The study, published in Global Surgical Education, the Journal of the Association for Surgical Education, emerged from a problem that will feel familiar to clinicians everywhere. Secure messaging embedded within the electronic medical record has become the standard channel for continuous communication among multidisciplinary teams, replacing pagers and phone calls with a searchable, auditable, and legally compliant record. Yet the same features that make these platforms attractive, their immediacy and their low barrier to sending a message, also make them prone to overuse. At the trauma center in question, investigators identified high secure chat volume and fragmented communication as concrete barriers to efficiency, resident education, and interprofessional collaboration between surgeons and nurses.

The consequences of message overload are not merely anecdotal. A growing body of research has linked electronic health record stress to clinician burnout, and studies of clinical decision support systems have documented how repeated alerts produce a phenomenon known as alert fatigue, in which users become desensitized to notifications and may begin ignoring them. Direct observation studies in emergency departments have shown that interruptions and multitasking are associated with task errors among physicians, while prospective observational research has tied workflow interruptions to increased workload for hospital doctors. For surgical residents, whose training depends on sustained engagement in the operating room and at the bedside, the stakes are particularly high: every ping during an operation or a teaching moment represents a potential disruption of intraoperative learning.

To understand the scale of the problem, the research team, led by Jackson A. Fos of the University of Tennessee Health Science Center College of Medicine in Chattanooga, together with colleagues at Erlanger Health, began with measurement rather than assumption. Baseline data were extracted from the electronic medical record’s secure chat logs over two separate 72-hour audit periods, providing a quantitative portrait of who was messaging whom, and how often, across the trauma surgery service. This audit-driven approach is a hallmark of rigorous quality improvement methodology: rather than relying on impressions of being overwhelmed, the team established an objective numerical baseline against which any intervention could be judged.

The intervention itself was designed by a multidisciplinary quality improvement team that included resident surgeons, advanced practice providers, and nursing leadership, ensuring that the people affected by the workflow shaped its redesign. The core insight was one of triage and routing: not every message directed at a resident needed to reach a resident. During daytime hours, defined as 06:00 to 16:00, nursing communications were rerouted to advanced practice providers rather than to the resident surgeons. The APPs, who are experienced clinicians embedded in the trauma service, would address messages falling within their scope of practice directly, and escalate only unresolved or genuinely resident-level concerns to the appropriate provider. This created a filtering layer that preserved the clinical content of communication while shielding trainees from routine traffic.

Rerouting messages was only one strand of a broader communication restructuring. The intervention package also included structured handoffs, which standardize the transfer of patient information between shifts and reduce the need for clarifying messages later in the day. Multidisciplinary rounds were enhanced, bringing nurses, APPs, and residents into the same physical conversation at the bedside so that questions could be answered synchronously rather than through asynchronous chat threads. Finally, the team delivered education on communication expectations, establishing shared norms about what belongs in a secure message, who should receive it, and when an alternative channel is more appropriate. A three-month implementation period was deliberately established before post-intervention audits, allowing the new workflow to bed in and avoiding the trap of measuring a system mid-transition.

The results, measured against the baseline audits, were substantial. Residents demonstrated a 27.7 percent reduction in the average number of messages received per 24-hour period. Nursing-related communications to residents fell by 35.9 percent, and during the targeted daytime window of 06:00 to 16:00, the nursing communications received by residents dropped by 31.3 percent. The authors attribute this daytime improvement to the APP management of routine concerns, enhanced communication during rounds, and improved utilization of the secure messaging platform itself. In other words, the intervention did not simply shift burden silently onto someone else’s shoulders; it changed how the whole team communicated, making the messaging system more purposeful for everyone involved.

What makes these findings resonate beyond a single trauma service is the way they reframe the problem of communication fatigue. Much of the discourse around electronic health records treats message volume as a byproduct of software design, something to be solved by vendors building better interfaces. This study suggests that a significant portion of the burden is organizational rather than technological. The same platform, with the same features, produced dramatically different message loads once the team clarified roles and routing. The intervention required no new software, no capital expenditure, and no change to the medical record itself, only a deliberate redistribution of communication responsibilities that leveraged the existing expertise of advanced practice providers.

