The method is called the Functional Resonance Analysis Method, or FRAM, and it was created by safety researcher Erik Hollnagel to study complex sociotechnical systems in which humans, organizations, and technologies interact in ways that no flowchart can fully capture. Rather than describing a process as a fixed sequence of steps, FRAM represents it as a network of interdependent functions that can activate simultaneously and influence one another. Its central insight is that small, everyday variations in timing, resources, or behavior are normal and usually harmless, but when several of these variations align, they can resonate and amplify into major failures, much like structural resonance in engineering. In surgery, that resonance looks like a canceled operation caused by a sick nurse, a late pre-operative test, and an overrunning morning list all landing on the same day.

Traditional surgical process models, the formal or semi-formal representations used in computer-assisted surgery research, have struggled to capture this reality. Most focus narrowly on what happens inside the operating room, describe work as it is imagined in official protocols rather than work as it is actually done, and assume that workflows proceed sequentially. Real operating room management is nothing of the sort. It is a parallel, adaptive, multi-agent endeavor in which patients, residents, attending surgeons, and central patient management continuously negotiate and renegotiate the plan. The Munich team, led by Sidra Rashid of the MITI Research Group, argued that any scheduling model realistic enough to support AI-assisted planning must first capture this genuine complexity, and that FRAM offered a way to do it.

To build their model, the researchers spent months embedded in the visceral surgery department of University Hospital rechts der Isar. They conducted semi-structured interviews with twelve staff members, including central patient management staff, surgeons, residents, schedulers, coordinators, assistants, anesthetists, and nursing management, and complemented the interviews with direct shadowing during morning meetings, in operating rooms, and in informal staff interactions. This combination proved essential: the observations revealed informal practices and operational challenges that never surfaced in the formal interviews, such as surgeon preferences and meeting-based coordination, exactly the work-as-done details that conventional models omit.

From this evidence, the team constructed a FRAM model containing 98 unique interconnected functions spanning four central human agents, the patient, the medical resident, the attending surgeon, and central patient management, along with a fifth systemic agent representing the scheduling software infrastructure. Each function is described by six aspects: the input that triggers it, the output it produces, the preconditions that must be met, the resources it requires, the controls or rules that govern it, and the timing constraints that bound it. Functions are linked through these aspects, so that one function’s output becomes another’s input, resource, or precondition. This web of couplings is precisely how variability propagates through the system. The model was organized into four temporal phases, from the initial patient visit through the day of surgery, and validated iteratively with the interviewed staff.

The genuinely novel step came next. Using the FRAM Model Interpreter, a simulation tool that performs cycle-by-cycle analysis of which functions can activate, the team ran the model through ten simulation cycles, mapping each cycle onto the temporal phases of the scheduling process. They also introduced a structured interpretation protocol that assigns each function a profile specifying which inputs, preconditions, resources, and timing requirements must be satisfied for activation, using logical rules such as all, any, or none. Clinical functions like examining and consulting a patient demanded complete information before activating, while coordination functions like planning the surgical schedule used flexible profiles, reflecting the improvisational nature of real scheduling work. The researchers say this cycle-mapping interpretation approach had not been used in prior qualitative applications of FRAM.

The simulation results were revealing. The very first cycle activated 58 functions simultaneously, fourteen entry functions and forty-four background functions, underscoring how much of surgical scheduling begins in parallel rather than in sequence. Coordination functions such as planning the schedule and rescheduling surgeries activated repeatedly across multiple cycles, demonstrating that scheduling is iterative and adaptive rather than a one-time decision. Notably, a four-cycle gap emerged between the initial planning of the schedule in cycle four and the final provision of the daily schedule in cycle eight, a window filled with repeated team allocation, discussion, and adaptation that the analysis identified as the primary bottleneck in finalizing the schedule.

