Systematic review of diagnostic pathways for patients presenting with acute abdominal pain

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.

[Consultations by senior physicians in general and abdominal surgery for other medical disciplines over 10 years at a tertiary center-Is a fast time-consuming processing necessary? : Spectrum of clinical findings, diagnoses and treatment decision making]

BACKGROUND

The challenges of an adequate, efficient and rational medical treatment and care of patients are always associated with an interprofessional activity of several specialist disciplines.

AIM

The spectrum of variable diagnoses and the profile of surgical decision-making with further surgical measures within the framework of senior physician consultation in general and visceral surgery for neighboring medical disciplines were analyzed on a representative patient cohort over a defined observational time period.

PATIENTS AND METHODS

All consecutive patients (n = 549 cases) were documented as part of a clinical systematic prospective single center observational study at a tertiary center using a computer-based patient registry over 10 years (1 October 2006-30 September 2016). The data were analyzed with respect to the spectrum of clinical findings, diagnoses, treatment decisions and the influencing factors as well as gender and age differences and time-dependent developmental trends using χ2-tests and U‑tests.

RESULTS (KEY POINTS)

The predominant discipline for requests for surgical consultation was cardiology (19.9%) followed by surgical disciplines (11.8%) and gastroenterology (11.3%). Disorders of wound healing (7.1%) and acute abdomen (7.1%) were predominant in the diagnostic profile. In 11.7% of the patients the indications for immediate surgery were derived, whereas in 12.9% elective surgery was recommended. The conformity rate of suspected and definitive diagnoses was only 58.4%.

CONCLUSION

The surgical consultation work is an important mainstay of a sufficient and especially timely clarification of surgically relevant questions in nearly all medical institutions and especially in a center. This serves i) the quality assurance of surgery in the clinical care of patients with need of additional interdisciplinary needs for surgical treatment in the daily practice of general and abdominal surgery in research on clinical care, ii) clinical marketing and monetary aspects in the sense of patient recruitment and iii) last but not least to provide emergency care of patients. Due to the high proportion of 12% of subsequent emergency operations, which were derived from requests for general and visceral surgical consultations, such requests must be processed promptly during working hours.

Retroperitoneal Hemorrhage Due to Spontaneous Renal Rupture as the First Presentation of Antiphospholipid Syndrome: A Case Report

Spontaneous renal rupture (SRR) with retroperitoneal hemorrhage is an extremely rare medical emergency and is rather challenging for the surgical team. Management of SRR often requires surgical intervention and nephrectomy as it is life-threatening. Antiphospholipid syndrome (APLS) is an autoimmune disease that affects several organs, including kidneys, causing significant abnormalities. Current data suggest that APLS can result in renal artery stenosis, renal vein thrombosis, arterial hypertension, thrombotic microangiopathy, and antiphospholipid syndrome nephropathy where there is renal involvement. Here, we report the case of a 49-year-old man who presented to the Emergency Department with sudden-onset abdominal pain in the context of retroperitoneal bleeding due to SRR. The patient developed hemodynamic instability and underwent a total nephrectomy. The surgical specimen revealed APLS-related lesions. Serological tests confirmed the diagnosis of APLS, which was managed with acenocoumarol and hydroxychloroquine. Since then, he has not experienced any thromboembolic or hemorrhagic episodes. This article aims to present for the first time a case of SRR as the first presentation of APLS as well as to analyze the possible associated mechanisms.

Sociodemographic Differences in Care Plans and Time to Treatment Among Children Being Considered for Adenotonsillectomy

OBJECTIVE

To assess sociodemographic differences in care plans and time to evaluation or treatment after otolaryngologic consultation among children with obstructive sleep-disordered breathing (oSDB).

STUDY DESIGN

Retrospective cohort study.

SETTING

Single tertiary children's hospital.

METHODS

We included children aged 2 to 9 years with oSDB seen from June to December 2018 as new otolaryngology clinic patients. Logistic regression was used to examine whether sociodemographic factors were associated with having adenotonsillectomy or polysomnography planned at the end of the visit. Kaplan-Meier analyses and Cox proportional hazards models were used to compare times to these events.

RESULTS

An overall 1020 children were included, of whom 65% were White and 18% were Black. Approximately 77% were metropolitan residents, 52% were publicly insured, and 88% of caregivers spoke primarily English. Treatment plans included adenotonsillectomy for 62% of patients, polysomnography for 15%, and new medication therapy for 13%. In multivariable analyses, there were no significant differences by child race/ethnicity, metropolitan/nonmetropolitan residence, type of health insurance, or caregiver primary language in the likelihood of having adenotonsillectomy or polysomnography planned. Among children for whom adenotonsillectomy was planned, children from metropolitan areas had greater times to surgery than children from nonmetropolitan areas (hazard ratio, 0.81 [95% CI, 0.66-0.99]; P = .04). This was explained by a difference between Black children from metropolitan areas and White children from nonmetropolitan areas (hazard ratio, 0.65 [95% CI, 0.49-0.86]; P = .003); there were no racial/ethnic differences in time to surgery among metropolitan-residing children (P = .09).

CONCLUSIONS

After initial otolaryngology consultation, children with oSDB from metropolitan areas have longer times to adenotonsillectomy than those from nonmetropolitan areas.

Exploring the evidence-practice gap in the use of plain radiography for acute abdominal pain and intestinal obstruction: a systematic review and meta-analysis

AIM

Previous studies, some dating back several decades, have recommended that the use of plain abdominal radiography should be curbed, particularly with the growth of more accurate imaging modalities. However, evidence from referral data suggests that plain abdominal radiography continues to be a commonly requested examination. The aim of this review was to explore the gap between evidence and practice by re-examining the evidence using a robust methodology, investigating the diagnostic accuracy of plain abdominal radiography.

METHODS

Studies were identified from electronic databases and reference lists. Eligible studies provided data as to the sensitivity and specificity of plain abdominal radiography for either acute abdominal pain (Group A) or suspected intestinal obstruction (Group B). Version 2 of the Quality Assessment of Diagnostic Accuracy Studies was used to assess the quality of studies and hierarchical summary receiver operator characteristic curves and coupled forest plots were generated.

RESULTS

Four studies evaluated plain abdominal radiography for acute abdominal pain (Group A) and 10 for suspected intestinal obstruction (Group B). Two studies investigated both presentations and were included in both groups. Methodological quality of studies was moderately high, though incorporation bias was a common limitation. Sensitivity for Group A studies ranged from 30 to 46%, with specificity from 75 to 88%. For Group B, the range of sensitivity was 48 to 96% and specificity from 50 to 100%.

CONCLUSION

The results suggest that use of plain abdominal radiography could be substantially reduced, particularly for patients with undifferentiated acute abdominal pain. While some guidelines exist, there is sound argument for clinical decision rules for abdominal imaging to inform evidence-based clinical decision-making and radiology referrals.