GCGiorgio Colangelo

Giorgio Colangelo

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Giorgio Colangelo has a total of 79 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Co-design of a trustworthy AI-based prognostic tool for predicting patient outcome in acute stroke

    by Elizabeth Hofvenschioeld, Adam Hilbert, Cathrine K. T. Bui, Susanne Bonekamp, Tess Buckley, Roberta Calegari, Luca A. Cappellini, Megan Coffee, Giorgio Colangelo, Boris Düdder, et al.

    This paper reports a descriptive, process-oriented case study of the application of Z-Inspection®, an ethically aligned co-design methodology, in the early design phase of an artificial intelligence (AI) system for healthcare. The methodology was applied within the Horizon Europe project VALIDATE [1], which develops and validates a prognostic clinical decision support system (CDSS) to support treatment decisions in acute ischaemic stroke. An interdisciplinary team of Z-Inspection® experts, AI developers, and clinical stakeholders jointly identified ethical, legal, and technical issues relevant to the planned system. The assessment resulted in 22 ethical issues, 12 dilemmas, 18 risks, and 48 derived requirements, each mapped to the European Commission’s trustworthy AI principles. The identified issues, dilemmas, risks, and derived requirements constitute the primary findings of this descriptive case study and document how general trustworthy-AI principles were translated into context-specific technical, clinical, governance, and organisational requirements. By documenting the process and publishing the complete requirements, the study provides a detailed case for critical scrutiny and potential uptake in other healthcare AI projects, though its transferability and scalability remain to be established in further studies.

  • Open Access

    HARMONICS: feasibility of a holistic value-based care hybrid programme that maximises clinical outcomes after stroke

    by Marta Rubiera, Alvaro Garcia-Tornel, Marian Muchada, Francisco Purroy, Joao Sargento-Freitas, Xavier Ustrell, Alejandro Bustamante, Yolanda Silva, Maria Dolors Alsina, Cristina Girao, et al.

    Introduction: The increasing number of stroke survivors underscores the need for coordinated post-discharge care and systematic outcome monitoring. HARMONICS aimed to provide standardised follow-up, integrating clinician-reported (CROMs) and patient-reported outcomes (PROMs) into a value-based care model. Patients and methods: Using lean methodology, post-stroke care pathways were mapped, and a harmonised workflow was implemented across 6 comprehensive stroke centres (CSCs) in Spain and Portugal. Consecutive patients discharged home or to socio-rehabilitation facilities with an mRS < 5 were offered participation. Follow-up was conducted via a smartphone app or telephone, enabling bidirectional communication with a case manager for health education, vital sign monitoring and PROMs collection. Feasibility required meeting 4 predefined indicators: inclusion > 60%, 3-month retention > 75%, PROMs completion > 60% and satisfaction > 70% measured by patient-reported experience measurement (PREM). Secondary analyses compared outcomes with historical cohorts. Results: Between 2022 and 2024, 4209 patients were recruited (40.2% women; median age 73 [IQR 62–81]; 75.6% ischaemic; median admission NIHSS 3 [1–6]; median discharge mRS 2 [1–3]). App use occurred in 59.9% (56% independently). Feasibility was achieved for inclusion (82.8%), retention (84.6%) and satisfaction (72.9%), but PROMs completion was 53.7% at 90 days. Despite mild severity, many reported suboptimal PROMs at 3 months, improving modestly by 1 year. Compared with historical controls, HARMONICS patients showed a better 3-month mRS distribution (OR 1.124; 95% CI, 1.042–1.213; P = .0026) and improved PROMs (P < .05). Discussion and Conclusion: HARMONICS is a feasible multicentre value-based follow-up model that promotes education, engagement and self-responsibility, with high rates of healthcare satisfaction reported by stroke survivors.

  • PRERISK: A Personalized, Artificial Intelligence–Based and Statistically–Based Stroke Recurrence Predictor for Recurrent Stroke

    by Giorgio Colangelo, Marc Ribo, Estefanía Montiel, Didier Dominguez, Marta Olivé-Gadea, Marian Muchada, Álvaro Garcia-Tornel, Manuel Requena, Jorge Pagola, Jesús Juega, et al.

