Radiomics of Intrahepatic Cholangiocarcinoma and Peritumoral Tissue Predicts Postoperative Survival: Development of a CT-Based Clinical-Radiomic Model.

BACKGROUND: For many tumors, radiomics provided a relevant prognostic contribution. This study tested whether the computed tomography (CT)-based textural features of intrahepatic cholangiocarcinoma (ICC) and peritumoral tissue improve the prediction of survival after resection compared with the standard clinical indices. METHODS: All consecutive patients affected by ICC who underwent hepatectomy at six high-volume centers (2009-2019) were considered for the study. The arterial and portal phases of CT performed fewer than 60 days before surgery were analyzed. A manual segmentation of the tumor was performed (Tumor-VOI). A 5-mm volume expansion then was applied to identify the peritumoral tissue (Margin-VOI). RESULTS: The study enrolled 215 patients. After a median follow-up period of 28 months, the overall survival (OS) rate was 57.0%, and the progression-free survival (PFS) rate was 34.9% at 3 years. The clinical predictive model of OS had a C-index of 0.681. The addition of radiomic features led to a progressive improvement of performances (C-index of 0.71, including the portal Tumor-VOI, C-index of 0.752 including the portal Tumor- and Margin-VOI, C-index of 0.764, including all VOIs of the portal and arterial phases). The latter model combined clinical variables (CA19-9 and tumor pattern), tumor indices (density, homogeneity), margin data (kurtosis, compacity, shape), and GLRLM indices. The model had performance equivalent to that of the postoperative clinical model including the pathology data (C-index of 0.765). The same results were observed for PFS. CONCLUSIONS: The radiomics of ICC and peritumoral tissue extracted from preoperative CT improves the prediction of survival. Both the portal and arterial phases should be considered. Radiomic and clinical data are complementary and achieve a preoperative estimation of prognosis equivalent to that achieved in the postoperative setting.

Flexible Approaches Based on Multistate Models and Microsimulation to Perform Real-World Cost-Effectiveness Analyses: An Application to Proprotein Convertase Subtilisin-Kexin Type 9 Inhibitors.

OBJECTIVES: This study aims to show the application of flexible statistical methods in real-world cost-effectiveness analyses applied in the cardiovascular field, focusing specifically on the use of proprotein convertase subtilisin-kexin type 9 inhibitors for hyperlipidemia. METHODS: The proposed method allowed us to use an electronic health database to emulate a target trial for cost-effectiveness analysis using multistate modeling and microsimulation. We formally established the study design and provided precise definitions of the causal measures of interest while also outlining the assumptions necessary for accurately estimating these measures using the available data. Additionally, we thoroughly considered goodness-of-fit assessments and sensitivity analyses of the decision model, which are crucial to capture the complexity of individuals' healthcare pathway and to enhance the validity of this type of health economic models. RESULTS: In the disease model, the Markov assumption was found to be inadequate, and a "time-reset" timescale was implemented together with the use of a time-dependent variable to incorporate past hospitalization history. Furthermore, the microsimulation decision model demonstrated a satisfying goodness of fit, as evidenced by the consistent results obtained in the short-term horizon compared with a nonmodel-based approach. Notably, proprotein convertase subtilisin-kexin type 9 inhibitors revealed their favorable cost-effectiveness only in the long-term follow-up, with a minimum willingness to pay of 39 000 Euro/life years gained. CONCLUSIONS: The approach demonstrated its significant utility in several ways. Unlike nonmodel-based or alternative model-based methods, it enabled to (1) investigate long-term cost-effectiveness comprehensively, (2) use an appropriate disease model that aligns with the specific problem under study, and (3) conduct subgroup-specific cost-effectiveness analyses to gain more targeted insights.

Patients' Radiation Exposure During Endovascular Abdominal Aortic Aneurysm Repair.