The educational implications deserve particular attention. Surgical residency is built on apprenticeship, and the operating room is its most protected classroom. When residents are tethered to a buzzing device, answering routine questions about laboratory values or discharge logistics, the threads of intraoperative teaching unravel. By reducing message volume by more than a quarter, the workflow change returned a measurable slice of cognitive bandwidth to trainees during precisely the hours when most elective and trauma operations take place. The authors emphasize that these findings highlight the impact of communication restructuring on the resident workflow and the educational environment within academic surgical services, positioning message management as a matter of curriculum protection, not just administrative convenience.

There are also lessons here for interprofessional collaboration, an area where poorly designed communication systems can quietly breed friction. Nurses need timely responses to patient concerns; residents need uninterrupted focus; APPs occupy a clinical middle ground that is often underused as a communication hub. By formally recognizing APPs as the first point of contact for daytime nursing communications, the trauma center did not merely offload work, it clarified a professional role and, according to the study’s acknowledgements, the APPs’ willingness to assume an expanded role in frontline communication management was essential to the project’s success. The result was a system in which each message reached the person best positioned to act on it, the definition of communication efficiency in a complex clinical environment.

For hospital leaders watching message volumes climb on their own services, the study offers a replicable template: audit the actual traffic, convene a multidisciplinary team to identify workflow inefficiencies, reroute routine communications to appropriate intermediaries, standardize handoffs and rounds, set explicit communication expectations, and then wait through a genuine implementation period before measuring again. The 27.7 percent overall reduction and the 35.9 percent drop in nursing-related messages achieved in Chattanooga demonstrate that meaningful relief from message fatigue is achievable with modest, well-targeted changes. As secure messaging continues its spread through healthcare, the question is shifting from whether to use these platforms to how to use them well, and this study provides one of the clearest answers yet: less ping, more purpose.

Subject of Research: Reducing secure messaging burden and communication fatigue among surgical residents through workflow restructuring

Article Title: Less ping, more purpose: reducing message fatigue and boosting collaboration through secure chat optimization

Article References: Fos, J. A., Jones, J. M., Mezick, H. M., Rippy, M. G., Nunez, N., Buerster, K. B., Zeringue, A., Holder, L., Pairitz, M., Urevick, A., Cox, E. S., Spain, S., Holladay, J., Giles, W. H., & Bhattacharya, S. D. (2026). Less ping, more purpose: reducing message fatigue and boosting collaboration through secure chat optimization. Global Surgical Education – Journal of the Association for Surgical Education, 5(1), Article 187. https://doi.org/10.1007/s44186-026-00603-6

Image Credits: AI Generated

DOI: 10.1007/s44186-026-00603-6

Keywords: secure messaging, communication fatigue, surgical residency, electronic medical record, advanced practice providers, quality improvement, trauma surgery, interprofessional communication, resident education, workflow optimization, alert fatigue, multidisciplinary rounds

The central finding across all three investigations is that well-constructed clinical decision support tools can nudge clinicians toward evidence-based decisions without slowing them down. In the emergency department study, the research team evaluated a tool designed to help clinicians select an appropriate dose of an intravenous loop diuretic for patients arriving with acute decompensated heart failure. This class of medication removes excess fluid that accumulates when the failing heart cannot maintain adequate circulation, allowing the heart to pump more effectively and relieving the profound shortness of breath that drives these patients to seek emergency care in the first place. Clinical guidelines recommend that patients with acute decompensated heart failure receive at least twice the dose of diuretics they take at home when they arrive in the emergency department, a bolus strategy intended to achieve rapid decongestion. In practice, however, the relentless demands of a busy emergency department make it difficult for clinicians to quickly review home medication lists and adjust diuretic therapy accordingly, and recommended dosing is frequently missed.