    BACKGROUND: Predicting stroke recurrence for individual patients is difficult, but individualized prediction may improve stroke survivors’ engagement in self-care. We developed PRERISK: a statistical and machine learning classifier to predict individual risk of stroke recurrence. METHODS: We analyzed clinical and socioeconomic data from a prospectively collected public health care–based data set of 41 975 patients admitted with stroke diagnosis in 88 public health centers over 6 years (2014–2020) in Catalonia-Spain. A new stroke diagnosis at least 24 hours after the index event was considered as a recurrent stroke, which was considered as our outcome of interest. We trained several supervised machine learning models to provide individualized risk over time and compared them with a Cox regression model. Models were trained to predict early, late, and long-term recurrence risk, within 90, 91 to 365, and >365 days, respectively. C statistics and area under the receiver operating characteristic curve were used to assess the accuracy of the models. RESULTS: Overall, 16.21% (5932 of 36 114) of patients had stroke recurrence during a median follow-up of 2.69 years. The most powerful predictors of stroke recurrence were time from previous stroke, Barthel Index, atrial fibrillation, dyslipidemia, age, diabetes, and sex, which were used to create a simplified model with similar performance, together with modifiable vascular risk factors (glycemia, body mass index, high blood pressure, cholesterol, tobacco dependence, and alcohol abuse). The areas under the receiver operating characteristic curve were 0.76 (95% CI, 0.74–0.77), 0.60 (95% CI, 0.58–0.61), and 0.71 (95% CI, 0.69–0.72) for early, late, and long-term recurrence risk, respectively. The areas under the receiver operating characteristic curve of the Cox risk class probability were 0.73 (95% CI, 0.72–0.75), 0.59 (95% CI, 0.57–0.61), and 0.67 (95% CI, 0.66–0.70); machine learning approaches (random forest and AdaBoost) showed statistically significant improvement ( P <0.05) over the Cox model for the 3 recurrence time periods. Stroke recurrence curves can be simulated for each patient under different degrees of control of modifiable factors. CONCLUSIONS: PRERISK is a novel approach that provides a personalized and fairly accurate risk prediction of stroke recurrence over time. The model has the potential to incorporate dynamic control of risk factors.


  • Abstract TP178: AI Based Personalized Stroke Predictor For Patient Awareness And Treatment Compliance

    by Giorgio Colangelo, Estefania Montiel, Didier Herrera, Marc Ribo, Marta Rubiera, Carlos A Molina

    Personal prediction of stroke recurrence based on modifiable factors may enhance patient compliance to treatments and healthy lifestyles while optimizing resources of health centers. Vascular risk factors, socio-economic indicators and habits correlate with stroke morbidity and further recurrence. We aimed to estimate stroke recurrence probability as a function of time (3 months, < 1 year and > 1year), both at individual level and with larger classes of individuals. Clinical and socioeconomic public healthcare-based dataset of 41325 patients admitted with stroke diagnosis in 88 public hospitals over 6 years were analyzed. Overall, 8509 patients presented a stroke (one or more) recurrence (20.6%), with the following temporal distribution: 3 months, 1 year and > 1 year, 57%, 17% and 26% respectively. We developed a supervised-machine learning based study and identified modifiable and non-modifiable risk factors with stronger impact on risk of stroke recurrence. An algorithm able to provide individualized risk of stroke recurrence at 3 and 12 months was developed (AUROC = 0.80, for balanced classes). The risk can be continuously updated according to the status of modifiable risk factors. We also calculated the survival curve for each patient, to detect different risk recurrence periods along time. Download figure a) ROC curve for the three classes predicted. b) Feature importance to explain the model for features modifiable by the patient or notc) Probability over time of “No stroke recurrence” in an example patient according to optimal (orange) or poor (blue) control of vascular risk factors Machine learning analyses can improve risk prediction and offer individualized information to patients that can be used as feedback for secondary prevention strategies. Our approach is compatible with prevention strategies which, by continuous patient communication and feedbacks, make patients more likely to comply with treatment prescribed or lifestyle changes suggested.