BACKGROUND: To investigate associations between patient characteristics, intraprocedural complexity factors, and radiation exposure to patients during endovascular abdominal aortic aneurysm repair (EVAR). METHODS: Elective standard EVAR procedures between January 2015 and December 2020 were retrospectively analyzed. Patient characteristics and intraprocedural data (i.e., type of device, endograft configuration, additional procedures, and contralateral gate cannulation time [CGCT]) were collected. Dose area product (DAP) and fluoroscopy time were considered as measurements of radiation exposure. Furthermore, effective dose (ED) and doses to internal organs were calculated using PCXMC 2.0 software. Descriptive statistics, univariable, and multivariable linear regression were applied to investigate predictors of increased radiation exposure. RESULTS: The 99 patients were mostly male (90.9%) with a mean age of 74 ± 7 years. EVAR indications were most frequently abdominal aortic aneurysm (93.9%), penetrating aortic ulceration (2.0%), focal dissection (2.0%), or subacute rupture of infrarenal abdominal aortic aneurysm (2.0%). Median fluoroscopy time was 19.6 minutes (interquartile range [IQR], 14.1-29.4) and median DAP was 86,311 mGy cm2 (IQR, 60,160-130,385). Median ED was 23.2 mSv (IQR, 17.0-34.8) for 93 patients (93.9%). DAP and ED were positively correlated with body mass index (BMI) and CGCT. Kidneys, small intestine, active bone marrow, colon, and stomach were the organs that received the highest equivalent doses during EVAR. Higher DAP and ED values were observed using the Excluder endograft, other bi- and tri-modular endografts, and EVAR with ≥2 additional procedures. Multivariable linear regression analysis revealed that BMI, ≥2 additional procedures during EVAR, and CGCT were independent positive predictors of DAP and ED levels after accounting for endograft type. CONCLUSIONS: Patient-related and procedure-related factors such as BMI, ≥2 additional procedures during EVAR, and CGCT resulted predictors of radiation exposure for patients undergoing EVAR, as quantified by higher DAP and ED levels. The main intraprocedural factor that increased radiation exposure was CGCT. These data can be of importance for better managing radiation exposure during EVAR.

Cost-effectiveness of single-pill and separate-pill administration of antihypertensive triple combination therapy: a population-based microsimulation study.

BACKGROUND: Single-pill combination (SPC) of three antihypertensive drugs has been shown to improve adherence to therapy compared with free combinations, but little is known about its long-term costs and health consequences. This study aimed to evaluate the lifetime cost-effectiveness profile of a three-drug SPC of an angiotensin-converting enzyme inhibitor, a calcium-channel blocker, and a diuretic vs the corresponding two-pill administration (a two-drug SPC plus a third drug separately) from the Italian payer perspective. METHODS: A cost-effectiveness analysis was conducted using multi-state semi-Markov modeling and microsimulation. Using the healthcare utilization database of the Lombardy Region (Italy), 30,172 and 65,817 patients aged ≥ 40 years who initiated SPC and two-pill combination, respectively, between 2015 and 2018 were identified. The observation period extended from the date of the first drug dispensation until death, emigration, or December 31, 2019. Disease and cost models were parametrized using the study cohort, and a lifetime microsimulation was applied to project costs and life expectancy for the compared strategies, assigning each of them to each cohort member. Costs and life-years gained were discounted by 3%. Probabilistic sensitivity analysis with 1,000 samples was performed to address parameter uncertainty. RESULTS: Compared with the two-pill combination, the SPC increased life expectancy by 0.86 years (95% confidence interval [CI] 0.61-1.14), with a mean cost differential of -€12 (95% CI -9,719-8,131), making it the dominant strategy (ICER = -14, 95% CI -€15,871-€7,113). The cost reduction associated with the SPC was primarily driven by savings in hospitalization costs, amounting to €1,850 (95% CI 17-7,813) and €2,027 (95% CI 19-8,603) for patients treated with the SPC and two-pill combination, respectively. Conversely, drug costs were higher for the SPC (€3,848, 95% CI 574-10,640 vs. €3,710, 95% CI 263-11,955). The cost-effectiveness profile did not significantly change according to age, sex, and clinical status. CONCLUSIONS: The SPC was projected to be cost-effective compared with the two-pill combination at almost all reasonable willingness-to-pay thresholds. As it is currently prescribed to only a few patients, the widespread use of this strategy could result in benefits for both patients and the healthcare system.

A NLP-based semi-automatic identification system for delays in follow-up examinations: an Italian case study on clinical referrals.