To address this gap, the University of Michigan team implemented an interruptive alert within the electronic health record that fired when a patient showed signs of fluid overload or kidney dysfunction, prompting the treating clinician to consider guideline-recommended diuretic dosing. The alert was triggered in 223 patient encounters at the U-M Health Emergency Department. In nearly three-quarters of those cases, clinicians followed the recommended diuretic dosing after the alert appeared. Critically, the tool accomplished this without creating the kind of delay that often undermines the adoption of decision support systems: the median time from arrival at the emergency department to diuretic administration was roughly two hours in both groups, meaning the alert influenced the content of the treatment decision rather than its timing.

The researchers were careful to note the limits of what the study demonstrated. The investigation did not assess whether following the digital alerts improved downstream patient outcomes such as the amount of fluid removed or the length of hospital stay. Even so, the results establish something foundational for the field: the tools are easily used in a real clinical setting and measurably affect treatment decisions. As Sarah Adie, Pharm.D., a clinical cardiology pharmacy specialist at U-M Health and an author on all three studies, explained, this is a critical first step toward broad clinical adoption in settings that treat critically ill cardiac patients. Demonstrating feasibility and behavioral impact in a live emergency department environment is a prerequisite for the larger outcome trials that would justify deployment across many institutions.

The second study shifted the setting to the intensive care unit and examined sedation practices in more than 1,600 patients receiving mechanical ventilation in the cardiac and medical intensive care units. Deep sedation is common in intensive care, but leading cardiac and critical care society guidelines favor limiting its use, because prolonged heavy sedation may contribute to worse outcomes, including prolonged ventilator dependence and longer recovery. Changing sedation practice, however, is notoriously difficult, since it requires coordinated action from both physicians and nurses at the bedside, often under time pressure. The research team introduced an electronic health record-based intervention that encouraged the care team to use lighter sedation, surfacing the recommendation at the moment sedative decisions were being made.

The results were striking. After implementation, the average amount of time patients spent deeply sedated during the first 48 hours after intubation dropped in the cardiac intensive care unit from 16.8 hours to 12.4 hours, a reduction of more than four hours per patient. Nurses also reduced the continuous dose of commonly used sedatives, including fentanyl, propofol, midazolam and dexmedetomidine, in 23 percent of cases when the electronic health record generated an alert. These figures suggest that a well-timed digital prompt can shift entrenched practice patterns in an environment where clinicians are managing multiple simultaneous demands. As Anna Barker, M.D., Ph.D., a pulmonologist at University of Michigan Health and senior author of the light sedation paper, emphasized, the alerts are not designed to replace clinical judgment; rather, they are a tool delivered at high-pressure moments to assist clinicians with evidence-based guidance.

The third study tackled one of the most treacherous diagnostic challenges in cardiology: normotensive cardiogenic shock. This condition occurs when the heart cannot pump enough blood to the organs even though the patient’s blood pressure remains normal. Because cardiogenic shock is classically associated with low blood pressure, clinicians may fail to recognize that a normotensive patient is already in shock, and delays in diagnosis can be life threatening. The researchers implemented an electronic health record alert that identified patients displaying additional physiological signs of normotensive cardiogenic shock, such as subtle markers of hypoperfusion that might otherwise be overlooked, and facilitated direct communication with the shock team in the cardiac intensive care unit.

Clinicians engaged with the alert in 14 percent of cases, and those engagements were linked with higher rates of cardiac intensive care unit consultation within 12 hours. While the engagement rate may appear modest, the study illustrates a different design philosophy from the diuretic and sedation alerts: rather than prompting a medication decision, this alert functioned as a recognition and escalation tool, bridging the gap between a bedside clinician who may not suspect shock and a specialized team equipped to deploy advanced therapies. In conditions where early specialist involvement changes the trajectory of illness, even a low-frequency, high-value alert can be clinically meaningful.