The simulation also exposed how disruptions compound. A disruptive entry function representing a staff member calling in sick recurred in cycles two, four, six, and eight, and each time it coincided with rescheduling and cancellation functions, tracing a direct causal pathway from staff unavailability to schedule upheaval. Three separate delay functions, originating with surgeons, patients, and residents, co-activated in multiple cycles, indicating that delays from different sources stack and amplify one another rather than occurring independently. This is functional resonance made visible: ordinary variability in several places at once producing an outsized systemic effect.

To move beyond qualitative description, the team applied FRAMalyse, an open-source analysis tool, to compute quantitative measures of variability across the coupling network. The Overall Functional Coupling Variability metric integrates network centrality measures, including Katz, in-closeness, out-closeness, and betweenness centrality, to rank functions by their potential to contribute to resonance. The results were unambiguous: allocating the operating room team showed the highest variability of any function in the entire model, burdened by a dense web of upstream dependencies including staff availability, surgery characteristics, team qualifications, documentation, and meeting outcomes, combined with constraints on training, skills, preferences, and shift composition. Attending surgeons performed the most functions overall, while central patient management showed the highest coupling density, reflecting its role in implementing decisions made by clinicians and patients. The patient visit phase emerged as the most functionally dense stage, where key surgical decisions are made through direct patient-surgeon interaction.

The authors are careful to note the limits of this first quantitative application. The model covers a single department in one hospital, the simulation represents just one possible instantiation of system behavior, and the weighting factors within the variability metric are not yet empirically validated, so the bottleneck ranking should be read as indicative rather than definitive. No external validation against observed disruption data has yet been performed. But the roadmap is ambitious: the team plans to validate the candidate bottlenecks against historical scheduling data, compare FRAM against alternative modeling formalisms such as BPMN and Petri nets, extend the model across the full perioperative pathway, integrate AI-based scheduling systems, and ultimately develop dynamic long-term simulations that could evolve into a digital twin of hospital operations. If that vision is realized, a safety method born in industrial risk analysis could become a predictive decision-support tool, helping hospitals design schedules that bend with reality instead of breaking under it.

Subject of Research: Quantitative application of the Functional Resonance Analysis Method to model surgical scheduling complexity and identify process bottlenecks

Article Title: Introducing FRAM as a tool for surgical process modeling: a case study for understanding surgical scheduling complexity

Article References: Rashid, S., Weber, R., Geiger, A., Wagner, L., Bernhard, L., Spicker, E., Jell, A., Fottner, J., Wilhelm, D., & Grabbe, N. (2026). Introducing FRAM as a tool for surgical process modeling: a case study for understanding surgical scheduling complexity. International Journal of Computer Assisted Radiology and Surgery. https://doi.org/10.1007/s11548-026-03800-2

Image Credits: AI Generated

DOI: 10.1007/s11548-026-03800-2

Keywords: FRAM, surgical scheduling, operating room management, surgical process modeling, functional resonance, hospital operations, variability propagation, bottleneck identification, sociotechnical systems, digital twin, computer-assisted surgery, patient safety

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, published in the journal Air Quality, Atmosphere & Health, was led by İbrahim Sarbay of Gaziosmanpaşa Training and Research Hospital in İstanbul together with colleagues at İzmir Katip Çelebi University. The team assembled daily emergency department visit counts from two tertiary hospitals, one in İstanbul and one in İzmir, spanning October 2023 through June 2025. After careful temporal alignment, 625 daily observations were available at each site. Alongside attendance figures, the researchers matched five meteorological variables: temperature, atmospheric pressure, humidity, wind speed, and precipitation. The goal was simple and ambitious: to test rigorously whether weather data add meaningful predictive power to forecasting models, or whether simpler, calendar-driven approaches suffice.

Methodologically, the study was designed as a genuine bake-off between statistical and machine-learning approaches. The authors first compared univariate forecasting models that used only the historical series of daily visits, then built multivariable models in four flavors: SARIMAX, a seasonal autoregressive integrated moving average framework that can absorb external predictors; dynamic regression, which models the target series as a function of calendar and weather covariates; and two ensemble tree methods, random forest and XGBoost, which are widely used in applied machine learning for tabular forecasting problems. Accuracy was measured with a battery of standard metrics, including root mean square error, mean absolute error, and the percentage-based measures MAPE, sMAPE, and MASE, which normalize error against a naive benchmark.