BACKGROUND: This study aims to propose a semi-automatic method for monitoring the waiting times of follow-up examinations within the National Health System (NHS) in Italy, which is currently not possible to due the absence of the necessary structured information in the official databases. METHODS: A Natural Language Processing (NLP) based pipeline has been developed to extract the waiting time information from the text of referrals for follow-up examinations in the Lombardy Region. A manually annotated dataset of 10 000 referrals has been used to develop the pipeline and another manually annotated dataset of 10 000 referrals has been used to test its performance. Subsequently, the pipeline has been used to analyze all 12 million referrals prescribed in 2021 and performed by May 2022 in the Lombardy Region. RESULTS: The NLP-based pipeline exhibited high precision (0.999) and recall (0.973) in identifying waiting time information from referrals' texts, with high accuracy in normalization (0.948-0.998). The overall reporting of timing indications in referrals' texts for follow-up examinations was low (2%), showing notable variations across medical disciplines and types of prescribing physicians. Among the referrals reporting waiting times, 16% experienced delays (average delay = 19 days, standard deviation = 34 days), with significant differences observed across medical disciplines and geographical areas. CONCLUSIONS: The use of NLP proved to be a valuable tool for assessing waiting times in follow-up examinations, which are particularly critical for the NHS due to the significant impact of chronic diseases, where follow-up exams are pivotal. Health authorities can exploit this tool to monitor the quality of NHS services and optimize resource allocation.

A Deep Survival EWAS approach estimating risk profile based on pre-diagnostic DNA methylation: An application to breast cancer time to diagnosis.

Previous studies for cancer biomarker discovery based on pre-diagnostic blood DNA methylation (DNAm) profiles, either ignore the explicit modeling of the Time To Diagnosis (TTD), or provide inconsistent results. This lack of consistency is likely due to the limitations of standard EWAS approaches, that model the effect of DNAm at CpG sites on TTD independently. In this work, we aim to identify blood DNAm profiles associated with TTD, with the aim to improve the reliability of the results, as well as their biological meaningfulness. We argue that a global approach to estimate CpG sites effect profile should capture the complex (potentially non-linear) relationships interplaying between sites. To prove our concept, we develop a new Deep Learning-based approach assessing the relevance of individual CpG Islands (i.e., assigning a weight to each site) in determining TTD while modeling their combined effect in a survival analysis scenario. The algorithm combines a tailored sampling procedure with DNAm sites agglomeration, deep non-linear survival modeling and SHapley Additive exPlanations (SHAP) values estimation to aid robustness of the derived effects profile. The proposed approach deals with the common complexities arising from epidemiological studies, such as small sample size, noise, and low signal-to-noise ratio of blood-derived DNAm. We apply our approach to a prospective case-control study on breast cancer nested in the EPIC Italy cohort and we perform weighted gene-set enrichment analyses to demonstrate the biological meaningfulness of the obtained results. We compared the results of Deep Survival EWAS with those of a traditional EWAS approach, demonstrating that our method performs better than the standard approach in identifying biologically relevant pathways.

Editor's Choice - Comparison of the Reproducibility of Ultrasound Calliper Placement Methods in Abdominal Aortic Diameter Measurements: A Systematic Review and Meta-Analysis of Diagnostic Test Accuracy Studies.