Taken together, the three studies map how targeted electronic health record alerts can assist clinicians across the continuum of critical cardiac care, from the first hours in the emergency department through intensive care management. The design of each intervention differed according to the clinical problem. In the emergency department, the tool offered patient-specific recommendations at the moment the diuretic order was placed, embedding the guideline directly into the ordering workflow. In the two intensive care unit studies, alerts prompted clinicians to limit deep sedation or to escalate suspected shock cases to specialized critical care teams. In each case, the intervention respected the existing workflow rather than adding parallel tasks, which the researchers identify as a key principle: these clinical decision support tools are most useful when they help clinicians make the right decision in the moment, rather than adding more noise to already busy workflows, as Scott Ketcham, M.D., a cardiologist at the University of Michigan Health Frankel Cardiovascular Center and an author on all three studies, observed.

The researchers describe the work as proof of concept, and they are explicit that more must be done to ensure electronic alerts are beneficial without disrupting clinical workflow. Alert fatigue remains one of the most persistent problems in health information technology, as clinicians bombarded with low-value notifications learn to dismiss them reflexively, undermining even genuinely useful tools. The Michigan studies suggest a path forward: alerts that are triggered by specific clinical signals, deliver a single actionable recommendation, and arrive at the exact moment a decision is being made. The next step, according to Ketcham, is to evaluate these interventions across multiple health systems to better understand their impact on patient outcomes and determine how they can help improve the care of critically ill cardiac patients nationwide. If those multi-center evaluations confirm what these early studies hint at, the electronic health record, long criticized as a source of friction, may earn a new role as an active partner in the care of the sickest patients with heart disease.

Subject of Research: Electronic health record clinical decision support alerts for critically ill cardiac patients

Article Title: Digital alerts support timely treatment decisions of critically ill cardiac patients

Article References: Digital alerts support timely treatment decisions of critically ill cardiac patients. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: electronic health records, clinical decision support, acute decompensated heart failure, diuretics, cardiac intensive care, sedation, cardiogenic shock, emergency department, ventilators, alert fatigue, Michigan Medicine, patient outcomes

The core insight behind CLATS is that alert optimization is not purely a statistical problem; it is an operational one. Most deployed deterioration-warning systems rely on static or ad hoc thresholds set when the software is installed. But hospitals are not static environments. Patient case-mix shifts between winter and summer, staffing levels rise and fall across shifts, and the workload a unit can absorb on a Tuesday afternoon differs from what it can absorb at three in the morning. A threshold that keeps missed events acceptably rare during calm periods may flood the same unit with alerts during a surge, or vice versa. The researchers argue that any sensible alert policy must therefore balance two competing quantities that most systems treat separately: the sensitivity of the detector, meaning its ability to catch true deterioration events, and the workload burden it imposes on the clinical staff who must respond.

CLATS addresses this trade-off with a deliberately transparent architecture that the authors describe as auditable and deterministic. The system pairs a calibrated predictive model with a two-threshold, three-tier triage policy. Patients whose deterioration risk score exceeds the upper threshold L2 land in the highest-alert tier and trigger immediate attention. Patients scoring between the lower threshold L1 and L2 fall into a middle tier, and those below L1 require no action. This tiered structure matters because it lets the optimizer treat false positives with nuance: an alert that merely asks a nurse to glance at a chart costs far less than one that demands an emergency response team. Rather than counting every false alarm equally, CLATS assigns tiered false-positive costs, alongside explicit penalties for missed events and for system overload situations in which the volume of alerts exceeds what the ward can realistically process.

The machinery that makes this work is a penalized, operations-aware cost function. In essence, the optimizer searches for the pair of thresholds that minimizes a weighted sum of harm: the penalty for each missed deterioration event, the accumulated costs of false alarms in each tier, and the burden of overload. Crucially, the search operates under a hard constraint, a fixed sensitivity target that the system must never fall below, no matter how attractive the cost savings. This design decision reflects a clinical reality that pure cost-benefit mathematics can obscure: in medicine, missing a true deterioration event is generally far more dangerous than responding to a few extra false ones, so the safety floor is enforced structurally rather than traded away when convenient.

