Emilia-Romagna Region Italy Research Articles

Scaling up integrated care: Can community hospitals be an answer? A multiple-case study from the Emilia-Romagna region in Italy

Integrated care is considered to be essential in improving care for people with chronic conditions who need continuous care. In 2022, the Italian Government asked all regions to build or renovate a massive number of community care facilities, employing European Next Generation funds, to be spent by 2026. Under the theoretical lens of the Structural Contingency Theory, the paper aims at aims at describing the contextual and organizational factors underlying the interconnection between integrated care and community hospitals. The study employs a multiple-case study design, relying both on quantitative and qualitative data, conducted in a 6 months-period. It investigated seven community hospitals belonging to a single Local Health Authority in Emilia-Romagna region in Italy. The choice of the empirical context was driven by Emilia-Romagna's long- and well-established tradition of community-based care. Overall, our analysis shows that community hospitals offers opportunities of integrated care, including better integration between care sectors, between primary care and specialist staff, between healthcare structures and their local community. The study confirms the value of the Structural Contingency Theory and its key message: implementation is not a mechanical step of the policy cycle and requires important adjustments to the planning phase according to environment and organizational factors.

The association between surgical complications and compliance to the World Health Organization Surgical Safety Checklist: A retrospective analysis of hospital records.

The World Health Organization Surgical Safety Checklist (SSC), now used by healthcare providers worldwide, has proved to be useful in the improvement of patients' health through the reduction of mortality and morbidity after surgery. In the Emilia-Romagna region in Italy the SSC is accompanied by a document that registers any non-conformity (NC) identified during SSC completion. This study aimed to investigate the association between surgical complications and checklist compliance, in terms of incompleteness and presence of NCs, using data from the Modena Local Health Unit (LHU). We used data from surgeries performed in the Modena LHU between 2018 and 2022, with their SSC and related NC document. We estimated relative risks (RRs) of complications fitting three modified Poisson regression models. Model 1 included checklist incompleteness and NC presence, Model 2 adjusted Model 1 for patients' sex and age group, and Model 3 adjusted Model 2 for the other potential confounders. We also performed a sensitivity analysis estimating the same three models including death outcomes as complications. We found an increased risk of complications for both checklist incompleteness (unadjusted RR [uRR]= 2.04; 95% confidence interval [CI]: 1.17 to 3.54) and presence of NCs (uRR = 2.35; 95% CI: 1.71 to 3.22). Results were consistent after adjustment and in the sensitivity analysis. Improving checklist compliance can reduce the risk of surgical complications. In particular, NCs are a risk factor that must be further investigated to better understand their relationship with complications. We believe that NCs data recording is helpful for both researchers in the scope of surgical complications, and healthcare professionals in the operating room.

Comparative analysis of conventional and machine learning techniques for rainfall threshold evaluation under complex geological conditions

This research focuses on the essential task of defining rainfall thresholds in regions with complex geological features, specifically at a regional scale. It examines a variety of methodologies, from traditional empirical-statistical methods to cutting-edge machine learning (ML) techniques, for establishing these thresholds. The Emilia-Romagna region in Italy, known for its intricate geological structure and prevalence of weak rocks that often lead to large and deep-seated landslides, serves as the study area. The region’s complex interplay between rainfall and landslide incidences poses a significant challenge in accurately determining rainfall thresholds. The effectiveness of ML methods is compared against conventional empirical-statistical approaches, evaluating factors such as prediction accuracy, model complexity, and the interpretability of results for use by regional landslide warning system operators. The findings indicate that machine learning techniques have an edge over traditional methods, yielding higher performance scores and fewer false positives. Nevertheless, these advancements are modest when considering the increased complexity of ML methods and the incorporation of additional rainfall parameters. This underlines the continued need for improvements in data quality and volume. The study stresses the importance of enhancing data collection and analysis techniques, especially in an era where advanced AI tools are increasingly available, to improve the accuracy of predicting rainfall thresholds for effective landslide warning systems.

First report of postharvest pear bitter rot caused by Colletotrichum acutatum in Italy.