OBJECTIVE: To assess which ultrasound (US) method of maximum anteroposterior (AP) abdominal aortic diameter measurement can be considered most reproducible. DATA SOURCES: MEDLINE, Scopus, and Web of Science were searched (PROSPERO ID: 276694). Eligible studies reported intra- and or interobserver agreement according to Bland-Altman analysis (mean ± standard deviation [SD]) for abdominal aortic diameter AP US evaluations with an outer to outer (OTO), inner to inner (ITI), and or leading edge to leading edge (LELE) calliper placement. REVIEW METHODS: The Preferred Reporting Items for a Systematic Review and Meta-Analysis of Diagnostic Test Accuracy Studies statement was followed. The QUADAS-2 tool and QUADAS-C extension were used for risk of bias assessment and the GRADE framework to rate the certainty of evidence. Pooled estimates (fixed effects meta-analysis, after a test of homogeneity of means) for each US method were compared with pairwise one sided t tests. Sensitivity analyses (for studies published in 2010 or later) and meta-regression were also performed. RESULTS: 21 studies were included in the qualitative analysis. Twelve were eligible for quantitative analysis. Studies showed heterogeneity in the US model and transducer used, sex of participants, and observer professions, expertise, and training. Included studies shared a common mean for each US method (OTO: p = 1.0, ITI: p = 1.0, and LELE: p = 1.0). A pooled estimate of interobserver reproducibility for each US method was obtained, combining the mean ± SD (Bland-Altman analysis) from each study: OTO: 0.182 ± 0.440; ITI: 0.170 ± 0.554; and LELE: 0.437 ± 0.419. There were no statistically significant differences between the methods (OTO vs. ITI: p = .52, OTO vs. LELE: p = .069, ITI vs. LELE: p = .17). Considering studies published in 2010 and later, the pooled estimate for LELE was the smallest, without statistically significant differences between the methods. Despite the low risk of bias, the certainty of the evidence for both meta-analysed outcomes remained low. CONCLUSION: The interobserver reproducibility for OTO and ITI was 2.5 times smaller (indicating better reproducibility) than LELE; however, without statistically significant differences between the methods and low GRADE evidence certainty. Additional data are needed to validate these findings, while inherent differences between the methods need to be emphasised.

Capturing the variety of clinical pathways in patients with schizophrenic disorders through state sequences analysis.

BACKGROUND: Care pathways are increasingly being used to enhance the quality of care and optimize the use of resources for health care. Nevertheless, recommendations regarding the sequence of care are mostly based on consensus-based decisions as there is a lack of evidence on effective treatment sequences. In a real-world setting, classical statistical tools were insufficient to consider a phenomenon with such high variability adequately and have to be integrated with novel data mining techniques suitable for identifying patterns in complex data structures. Data-driven techniques can potentially support empirically identifying effective care sequences by extracting them from data collected routinely. The purpose of this study is to perform a state sequence analysis (SSA) to identify different patterns of treatment and to asses whether sequence analysis may be a useful tool for profiling patients according to the treatment pattern. METHODS: The clinical application that motivated the study of this method concerns the mental health field. In fact, the care pathways of patients affected by severe mental disorders often do not correspond to the standards required by the guidelines in this field. In particular, we analyzed patients with schizophrenic disorders (i.e., schizophrenia, schizotypal or delusional disorders) using administrative data from 2015 to 2018 from Lombardy Region. This methodology considers the patient's therapeutic path as a conceptual unit, composed of a succession of different states, and we show how SSA can be used to describe longitudinal patient status. RESULTS: We define the states to be the weekly coverage of different treatments (psychiatric visits, psychosocial interventions, and anti-psychotic drugs), and we use the longest common subsequences (dis)similarity measure to compare and cluster the sequences. We obtained three different clusters with very different patterns of treatments. CONCLUSIONS: This kind of information, such as common patterns of care that allowed us to risk profile patients, can provide health policymakers an opportunity to plan optimum and individualized patient care by allocating appropriate resources, analyzing trends in the health status of a population, and finding the risk factors that can be leveraged to prevent the decline of mental health status at the population level.

Detecting early signals of COVID-19 outbreaks in 2020 in small areas by monitoring healthcare utilisation databases: first lessons learned from the Italian Alert_CoV project.

BackgroundDuring the COVID-19 pandemic, large-scale diagnostic testing and contact tracing have proven insufficient to promptly monitor the spread of infections.AimTo develop and retrospectively evaluate a system identifying aberrations in the use of selected healthcare services to timely detect COVID-19 outbreaks in small areas.MethodsData were retrieved from the healthcare utilisation (HCU) databases of the Lombardy Region, Italy. We identified eight services suggesting a respiratory infection (syndromic proxies). Count time series reporting the weekly occurrence of each proxy from 2015 to 2020 were generated considering small administrative areas (i.e. census units of Cremona and Mantua provinces). The ability to uncover aberrations during 2020 was tested for two algorithms: the improved Farrington algorithm and the generalised likelihood ratio-based procedure for negative binomial counts. To evaluate these algorithms' performance in detecting outbreaks earlier than the standard surveillance, confirmed outbreaks, defined according to the weekly number of confirmed COVID-19 cases, were used as reference. Performances were assessed separately for the first and second semester of the year. Proxies positively impacting performance were identified.ResultsWe estimated that 70% of outbreaks could be detected early using the proposed approach, with a corresponding false positive rate of ca 20%. Performance did not substantially differ either between algorithms or semesters. The best proxies included emergency calls for respiratory or infectious disease causes and emergency room visits.ConclusionImplementing HCU-based monitoring systems in small areas deserves further investigations as it could facilitate the containment of COVID-19 and other unknown infectious diseases in the future.

