[Analysis on clinical features and risk factors of death in 210 patients with acute mushroom poisoning]

Early Triage of Critically Ill Adult Patients With Mushroom Poisoning: Machine Learning Approach

BACKGROUND

Early triage of patients with mushroom poisoning is essential for administering precise treatment and reducing mortality. To our knowledge, there has been no established method to triage patients with mushroom poisoning based on clinical data.

OBJECTIVE

The purpose of this work was to construct a triage system to identify patients with mushroom poisoning based on clinical indicators using several machine learning approaches and to assess the prediction accuracy of these strategies.

METHODS

In all, 567 patients were collected from 5 primary care hospitals and facilities in Enshi, Hubei Province, China, and divided into 2 groups; 322 patients from 2 hospitals were used as the training cohort, and 245 patients from 3 hospitals were used as the test cohort. Four machine learning algorithms were used to construct the triage model for patients with mushroom poisoning. Performance was assessed using the area under the receiver operating characteristic curve (AUC), decision curve, sensitivity, specificity, and other representative statistics. Feature contributions were evaluated using Shapley additive explanations.

RESULTS

Among several machine learning algorithms, extreme gradient boosting (XGBoost) showed the best discriminative ability in 5-fold cross-validation (AUC=0.83, 95% CI 0.77-0.90) and the test set (AUC=0.90, 95% CI 0.83-0.96). In the test set, the XGBoost model had a sensitivity of 0.93 (95% CI 0.81-0.99) and a specificity of 0.79 (95% CI 0.73-0.85), whereas the physicians' assessment had a sensitivity of 0.86 (95% CI 0.72-0.95) and a specificity of 0.66 (95% CI 0.59-0.73).

CONCLUSIONS

The 14-factor XGBoost model for the early triage of mushroom poisoning can rapidly and accurately identify critically ill patients and will possibly serve as an important basis for the selection of treatment options and referral of patients, potentially reducing patient mortality and improving clinical outcomes.

Demographic, clinical, and laboratory findings of mushroom-poisoned patients in Kermanshah province, west of Iran

Background

Mushroom poisoning can cause gastrointestinal, renal, and hepatic symptoms and even death. This descriptive study examined the demographic, clinical, and laboratory findings of patients with fungal poisoning, a type of fungus causing the poisoning, and the incidence and mortality rates of fungal poisoning in Kermanshah province, western Iran, from 2014 to 2018.

Methods

The medical records of 193 patients with mushroom poisoning from 2014 to 2018 were evaluated. The liver and kidney function tests, electrolytes, abdominal and pelvic ultrasound, chest x-ray, coagulation tests, and coagulation factors (fibrinogen, prothrombin) were assessed. Data were collected from the medical records of patients admitted to the Poisoning Center of Imam Khomeini Hospital in Kermanshah, Iran using a researcher-made checklist. Data were analyzed by SPSS (version 16) using descriptive statistics, including mean, standard deviation, and frequency distribution tables. Trend analysis for proportion was done by chi-square statistics in STATA-14 software (ptrend command).

Results

Of cases, ‌51.3% were male, 92.6% were city dwellers, 38.3% were aged 21–40 years, and 92.5% were poisoned during the spring. The fungus that caused poisoning was Amanita virosa. The gastrointestinal, nervous, and visual systems were the most common systems involved. The most common gastrointestinal symptoms included nausea and vomiting (72.0%) and abdominal pain (71.0%). Vertigo (11.9%) and headache (9.3%) were the most common neurological symptoms. The most common visual manifestation was blurred vision (7.8%). Of cases, 23.7% had metabolic acidosis. The increased alkaline phosphatase level was the most common liver disorder in 98.7% of the cases. Increased blood urea nitrogen and creatinine levels were also reported in 21.0% and 17.7% of the cases, respectively. The serum lactic dehydrogenase and creatine phosphokinase levels also increased in 99.3% and 30.2% of the patients, respectively. The mortality rate was 1.6% (n = 3).

Conclusion

The fungal poisoning diagnosis should always be considered in young patients referred to the emergency department with gastrointestinal complaints, a history of consuming wild self-picked mushrooms, and high liver and kidney test values. Since most fungal poisonings occur in the spring, it is necessary to inform the community of the dangers of consuming self-picked wild mushrooms, especially in this season.