Predicting the risk of acute kidney injury in patients with acute pancreatitis complicated by sepsis using a stacked ensemble machine learning model: a retrospective study based on the MIMIC database

Objective
This study developed and validated a stacked ensemble machine learning model to predict the risk of acute kidney injury in patients with acute pancreatitis complicated by sepsis.

Design
A retrospective study based on patient data from public databases.

Participants
This study analysed 1295 patients with acute pancreatitis complicated by septicaemia from the US Intensive Care Database.

Methods
From the MIMIC database, data of patients with acute pancreatitis and sepsis were obtained to construct machine learning models, which were internally and externally validated. The Boruta algorithm was used to select variables. Then, eight machine learning algorithms were used to construct prediction models for acute kidney injury (AKI) occurrence in intensive care unit (ICU) patients. A new stacked ensemble model was developed using the Stacking ensemble method. Model evaluation was performed using area under the receiver operating characteristic curve (AUC), precision-recall (PR) curve, accuracy, recall and F1 score. The Shapley additive explanation (SHAP) method was used to explain the models.

Main outcome measures
AKI in patients with acute pancreatitis complicated by sepsis.

Results
The final study included 1295 patients with acute pancreatitis complicated by sepsis, among whom 893 cases (68.9%) developed acute kidney injury. We established eight base models, including Logit, SVM, CatBoost, RF, XGBoost, LightGBM, AdaBoost and MLP, as well as a stacked ensemble model called Multimodel. Among all models, Multimodel had an AUC value of 0.853 (95% CI: 0.792 to 0.896) in the internal validation dataset and 0.802 (95% CI: 0.732 to 0.861) in the external validation dataset. This model demonstrated the best predictive performance in terms of discrimination and clinical application.

Conclusion
The stack ensemble model developed by us achieved AUC values of 0.853 and 0.802 in internal and external validation cohorts respectively and also demonstrated excellent performance in other metrics. It serves as a reliable tool for predicting AKI in patients with acute pancreatitis complicated by sepsis.

Leggi
Febbraio 2025

Gender, race and ethnicity biases experienced by hospital physicians: an umbrella review to explore emerging biases in the evidence base

Objectives
To examine the authorship and content of systematic reviews (SRs) of biases experienced by medical professionals through a gender lens.

Design
Review of SRs.

Data sources
We searched PubMed, Embase, PsycINFO and CINAHL from inception. Searches were conducted in May 2022 and updated in October 2023.

Eligibility criteria
Reviews of studies reporting biases experienced by hospital physicians at any stage of their careers and in any country. Reviews were included if they used systematic methods to search the literature and synthesise the data. Non-English language publications were excluded.

Data extraction and synthesis
The main theme of each eligible review was identified through qualitative thematic analysis. We used NamSor to determine the first/last authors’ gender and computed the proportion of female authors for each review theme.

Results
56 articles were included in the review. These covered 12 themes related to gender, race and ethnicity bias experienced by physicians at any stage of their careers. The overall proportion of female authors was 70% for first authors and 51% for last authors. However, the gender of authors by theme varied widely. Female authors dominated reviews of research on discrimination and motherhood, while male authors dominated reviews on burnout, mental health and earnings. Only six reviews were identified that included race and ethnicity; 9 out of the 12 first and last authors were female.

Conclusions
Understanding the potential for a gendered evidence base on biases experienced by hospital physicians is important. Our findings highlight apparent differences in the issues being prioritised internationally by male and female authors, and a lack of evidence on interventions to tackle biases. Going forward, a more collaborative and comprehensive framework is required to develop an evidence base that is fit for purpose. By providing a point of reference, the present study can help this future development.

PROSPERO registration number
CRD42021259409; Pre-results.

Leggi
Febbraio 2025

Association between adjuvant radiotherapy in adults with gastric cancer and risk of second primary malignancy: a retrospective cohort study using the Surveillance, Epidemiology and End Results database

Objectives
This study aims to assess the association between adjuvant radiotherapy and the development of second primary malignancies (SPMs) and identify its determinants in patients who have undergone surgical treatment for gastric cancer.

Design
Retrospective cohort study using the Surveillance, Epidemiology and End Results (SEER) database.

Setting
Cohorts (18 registries, 2000–2018, from SEER) were screened for any malignancy that developed after sufficient latency from diagnosis of surgically treated non-metastatic gastric cancer.

Participants
24 777 surgically treated gastric cancer cases were included in the cohort. Among them, 6128 patients underwent adjuvant radiotherapy.

Outcome measures
The cumulative incidence of SPMs was estimated using Fine and Gray’s competing risk model and the radiotherapy-correlated risks were calculated using Poisson regression analysis.