Mapping Tumor Heterogeneity via Local Entropy Assessment: Making Biomarkers Visible.

Advanced imaging and analysis improve prediction of pathology data and outcomes in several tumors, with entropy-based measures being among the most promising biomarkers. However, entropy is often perceived as statistical data lacking clinical significance. We aimed to generate a voxel-by-voxel visual map of local tumor entropy, thus allowing to (1) make entropy explainable and accessible to clinicians; (2) disclose and quantitively characterize any intra-tumoral entropy heterogeneity; (3) evaluate associations between entropy and pathology data. We analyzed the portal phase of preoperative CT of 20 patients undergoing liver surgery for colorectal metastases. A three-dimensional core kernel (5 × 5 × 5 voxels) was created and used to compute the local entropy value for each voxel of the tumor. The map was encoded with a color palette. We performed two analyses: (a) qualitative assessment of tumors' detectability and pattern of entropy distribution; (b) quantitative analysis of the entropy values distribution. The latter data were compared with standard Hounsfield data as predictors of post-chemotherapy tumor regression grade (TRG). Entropy maps were successfully built for all tumors. Metastases were qualitatively hyper-entropic compared to surrounding parenchyma. In four cases hyper-entropic areas exceeded the tumor margin visible at CT. We identified four "entropic" patterns: homogeneous, inhomogeneous, peripheral rim, and mixed. At quantitative analysis, entropy-derived data (percentiles/mean/median/root mean square) predicted TRG (p < 0.05) better than Hounsfield-derived ones (p = n.s.). We present a standardized imaging technique to visualize tumor heterogeneity built on a voxel-by-voxel entropy assessment. The association of local entropy with pathology data supports its role as a biomarker.

PET/CT-based radiomics of mass-forming intrahepatic cholangiocarcinoma improves prediction of pathology data and survival.

PURPOSE: Intrahepatic cholangiocarcinoma (IHC) is an aggressive disease with few reliable preoperative biomarkers. This study aims to elucidate if radiomics extracted from preoperative [18F]FDG PET/CT may grant a non-invasive biological characterization of IHC and predict outcome after complete resection of the tumor. METHODS: All patients preoperatively imaged by [18F]FDG PET/CT who underwent hepatectomy for mass-forming IHC in the period 2010-2019 were retrospectively evaluated. On PET images, manual slice-by-slice segmentation of IHC was performed (Tumor-VOI). A 5-mm margin region was semi-automatically generated around the tumor (Margin-VOI). Textural analysis was performed using the LifeX software. Analyzed outcomes included tumor grading (G3 vs. G1-2), microvascular invasion (MVI), overall survival (OS), and progression-free survival (PFS). The performances of the combined clinical-radiomic models were compared with those of standard clinical models. RESULTS: Overall, 74 patients (40 females, median age 68 years) were included. Considering tumor grading and MVI, the models combining the clinical data and radiomics of the Tumor-VOI had better performances than the clinical ones (AUC = 0.78 vs. 0.72 for grading; 0.87 vs. 0.78 for MVI). The inclusion into the models of radiomics of the Margin-VOI further improved the prediction of grading (AUC = 0.83), but not of MVI. Considering OS and PFS, the models including the preoperative clinical data and radiomics of the Tumor-VOI and Margin-VOI had better performances than the pure clinical ones (C-index = 0.81 vs. 0.76 for OS; 0.81 vs. 0.72 for PFS) and similar to the models including the pathology and postoperative data (C-index = 0.81 for OS; 0.79 for PFS). No model retained the standard SUV measures. CONCLUSION: The PET-based radiomics of IHC can predict pathology data and allow a reliable preoperative evaluation of prognosis. The radiomics of both the tumoral and peritumoral areas had clinical relevance. The combined clinical-radiomic models outperformed the pure preoperative clinical ones and achieved performances non-inferior to the postoperative models.

