Background: Predictive models in surgery promise to improve clinical care by anticipating complications, guiding decision-making, and supporting personalized treatment strategies. Although their potential to enhance outcomes and efficiency is substantial, their integration into clinical practice also raises profound ethical challenges. Ethical Framework: These challenges span the entire lifecycle of predictive models from data collection and development to validation and clinical use. They touch upon patient privacy, algorithmic bias, transparency, and the shifting responsibilities of clinicians. Importantly, the ethical concerns are not isolated to one group but shared across patients, developers, and clinicians within a dynamic stakeholder relationship. Analysis: Key risks include biased or unrepresentative datasets, privacy breaches, opaque decision-making processes, and the danger of deskilling surgeons if reliance on algorithms becomes excessive. To mitigate these risks, strategies, such as out-of-distribution detection, standardized data collection, parallel model development, and continuous auditing, are essential. Beyond technical safeguards, embedding predictive models within a framework of accountability and patient-centered care is necessary to sustain trust and equity. Conclusion: The integration of predictive models into surgery requires more than technical excellence, and it demands ethical vigilance. Preparing future clinicians through education that emphasizes both clinical reasoning and ethical awareness is critical. By aligning predictive model development with human-centered values, healthcare systems can ensure that these innovations enhance surgical practice while safeguarding equity, transparency, and patient trust.

OBJECTIVES: The aim of this study was to assess the walkout rate and to identify influencing patient and visit characteristics on walkout. Furthermore, we assessed the reasons for leaving and medical care needs after leaving.
METHODS: In a 4-month population-based cohort study, the characteristics and influencing factors of walkout from two emergency departments in the Netherlands were studied. Afterwards, a follow-up telephone interview was conducted to assess the reasons for leaving and medical care needed.
RESULTS: A total of 169 out of 23 780 (0.7%) registered patients left without treatment, of whom 62% left after triage. Of the triaged walkouts, 26% had urgent or highly urgent medical complaints and target times to treatment had elapsed for 54% of the triaged walkouts. Independent predictors of leaving without treatment included being self-referred, arriving during the evening or night or during crowded conditions, and relatively lower urgency triage allocation. Ninety (53%) walkouts were contacted afterwards by phone. Long waiting time (61%) was the most-cited prime reason for leaving. Medical problems had resolved spontaneously in 19 of the 90 (21%) walkouts, and 47 (52%) walkouts reported having sought medical care elsewhere. For 24 of the 90 (27%) walkouts with persisting complaints, medical care was advised during the follow-up telephone call.
CONCLUSION: The average observed daily walkout rate was 1.4 patients over the 4-month period. In general, walkouts are self-referrals with lower urgent complaints, arriving during the evening or night shift or during crowded conditions. Most walkouts leave because of perceived long waiting times.

Background: Unscheduled return visits to the emergency department (ED) may reflect shortcomings in care. This study characterized ED return visits with respect to incidence, risk factors, reasons and post-ED disposition. We hypothesized that risk factors for unscheduled return and reasons for returning would differ from previous studies, due to differences in health care systems. Methods: All unscheduled return visits occurring within 1 week and related to the initial ED visit were selected. Multivariable logistic regression was conducted to determine independent factors associated with unscheduled return, using patient information available at the initial visit. Reasons for returning unscheduled were categorized into illness-, patient- or physician-related. Post-ED disposition was compared between patients with unscheduled return visits and the patients who did not return. Results: Five percent (n = 2,492) of total ED visits (n = 49,341) were unscheduled return visits. Patients with an urgent triage level, patients presenting during the night shift, with a wound or local infection, abdominal pain or urinary problems were more likely to return unscheduled. Reasons to revisit unscheduled were mostly illness-related (49%) or patient-related (41%). Admission rates for returning patients (16%) were the same as for the patients who did not return (17%). Conclusions: Apart from abdominal complaints, risk factors for unscheduled return differ from previous studies. Short-term follow-up at the outpatient clinic or general practitioner for patients with urgent triage levels and suffering from wounds or local infections, abdominal pain or urinary problem might prevent unscheduled return.

Background: Nearly all Dutch citizens have a general practitioner (GP), acting as a gatekeeper to secondary care. Some patients bypass the GP and present to the emergency department (ED). To make best use of existing emergency care, Dutch health policy makers and insurance companies have proposed the integration of EDs and GP cooperatives (GPCs) into one facility. In this study, we examined ED use and assessed the characteristics of self-referrals and non-self-referrals, their need for hospital emergency care and self-referrals' motives for presenting at the ED. Methods: A descriptive cohort study was conducted in a Dutch level 1 trauma centre. Differences in patient characteristics, time of presentation and need for hospital emergency care were analysed using χ² tests and t tests. A patient was considered to need hospital emergency care when he/she was admitted to the hospital, had an extremity fracture and/or when diagnostic tests were performed. Main determinants of self-referral were identified via logistic regression. Results: Of the 5,003 consecutive ED patients registering within the 5-week study period, 3,028 (60.5%) were self-referrals. Thirty-nine percent of the self-referrals had urgent acuity levels, as opposed to 65% of the non-self-referrals. Self-referrals more often suffered from injuries (49 vs. 20%). One third of the self-referrals presented during office hours. Of all self-referrals, 51% needed hospital emergency care. Younger age; non-urgent acuity level; chest pain, ear, nose or throat problems; and injuries were independent predictors for self-referral. Most cited motives for self-referring were ‘accessibility and convenience’ and perceived ‘medical necessity’. Conclusions: A substantial part of the self-referrals needed hospital emergency care. The 49% self-referrals who were eligible for GP care presented during out-of-hours as well as during office hours. This calls for an integrative approach to this health care problem.