Technically, the optimization proceeds in two phases. Initial thresholds are determined on validation data using isotonic calibration, a non-parametric technique that maps raw model scores into well-calibrated probabilities by fitting a monotonic, non-decreasing function. Isotonic calibration is prized in clinical prediction because it makes no assumptions about the shape of the relationship between scores and outcomes and produces probabilities that can be trusted as genuine risk estimates. On top of those calibrated scores, a discrete grid search enumerates candidate threshold pairs and identifies the combination that minimizes the operations-aware cost. Grid search is a blunt but dependable instrument: because the space of threshold pairs is finite and enumerable, every decision the system makes can be traced, reproduced, and explained to a hospital governance committee, a property many black-box alternatives lack.

What distinguishes CLATS from a one-time tuning exercise is its closed loop. Once deployed, the system does not let its thresholds fossilize. Instead, it operates in review cycles, re-estimating the optimal thresholds as new data accumulates and as staffing and patient-population conditions shift. The refinement process uses exponential smoothing, which blends the newly computed thresholds with the previous values while weighting recent observations more heavily, and guardrail constraints, which bound how far thresholds may move in a single cycle. The guardrails are a safeguard against instability: a sudden data anomaly or transient shift in the ward could otherwise cause a wild threshold swing that disrupts clinical workflows. With smoothing and bounded updates, the system adapts gradually and predictably, in the spirit of stochastic learning and adaptive control rather than abrupt reconfiguration.

The evaluation reported in the paper is synthetic, and the authors are unusually explicit about what that means for interpretation. Working with simulated data and an isotonic-calibrated CatBoost model, a gradient-boosted decision tree method known for strong performance on tabular clinical data, CLATS maintained a sensitivity of at least 0.989 across the tested conditions. Under the controlled data-generating assumptions of the simulation, the system produced no false positive alerts, a result that must be read carefully: it validates the optimization mechanism itself, not clinical performance, because real hospital data contain noise, label ambiguity, and distribution shift that simulations rarely capture. The authors state plainly that these findings support the feasibility of the CLATS mechanism rather than constituting clinical evidence, a caveat that responsible readers should carry forward.

The more operationally interesting result concerns the closed-loop dynamics. During simulated re-optimization cycles, the adaptive threshold updates reduced the operational cost objective by an average of 4.6 percent per review cycle, without reducing recall in this setting. Compounded across repeated cycles, savings of that magnitude suggest that static thresholds leave meaningful efficiency on the table, particularly in environments where patient acuity and staffing fluctuate. Because the cost function explicitly encodes workload and overload penalties, the improvements translate conceptually into fewer disruptive alarms and less wasted clinical attention, precisely the resources that alarm fatigue squanders. Prior literature has linked clinician workload to patient safety outcomes, and operations-management research has long documented how overburdened staff experience degraded performance, giving the workload-aware formulation an empirical footing beyond simple intuition.

Several design choices position CLATS for eventual real-world adoption, even though that step awaits validation on genuine longitudinal clinical data. The framework is model-agnostic: the CatBoost predictor in the paper could be swapped for any sufficiently accurate deterioration model, since the optimization layer interacts only with calibrated risk scores. The system is also governance-compatible, offering a transparent, deterministic basis for decisions that hospital safety committees and regulators can inspect line by line. That transparency addresses a persistent obstacle in clinical artificial intelligence deployment. Studies of real-world sepsis prediction systems have shown that technical accuracy alone does not guarantee clinical uptake; integration into routine workflows, trust, and auditability often decide whether a predictive tool helps or gathers dust. A framework whose every threshold decision can be explained and reproduced speaks directly to those implementation barriers.

The research lands at a moment when healthcare institutions are actively searching for ways to tame alert burden, from remote patient monitoring programs to decision-support systems in intensive care, and the bibliography of the paper reflects that urgency, spanning early warning score evaluations, alert reduction frameworks, and reinforcement learning approaches to healthcare operations. CLATS contributes a specific and disciplined piece to that puzzle: not a new predictor, but a principled mechanism for turning any calibrated predictor into an operationally sustainable alert policy. The caveats remain clear. The results are synthetic, the data-generating assumptions are idealized, and the authors themselves, along with their funders at the Gust Engineering and Applied Innovation Research Center, frame the work as a foundation for future validation. If that future validation on real hospital data holds, closed-loop, operations-aware threshold optimization could become a standard layer in the clinical monitoring stack, quietly retuning the alarm systems that clinicians have learned, at their peril, to tune out.