Oligoscore: a clinical score to predict overall survival in patients with oligometastatic disease treated with stereotactic body radiotherapy.

BACKGROUND: to find clinical features that can predict prognosis in patients with oligometastatic disease treated with stereotactic body radiotherapy (SBRT). MATERIAL AND METHODS: Patients with less than 5 metastases in less than 3 different body sites were included in the analysis. Various clinical and treatment parameters were analyzed to create a Cox proportional hazard model for Overall Survival (OS). Subsequently, significant variables were used to create a score. RESULTS: 997 patients were analyzed. Median OS was 2.61 years, 1 and 3 years OS was respectively 85% and 43%. Location of the primary tumor, performance status, site of irradiated metastases, presence of extratarget non irradiated lesions and RT dose were significant prognostic factors for OS. These parameters were used to create a score and to distinguish three different classes, with median OS of 5.67 years in low risk, 2.47 years in intermediate risk and 1.82 years in high risk group. CONCLUSION: moving from easily accessible clinical parameters, a score was created to help the physician's decision about the better treatment or combination of treatments for the individual patient.

Non-parametric frailty Cox models for hierarchical time-to-event data.

We propose a novel model for hierarchical time-to-event data, for example, healthcare data in which patients are grouped by their healthcare provider. The most common model for this kind of data is the Cox proportional hazard model, with frailties that are common to patients in the same group and given a parametric distribution. We relax the parametric frailty assumption in this class of models by using a non-parametric discrete distribution. This improves the flexibility of the model by allowing very general frailty distributions and enables the data to be clustered into groups of healthcare providers with a similar frailty. A tailored Expectation-Maximization algorithm is proposed for estimating the model parameters, methods of model selection are compared, and the code is assessed in simulation studies. This model is particularly useful for administrative data in which there are a limited number of covariates available to explain the heterogeneity associated with the risk of the event. We apply the model to a clinical administrative database recording times to hospital readmission, and related covariates, for patients previously admitted once to hospital for heart failure, and we explore latent clustering structures among healthcare providers.

Joint modeling of recurrent events and survival: a Bayesian non-parametric approach.

Heart failure (HF) is one of the main causes of morbidity, hospitalization, and death in the western world, and the economic burden associated with HF management is relevant and expected to increase in the future. We consider hospitalization data for HF in the most populated Italian Region, Lombardia. Data were extracted from the administrative data warehouse of the regional healthcare system. The main clinical outcome of interest is time to death and research focus is on investigating how recurrent hospitalizations affect the time to event. The main contribution of the article is to develop a joint model for gap times between consecutive rehospitalizations and survival time. The probability models for the gap times and for the survival outcome share a common patient specific frailty term. Using a flexible Dirichlet process model for %Bayesian nonparametric prior as the random-effects distribution accounts for patient heterogeneity in recurrent event trajectories. Moreover, the joint model allows for dependent censoring of gap times by death or administrative reasons and for the correlations between different gap times for the same individual. It is straightforward to include covariates in the survival and/or recurrence process through the specification of appropriate regression terms. The main advantages of the proposed methodology are wide applicability, ease of interpretation, and efficient computations. Posterior inference is implemented through Markov chain Monte Carlo methods.

Dynamic monitoring of the effects of adherence to medication on survival in heart failure patients: A joint modeling approach exploiting time-varying covariates.

Adherence to medication is the process by which patients take their drugs as prescribed, and represents an issue in pharmacoepidemiological studies. Poor adherence is often associated with adverse health conditions and outcomes, especially in case of chronic diseases such as heart failure (HF). This turns out in an increased request for health care services, and in a greater burden for the health care system. In recent years, there has been a substantial growth in pharmacotherapy research, aimed at studying effects and consequences of proper/improper adherence to medication both for the increasing awareness of the problem and for the pervasiveness of poor adherence among patients. However, the way adherence is computed and accounted for into predictive models is far from being informative as it may be. In fact, it is usually analyzed as a fixed baseline covariate, without considering its time-varying behavior. The purpose and novelty of this study is to define a new personalized monitoring tool exploiting time-varying definition of adherence to medication, within a joint modeling approach. In doing so, we are able to capture and quantify the association between the longitudinal process of dynamic adherence to medication with the long-term survival outcome. Another novelty of this approach consists of exploiting the potential of health care administrative databases in order to reconstruct the dynamics of drugs consumption through pharmaceutical administrative registries. In particular, we analyzed administrative data provided by Regione Lombardia - Healthcare Division related to patients hospitalized for HF between 2000 and 2012.