The statistical verdict was delivered with Diebold-Mariano tests, a formal method for deciding whether one forecast is significantly more accurate than another, rather than merely better by a rounding error. Robustness checks added further depth: rolling-origin validation, which repeatedly re-estimates models as new data arrive, mimicking real operational deployment; hyperparameter sensitivity analysis; ensemble averaging; and a cross-center generalization test in which models trained at one hospital were applied to the other.

The headline result is striking in its simplicity. Among univariate models, a neural network autoregression approach performed best in İstanbul, while the Theta method, a decomposition-based statistical forecaster, won in İzmir. But when calendar and weather covariates entered the picture, models relying on calendar structure alone delivered the best holdout accuracy in both cities. Dynamic regression achieved a mean absolute percentage error of 5.88 percent in İstanbul, and SARIMAX reached 4.42 percent in İzmir, both with calendar-only inputs. These are clinically meaningful accuracies, precise enough to inform staffing rosters and bed planning.

Weather augmentation, meanwhile, behaved erratically. In İstanbul, adding meteorological variables significantly worsened the SARIMAX and dynamic regression forecasts, with p-values of .013 and .015 respectively. The sole bright spot was XGBoost, where weather inputs produced a significant improvement, with p = .005. In İzmir, weather made no significant difference for any model. The authors are candid that the effect of weather is model- and center-specific, and that no universal weather dividend emerged.

Equally consequential is the finding that models do not travel. When a model tuned at one hospital was deployed at the other, errors ballooned severalfold, with mean absolute percentage errors climbing to roughly 39 percent. Local attendance culture, catchment demographics, hospital-specific referral patterns, and idiosyncratic scheduling apparently imprint themselves so deeply on each site’s demand curve that a model calibrated elsewhere is nearly useless. For health systems hoping to buy a single, generic forecasting product, this is a cautionary datapoint: locally tuned systems outperform imported ones.

There is an important caveat the authors themselves flag. In the holdout analyses where weather appeared to help, the models were fed observed future meteorological values as exogenous inputs. In a real operational setting, tomorrow’s weather is not observed but forecast, and forecast error would erode any weather advantage. The weather-augmented results therefore represent an idealized upper bound on the incremental value of meteorological information, not a fully prospective simulation of a live deployment.

The broader scientific context makes the finding less paradoxical than it first appears. Epidemiological literature has long documented links between ambient temperature and morbidity, seasonal patterns in respiratory viral infections, and correlations between weather and trauma admissions. Weather does influence health. But those influences are largely entangled with the seasons, and the calendar already encodes the seasons. Day-of-week effects, holidays, paydays, and seasonal disease waves explain most of the predictable variance in emergency demand, leaving little residual signal for humidity or wind speed to capture once the calendar is modeled properly.

For hospital operations, the practical message is clear and refreshingly frugal. Daily emergency department attendance can indeed be forecast with an accuracy useful for staffing and resource planning, with errors around four to six percent at both Turkish centers. But the winning ingredients are not exotic weather feeds or elaborate machine-learning pipelines; they are each hospital’s own attendance history and the disciplined use of calendar structure. The most valuable weather forecast for an emergency department, it turns out, may simply be the knowledge that the calendar rarely lies.

Subject of Research: Time-series forecasting of daily emergency department visit volume using calendar and meteorological variables

Article Title: Forecasting emergency department visit volume using meteorological variables: a multicenter time-series study

Article References: Forecasting emergency department visit volume using meteorological variables: a multicenter time-series study. (n.d.). https://doi.org/10.1007/s11869-026-02097-z

Image Credits: AI Generated

DOI: 10.1007/s11869-026-02097-z

Keywords: emergency department, forecasting, time series, meteorological variables, machine learning, SARIMAX, XGBoost, dynamic regression, calendar effects, hospital operations, Türkiye, emergency