  • Open Access

    Simultaneous tracking of spin angle and amplitude beyond classical limits

    by Giorgio Colangelo, Ferran Martin Ciurana, Lorena C. Bianchet, Robert J. Sewell, Morgan W. Mitchell

    Measurement of spin precession is central to extreme sensing in physics1,2, geophysics3, chemistry4, nanotechnology5 and neuroscience6, and underlies magnetic resonance spectroscopy7. Because there is no spin-angle operator, any measurement of spin precession is necessarily indirect, for example, it may be inferred from spin projectors at different times. Such projectors do not commute, and so quantum measurement back-action—the random change in a quantum state due to measurement—necessarily enters the spin measurement record, introducing errors and limiting sensitivity. Here we show that this disturbance in the spin projector can be reduced below N1/2—the classical limit for N spins—by directing the quantum measurement back-action almost entirely into an unmeasured spin component. This generates a planar squeezed state8 that, because spins obey non-Heisenberg uncertainty relations9,10, enables simultaneous precise knowledge of spin angle and spin amplitude. We use high-dynamic-range optical quantum non-demolition measurements11,12,13 applied to a precessing magnetic spin ensemble to demonstrate spin tracking with steady-state angular sensitivity 2.9 decibels below the standard quantum limit, simultaneously with amplitude sensitivity 7.0 decibels below the Poissonian variance14. The standard quantum limit and Poissonian variance indicate the best possible sensitivity with independent particles. Our method surpasses these limits in non-commuting observables, enabling orders-of-magnitude improvements in sensitivity for state-of-the-art sensing15,16,17,18 and spectroscopy19,20.


  • Real-time shot-noise-limited differential photodetection for atomic quantum control

    by F. Martin Ciurana, G. Colangelo, Robert J. Sewell, Morgan W. Mitchell

    We demonstrate high-efficiency, shot-noise-limited differential photodetection with real-time signal conditioning, suitable for feedback-based quantum control of atomic systems. The detector system has quantum efficiency of 0.92, is shot-noise-limited from 7.4×105 to 3.7×108 photons per pulse, and provides real-time voltage-encoded output at up to 2.3 M pulses per second.


  • Open Access

    Quantum Nondemolition Measurement Enables Macroscopic Leggett-Garg Tests

    by C. Budroni, G. Vitagliano, G. Colangelo, R. J. Sewell, O. Gühne, G. Tóth, M. W. Mitchell

    We show how a test of macroscopic realism based on Leggett-Garg inequalities (LGIs) can be performed in a macroscopic system. Using a continuous-variable approach, we consider quantum nondemolition (QND) measurements applied to atomic ensembles undergoing magnetically driven coherent oscillation. We identify measurement schemes requiring only Gaussian states as inputs and giving a significant LGI violation with realistic experimental parameters and imperfections. The predicted violation is shown to be due to true quantum effects rather than to a classical invasivity of the measurement. Using QND measurements to tighten the “clumsiness loophole” forces the stubborn macrorealist to recreate quantum backaction in his or her account of measurement.


  • Open Access

    Generation of Macroscopic Singlet States in a Cold Atomic Ensemble

    by N. Behbood, F. Martin Ciurana, G. Colangelo, M. Napolitano, Géza Tóth, R. J. Sewell, M. W. Mitchell

    A spin entangled system of more than a million laser cooled atoms has been created using spin measurements along three orthogonal axes \char21{} the first measurement-induced spin squeezing to a singlet state.


  • Open Access

    Ultrasensitive Atomic Spin Measurements with a Nonlinear Interferometer

    by R. J. Sewell, M. Napolitano, N. Behbood, G. Colangelo, F. Martin Ciurana, M. W. Mitchell

    Interferometry plays a key role in new technologies such as atomic clocks and optical magnetometers. Scientists experimentally confirm that nonlinear measurements of atomic spin achieve state-of-the-art sensitivities that surpass the best possible linear measurements.


  • Certified quantum non-demolition measurement of atomic spins

    by Robert Sewell, Mario Napolitano, Naeimeh Behbood, Georgio Colangelo, Ferran Martin Ciurana, Morgan W. Mitchell

    We report certified quantum non-demolition measurement of atomic spins using criteria developed for continuous variable experiments in optics. We observe quantum state preparation and information--damage trade--off beyond classical limits by seven and twelve standard deviations.