Functional modeling of recurrent events on time-to-event processes.

In clinical practice, it is often the case where the association between the occurrence of events and time-to-event outcomes is of interest; thus, it can be modeled within the framework of recurrent events. The purpose of our study is to enrich the information available for modeling survival with relevant dynamic features, properly taking into account their possibly time-varying nature, as well as to provide a new setting for quantifying the association between time-varying processes and time-to-event outcomes. We propose an innovative methodology to model information carried out by time-varying processes by means of functional data, modeling each time-varying variable as the compensator of marked point process the recurrent events are supposed to derive from. By means of Functional Principal Component Analysis, a suitable dimensional reduction of these objects is carried out in order to plug them into a Cox-type functional regression model for overall survival. We applied our methodology to data retrieved from the administrative databases of Lombardy Region (Italy), related to patients hospitalized for Heart Failure (HF) between 2000 and 2012. We focused on time-varying processes of HF hospitalizations and multiple drugs consumption and we studied how they influence patients' overall survival. This novel way to account for time-varying variables allowed to model self-exciting behaviors, for which the occurrence of events in the past increases the probability of a new event, and to quantify the effect of personal behaviors and therapeutic patterns on survival, giving new insights into the direction of personalized treatment.

Evaluating the effect of healthcare providers on the clinical path of heart failure patients through a semi-Markov, multi-state model.

BACKGROUND: Investigating similarities and differences among healthcare providers, on the basis of patient healthcare experience, is of interest for policy making. Availability of high quality, routine health databases allows a more detailed analysis of performance across multiple outcomes, but requires appropriate statistical methodology. METHODS: Motivated by analysis of a clinical administrative database of 42,871 Heart Failure patients, we develop a semi-Markov, illness-death, multi-state model of repeated admissions to hospital, subsequent discharge and death. Transition times between these health states each have a flexible baseline hazard, with proportional hazards for patient characteristics (case-mix adjustment) and a discrete distribution for frailty terms representing clusters of providers. Models were estimated using an Expectation-Maximization algorithm and the number of clusters was based on the Bayesian Information Criterion. RESULTS: We are able to identify clusters of providers for each transition, via the inclusion of a nonparametric discrete frailty. Specifically, we detect 5 latent populations (clusters of providers) for the discharge transition, 3 for the in-hospital to death transition and 4 for the readmission transition. Out of hospital death rates are similar across all providers in this dataset. Adjusting for case-mix, we could detect those providers that show extreme behaviour patterns across different transitions (readmission, discharge and death). CONCLUSIONS: The proposed statistical method incorporates both multiple time-to-event outcomes and identification of clusters of providers with extreme behaviour simultaneously. In this way, the whole patient pathway can be considered, which should help healthcare managers to make a more comprehensive assessment of performance.

Data mining application to healthcare fraud detection: a two-step unsupervised clustering method for outlier detection with administrative databases.