Subject of Research: A closed-loop adaptive optimization framework for clinical deterioration alert thresholds

Article Title: CLATS: a closed-loop adaptive triage system for operations-aware clinical alert optimization

Article References: Alzhouri, F., Daraghmeh, M., Agarwal, A., & Ebrahimi, D. (2026). CLATS: a closed-loop adaptive triage system for operations-aware clinical alert optimization. Cluster Computing, 29(14), Article 793. https://doi.org/10.1007/s10586-026-06611-x

Image Credits: AI Generated

DOI: 10.1007/s10586-026-06611-x

Keywords: clinical alerts, alert fatigue, adaptive triage, machine learning, CatBoost, isotonic calibration, threshold optimization, hospital operations, sensitivity, closed-loop control, clinical decision support, predictive modeling

The research, led by L. Carpi of the University of Genova together with N. Oneto and M. Ferrari, tackles a deceptively simple question: which parts of a coastal town will waves actually reach during the worst storms? Answering it required reconstructing four decades of wave history. The team drew on a 43-year hindcast database maintained by the Department of Civil, Chemical and Environmental Engineering at Genoa, which contains numerical simulations of offshore wave conditions produced with the WaveWatchIII spectral wave model and the Weather Research and Forecasting atmospheric model. From the period between January 1979 and December 2022, the researchers selected the twenty largest storms arriving from the southeast and the twenty largest from the southwest, the two dominant and most destructive wave directions in the Ligurian Sea.

Simulating what those forty storms did when they reached the coast demanded an equally detailed picture of the seafloor and the land. Bathymetric data out to depths of twenty metres were collected with a multibeam echosounder offering centimetre-level resolution, while the beach and the seafront urban fabric were mapped with a LiDAR system mounted on an unmanned aerial vehicle. Offshore bathymetry came from regional government datasets. All of these sources were merged and interpolated into a high-resolution digital elevation model that captured not only the natural morphology but also the buildings, seawalls and narrow alleys that shape how floodwater moves through the town.

The heart of the modelling chain is XBeach, an open-source model that solves the time-dependent short wave action balance, roller energy equations and nonlinear shallow water equations, allowing it to reproduce wave groups, run-up and morphological change during storms. The researchers ran XBeach in surfbeat mode on a computational grid covering six square kilometres, with cell sizes shrinking to 2.5 metres in the coastal strip, fine enough to resolve the small streets and gaps between buildings through which water can surge. For storms from the southwest, which strike Camogli directly, XBeach alone proved sufficient. For storms from the southeast, however, the Portofino Promontory partially shelters the coast, and waves had to be translated to the offshore boundary of the model domain using D-Waves, the SWAN-based wave module of the Delft3D suite, applied over a grid of 115 square kilometres encompassing the promontory.

Validating the model posed a familiar problem: no field measurements exist for the historical storms of interest. The team therefore compared simulated significant wave heights and directions with measurements from an oceanographic buoy located inside the model domain during two events in May and August 2025. The agreement was strong. For the August event, the model achieved a coefficient of determination of 0.96, a correlation coefficient of 0.98 and a scatter index of just 0.16 for wave height, while wave direction errors, expressed as circular root-mean-square error, ranged from 12.0 to 19.6 degrees across the two events, figures comparable to those reported in other coastal wave-modelling applications. A second, more dramatic validation came from simulating the storm of 3 to 5 November 2023, which was not part of the exposure dataset. That southwest storm destroyed a beach restaurant built on stilts, and the model’s simulated maximum run-up of 2.6 metres reached precisely the location of the collapsed structure.