Results
Among patients with sufficient latency, there was no significant association between radiotherapy and the risk of developing second primary solid malignancies (relative risk=1.05, 95% CI 0.83 to 1.33) or haematological malignancies (relative risk=1.17, 95% CI 0.62 to 2.11). Interestingly, radiotherapy was associated with a reduced cumulative incidence of second lung and bronchus cancer compared with no radiotherapy, with a 15-year incidence of 1.4%–3.17% (p

Leggi
Febbraio 2025

Examining the relationship between incidence and mortality for commonly diagnosed cancers in the USA: an observational study using population-based SEER database

Objective
Incidence and mortality are fundamental epidemiologic measures of cancer burden, yet few studies have examined individual cancers to determine how these measures correlate across place. We assessed the relationship between incidence and mortality for commonly diagnosed cancers in the USA.

Design
Population-based observational study of US counties.

Setting and participants
The Surveillance, Epidemiology and End Results (SEER) database was used to obtain incidence (2000–2016) and mortality (2002–2018) data for the 12 most commonly diagnosed non-haematologic cancers.

Outcome measures
County-level correlation between cancer incidence and mortality. Cancers were grouped into terciles based on the population-weighted correlation coefficient (r). We also examined the 10 year risk of death, both from the diagnosed cancer and other causes.

Results
County-level incidence and mortality were strongly correlated in some cancers, yet uncorrelated in others. Cancers in the high-correlation tercile (r range: 0.96 to 0.78) included lung, stomach, liver and pancreas. For patients with these cancers, the risk of death from the diagnosed cancer was >4-times the risk of death from other causes. The moderate-correlation tercile (r: 0.75 to 0.58) included cancers of the colon, bladder, kidney and uterus. There was little or no relationship between incidence and mortality for cancers in the low-correlation tercile (r: 0.33 to –0.10): melanoma, prostate, breast and thyroid. The risk of death from the diagnosed cancer for these patients was either lower or no different than their risk of death from other causes.

Conclusions
For some cancers in the USA, the fundamental epidemiologic measure of disease frequency—incidence—now has little relationship with cancer death (mortality). Low correlations are most likely explained by differences in diagnostic practice leading to variable amounts of cancer overdiagnosis between different US counties.

Leggi
Febbraio 2025

Pathway Of Low Anterior Resection syndrome (LARS) relief after Surgery (POLARiS): protocol for an international, open-label, multi-arm, phase 3 randomised superiority trial within a cohort, with economic evaluation, process evaluation and qualitative sub-study, to explore the natural history of LARS and compare transanal irrigation and sacral neuromodulation to optimised conservative management for people with major LARS following a high or low anterior resection for colorectal cancer

Introduction
As a result of improving survival rates, the adverse consequences of rectal cancer surgery are becoming increasingly recognised. Low anterior resection syndrome (LARS) is one such consequence and describes a constellation of bowel symptoms after rectal cancer surgery which includes urgency, faecal incontinence, stool clustering and incomplete evacuation. LARS has a significant adverse impact on quality of life (QoL) and symptoms are present in up to 75% of patients in the first year after surgery. Despite this, little is known about the natural history and there is poor evidence to support current treatment options.

Methods and analysis
The objectives of POLARiS are to explore the natural history of LARS and to evaluate the clinical and cost-effectiveness of transanal irrigation (TAI) or sacral neuromodulation (SNM) compared with optimised conservative management (OCM) for people with major LARS.
POLARiS is a prospective, international, open-label, multi-arm, phase 3 randomised superiority trial within a cohort design, with internal pilot phase, qualitative sub-study, process evaluation and economic evaluation. Approximately 1500 adult participants from UK hospitals and 500 from Australian hospitals who have undergone a high or low anterior resection for colorectal cancer in the last 10 years will be recruited into the cohort. Six-hundred participants from the UK and 200 participants from Australia, with major LARS symptoms, defined as a LARS score of ≥30, will be recruited to the randomised controlled trial (RCT) element. Participants entering the RCT will be randomised between OCM, TAI or SNM, all with equal allocation ratios.
Cohort and RCT participants will be followed up for a 24-month period, completing a series of questionnaires measuring LARS symptoms and QoL, as well as clinical review for those in the RCT. A process evaluation, qualitative sub-study and economic evaluation will also be conducted.
The primary outcome measure of the POLARiS cohort and RCT is the LARS score up to 24 months post-registration/randomisation. Analyses of the RCT will be conducted on an intention-to-treat basis. Comparative effectiveness analyses for each endpoint will consist of two pairwise treatment comparisons: TAI versus OCM and SNM versus OCM. Secondary outcomes include health-related QoL, adverse events, treatment compliance and cost-effectiveness (up to 24 months post-registration/randomisation).

Ethics and dissemination
Ethical approval has been granted by Wales REC 4 (reference: 23/WA/0171) in the UK and Sydney Local Health District HREC (reference: 2023/ETH00749) in Australia. The results of this trial will be disseminated to participants on request and published on completion of the trial in a peer-reviewed journal and at international conferences.

Trial registration number
ISRCTN12834598; ACTRN12623001166662.

Leggi
Febbraio 2025