BACKGROUND: The healthcare sector is an interesting target for fraudsters. The availability of a great amount of data makes it possible to tackle this issue with the adoption of data mining techniques, making the auditing process more efficient and effective. This research has the objective of developing a novel data mining model devoted to fraud detection among hospitals using Hospital Discharge Charts (HDC) in Administrative Databases. In particular, it is focused on the DRG upcoding practice, i.e., the tendency of registering codes for provided services and inpatients health status so to make the hospitalization fall within a more remunerative DRG class. METHODS: We propose a two-step algorithm: the first step entails kmeans clustering of providers to identify locally consistent and locally similar groups of hospitals, according to their characteristics and behavior treating a specific disease, in order to spot outliers within this groups of peers. An initial grid search for the best number of features to be selected (through Principal Feature Analysis) and the best number of local groups makes the algorithm extremely flexible. In the second step, we propose a human-decision support system that helps auditors cross-validating the identified outliers, analyzing them w.r.t. fraud-related variables, and the complexity of patients' casemix they treated. The proposed algorithm was tested on a database relative to HDC collected by Regione Lombardia (Italy) in a time period of three years (2013-2015), focusing on the treatment of Heart Failure. RESULTS: The model identified 6 clusters of hospitals and 10 outliers among the 183 units. Out of those providers, we report the in depth the application of Step Two on three Hospitals (two private and one public). Cross-validating with the patients' population and the hospitals' characteristics, the public hospital seemed justified in its outlierness, while the two private providers were deemed interesting for a further investigation by auditors. CONCLUSIONS: The proposed model is promising in identifying anomalous DRG coding behavior and it is easily transferrable to all diseases and contexts of interest. Our proposal contributes to the limited literature regarding behavioral models for fraud detection, identifying the most 'cautious' fraudsters. The results of the first and the second Steps together represent a valuable set of information for auditors in their preliminary investigation.

Adherence to recommendations and clinical outcomes of patients hospitalized for stroke: the role of the admission ward-a real-life investigation from Italy.

OBJECTIVE: To determine whether out-of-hospital healthcare and adverse outcomes are better in stroke patients admitted to a neurology ward compared with those admitted to general wards. METHODS: Beneficiaries of the National Health Service from the Italian Lombardy Region who were discharged alive after hospital admission during the year 2009 for ischemic stroke (9776 patients) or intracerebral or subarachnoid hemorrhage (1102 patients) entered into the cohort and were followed until 2012. Exposure of interest was the ward type where inpatients were admitted (neuro vs. general wards). Outcomes were out-of-hospital healthcare (i.e., drug prescriptions, diagnostic procedures, and laboratory clinical evaluations) and adverse clinical outcomes (i.e., all-cause death and hospital readmission). Exposure-outcome associations were investigated. High-dimensional propensity score methodology was used for taking into account confounders. Mediation analysis was used to verify whether the association between ward type and clinical outcomes is mediated by out-of-hospital adherence to healthcare. RESULTS: Better adherence to out-of-hospital healthcare received from patients discharged from neuro, rather than general, wards was observed being the proportions of adherent patients 42.4% and 39.5%, respectively. Compared with general wards, discharge from neuro was associated with reduced 3-year emergency admissions (from 50.1 to 47.5% among ischemic stroke patients) and reduced 3-year mortality (from 37.5 to 27.0% among hemorrhagic stroke patients). From 10 to 15% of outcome risk, reductions were mediated by better adherence to out-of-hospital healthcare. CONCLUSIONS: For patients with acute ischemic and hemorrhagic stroke, admission to neuro vs. general wards is associated with better out-of-hospital healthcare and long-term adverse outcomes.

Urn models for response-adaptive randomized designs: a simulation study based on a non-adaptive randomized trial.

Recently, response-adaptive designs have been proposed in randomized clinical trials to achieve ethical and/or cost advantages by using sequential accrual information collected during the trial to dynamically update the probabilities of treatment assignments. In this context, urn models-where the probability to assign patients to treatments is interpreted as the proportion of balls of different colors available in a virtual urn-have been used as response-adaptive randomization rules. We propose the use of Randomly Reinforced Urn (RRU) models in a simulation study based on a published randomized clinical trial on the efficacy of home enteral nutrition in cancer patients after major gastrointestinal surgery. We compare results with the RRU design with those previously published with the non-adaptive approach. We also provide a code written with the R software to implement the RRU design in practice. In detail, we simulate 10,000 trials based on the RRU model in three set-ups of different total sample sizes. We report information on the number of patients allocated to the inferior treatment and on the empirical power of the t-test for the treatment coefficient in the ANOVA model. We carry out a sensitivity analysis to assess the effect of different urn compositions. For each sample size, in approximately 75% of the simulation runs, the number of patients allocated to the inferior treatment by the RRU design is lower, as compared to the non-adaptive design. The empirical power of the t-test for the treatment effect is similar in the two designs.