the period between January 1 and June 30, 2016, including all patients who presented to the ED of the Caritas Hospital St. Josef in Regensburg (teaching hospital with an academic urology and gynecology department, about 32,000 patients in the ED per year) and were categorized as "abdominal pain in adults" using the Manchester Triage System (MTS).

RESULTS

The study population consisted of 1417 patients (9.8% of all ED patients). The admission rate was 48.2%. Vomiting and fever as concomitant symptoms made hospitalization more likely (p = 0.00). Almost half of the patients had nonspecific abdominal pain (28.2%), gynecological causes (13.2%), or suspected acute appendicitis (6.7%). In all, 10% of patients received an abdominal CT investigation; 73% of the patients presented in the time from 08:00-20:00 h, and more frequently on weekdays (74.2%). Of these patients, 6.4% returned after discharge because of persisting or worsening symptoms. Finally, 58.6% of outpatients and 77.5% of inpatients received further treatment recommendations for new pharmacologic therapy (e.g., analgesics, proton pump inhibitors, antibiotics).

CONCLUSION

A variety of epidemiological data of our collective could be analyzed, which should be transferable to many other German EDs. The MTS shows a high reliability in terms of conversion rate in abdominal pain; despite comprehensive emergency diagnostics, a relevant proportion of complaints remain unclear.

Effect of taurine on immune function in mice with T-cell lymphoma during chemotherapy

OBJECTIVE

To observe the effect of taurine on immune function in mice with T-cell lymphoma during chemotherapy.

METHODS

A total of 40 C57BL/6 mice were selected and randomly divided into 4 groups, namely model group, chemotherapy group, taurine group and chemotherapy + taurine group, each containing 10 mice. Hypodermic injection was adopted to inoculate EL-4 cells in order to establish model of T-cell lymphoma. When the tumor achieved the size of 1 cm³, intervention treatments were given to the groups respectively. Mice in model group received 0.2 mL of normal saline which was intraperitoneally injected on Days 1, 8 and 15 with 3 weeks as a cycle; mice in chemotherapy group were administered with 80 mg/kg body weight of gemcitabine which was also intraperitoneally injected on Days 1, 8 and 15 with 3 weeks as a cycle; mice in taurine group were administered with 80 mg/kg body weight of taurine intraperitoneally injected daily for consecutive 8 d; mice in chemotherapy + taurine group were treated in the same manner as the mice in taurine group and chemotherapy group. Five mice were sacrificed at 2 and 3 weeks after intervention respectively, and the tumor tissues were collected and weighted after removal of auxiliary tissue, then the tumor inhibition rate was calculated. The thymus and spleen of mice sacrificed at 3 weeks after intervention were collected and weighted, and thymus and spleen indexes were calculated. Enzyme linked immunosorbent assay was used to detect the serum levels of IL-4, IL-10, IL-12 and IFN-γ in mice of each group.

RESULTS

The tumor weights in chemotherapy group, taurine group and chemotherapy + taurine group after 2 and 3 weeks of treatment were significantly lower than that in model group (P < 0.05); the tumor weight in chemotherapy + taurine group after 2 and 3 weeks of treatment was significantly lower than that in chemotherapy group (P < 0.05); the tumor inhibition rate in chemotherapy + taurine group was significantly higher than that in chemotherapy group and taurine group (P < 0.05); the thymus and spleen indexes in taurine group and chemotherapy + taurine group were significantly higher than those in chemotherapy group and model group (P < 0.05); the thymus and spleen indexes in chemotherapy group were significantly lower than those in model group (P < 0.05); after 3 weeks of treatment, the serum levels of IL-4, IL-12 and IFN-γ in chemotherapy group, taurine group and chemotherapy + taurine group were significantly lower than those in model group (P < 0.05); the IL-4 level in taurine group and chemotherapy + taurine group was significantly lower than that in chemotherapy group (P < 0.05); the serum level of IL-10 in chemotherapy group and chemotherapy + taurine group was significantly higher than that in model group and taurine group (P < 0.05); the serum level of IFN-γ in taurine group and chemotherapy + taurine group was significantly lower than that in model group and chemotherapy group (P < 0.05); after treatment of 3 weeks, the serum levels of IL-4 and IL-10 in chemotherapy group, taurine group and chemotherapy + taurine group were significantly lower than those in model group (P < 0.05), and IL-12 level was significantly higher than that in model group (P < 0.05); the level of IFN-γ in taurine group and chemotherapy + taurine group was significantly higher than that in model group (P < 0.05), while the level of IFN-γ in chemotherapy group was significantly lower than that in the other 3 groups (P < 0.05).

CONCLUSIONS

Taurine can effectively enhance the immune function of mice with T-cell lymphoma during chemotherapy, reduce the toxicity of chemotherapy.