With the model chain validated, the researchers computed two run-up indicators for every storm along six coastal transects: the run-up exceeded by two percent of the waves, and the maximum run-up. The contrast between wave directions was stark. For the twenty most intense southeast storms, run-up values almost never exceeded 1.8 metres and typically stayed below 1.3 metres, never crossing the two-metre threshold that marks the elevation above which tourism infrastructure begins to be threatened. Camogli is, in effect, only marginally exposed to storms from that quadrant, a consequence of the sheltering geometry of the Portofino Promontory.

Southwest storms told a very different story. Maximum run-up exceeded two metres in nearly every simulated event, and in five storms the two-percent run-up reached between 2.4 and 2.6 metres. The outlier was the storm of 29 October 2018, widely known as the Vaia Storm, which produced run-up values between 3.89 and 5.28 metres for the two-percent parameter and between 4.94 and 5.72 metres for maximum run-up. It was the only event in the entire 43-year record that pushed waves above the three-metre threshold, corresponding roughly to the maximum beach elevation before the urban settlement begins, where flooding of the town itself becomes a concrete possibility. That finding is consistent with the documented damage from the event and underscores a central message of the study: only long-term wave datasets can capture the rare but catastrophic storms that dominate coastal risk.

The spatial pattern of exposure revealed an uncomfortable structural problem. In earlier work on the nearby bay of Bonassola, a medium exposure class had acted as a buffer zone between low and high exposure, allowing authorities to issue graduated warnings and phase in mitigation measures. Along more than half of the Camogli coastline, that buffer is absent. Exposure jumps directly from low to high, because the beach is only ten to fifteen metres wide, has the steep profile typical of gravel and pebble shores, and is backed immediately by seawalls and building walls that leave no room for a wider dissipative beach. Small variations in wave run-up therefore produce abrupt transitions in exposure level, a dynamic that complicates emergency management and increases the likelihood of frequent high-level alerts.

That abruptness carries a human cost that the authors address head-on. Warning systems that cry wolf too often breed alert fatigue, eroding public trust and responsiveness, while overly precautionary closures of commercial activities impose economic costs and damage institutional credibility. The study found that choosing the more conservative maximum run-up indicator over the two-percent parameter would have generated only one additional flood warning across the entire historical record, limiting the fatigue risk in this particular setting, though the authors stress that the choice of indicator must be evaluated case by case. Because risk perception is strongly shaped by direct personal experience, and because the missing buffer zone is rooted in geomorphology and urban form rather than in any fixable technical shortcoming, the researchers argue that targeted risk communication and community preparedness must complement the modelling work.

The implications stretch well beyond one Ligurian town. As sea levels rise, coastlines like Camogli, with narrow beaches, rocky margins, intense urbanisation up to the waterline and no capacity to migrate landward, are likely to face growing storm exposure, making accurate, site-specific hazard assessment increasingly urgent. The study also flags its own limits: reliable results depend on accurate, up-to-date topographic and bathymetric data, which human development can rapidly invalidate, and on long-term offshore wave datasets, which remain scarce where buoy networks are sparse. Hindcast databases fill that gap, but uncertainties in them can propagate through the modelling chain. Even so, the message is clear and broadly applicable: in crowded coastal towns where a single metre of elevation separates safety from flooding, high-resolution modelling of decades of historical storms is not a luxury but a prerequisite for evidence-based warning thresholds, sensible mitigation planning and, ultimately, the protection of lives and livelihoods.

Subject of Research: Storm-induced coastal exposure modelling using hindcast wave data in a densely urbanised coastal area

Article Title: Modelling storm-induced coastal exposure using hindcast wave data in a densely urbanised coastal area

Article References: Carpi, L., Oneto, N., & Ferrari, M. (2026). Modelling storm-induced coastal exposure using hindcast wave data in a densely urbanised coastal area. Natural Hazards, 122(20), Article 649. https://doi.org/10.1007/s11069-026-08420-2

Image Credits: AI Generated

DOI: 10.1007/s11069-026-08420-2

Keywords: coastal exposure, wave run-up, storm hindcast, XBeach, coastal flooding, Ligurian Riviera, wave modelling, risk assessment, alert fatigue, sea-level rise, digital elevation model, Natural Hazards