The fungal genus Colletotrichum includes numerous important plant pathogenic species, some of which causes fruit bitter rot as well as leaf lesions (leaf black spot) on major crops, leading to yield losses (Fu et al. 2019; Talhinhas & Baroncelli, 2023). C. acutatum was reported associated with black spot on fallen, immature fruit of pear (Pyrus pyrifolia) in New Zealand (Damm et al. 2012); however, to our knowledge, this species has not been reported in Italy or nowhere else. In 2022, a significant increase of anthracnose symptoms was observed on pears in Emilia-Romagna region, Italy. Symptoms, such as round brown lesions of 1 to 4 cm, appeared on more than 50% of refrigerated stored fruit. These symptoms were undetectable at the end of September 2022 and appeared after a five-month period of storage (February 2023) at 4°C (e-Xtra 1A and B). Fungal isolates were obtained from symptomatic pears after surfaces sterilization with 96% ethanol by culturing necrotic tissue pieces on Potato Dextrose Agar at 25°C in the dark (e-Xtra 1C and D). Cultures were shades of coral color, from opalescent to sunkist coral, with slight aerial mycelium becoming grey and darker with age. When observed from the reverse side, the color was pink and, with age, became coral orange to dark amaranth. Conidia observed with a light microscope appeared hyaline and fusiform, 8 to 16 × 2.5 to 4 μm, with two pointed ends or one rounded end. (e-Xtra 1E) One reference isolate, named L51, was used for molecular characterization. Total genomic DNA was extracted, and the ITS region of rDNA amplified using the universal primers ITS1 and ITS4, then sequenced. The resulting sequences were 100% identical to those of C. acutatum (NR_144794.1: strain CBS 112996 ITS region; from TYPE material). Based on Damm et al. (2012), partial ACT, GAPDH, CHS and TUB2 gene sequences were also amplified and sequenced (GenBank Accession numbers: ITS: OR882016, ACT: OR882013, GAPDH: OR882011, CHS: OR882012, TUB2: OR882010), to characterize the isolates. Additionally, the multilocus phylogenetic analysis carried out with the obtained and reference sequences (Damm et al. 2012) revealed the species of analyzed isolates and confirmed the BLAST results, identifying the strain as C. acutatum (e-Xtra 1F). Koch's postulates were performed on 10 'Kaiser' pears. Surfaces sterilized fruits with 96% ethanol were subjected to wound inoculation with a conidial suspension (106 conidia ml-1) while 10 fruit were used as negative control and inoculated with sterile water. Following an incubation period of 8-14 days at 15-20°C, symptoms around the inoculation site resembled those initially observed, while the negative control showed no symptoms. Fungal colonies re-isolated from the lesions exhibited the same morphological characteristics as the original isolates. To our knowledge, this is the first report of pear bitter rot caused by C. acutatum in Italy and in Europe (Talhinhas & Baroncelli, 2023). Yet, bitter rot had not been recognized as a notable issue in pear cultivation. Nevertheless, given that pears rank as the 8th most cultivated fruit globally and economically very significant for the Emilia Romagna region in Italy the emergence of pear bitter rot caused by Colletotrichum species has the potential to evolve into a significant worldwide problem, warranting further investigation.

How do SUMPs Consider Factors Influencing Walkability and Cyclability? A Review of Literature and Planning Tools

Improving active mobility in settlements is one of the EU's core objectives to improve people's quality of life. EU guidelines indicate Sustainable Urban Mobility Plans (SUMPs) as strategic planning tools to achieve sustainable results through the definition of objectives and the provision of actions. Scientific research has extensively explored numerous factors in the built environment and active mobility infrastructures that influence mobility features and demands. However, a gap exists between research and urban plans employed to promote sustainable mobility. This paper examines whether these identified factors from scientific literature have implications for enhancing active mobility actions in Sustainable Urban Mobility Plans. First, a literature review highlights recurring factors in assessing active mobility networks. Then, an overview of actions supporting walkability and cyclability within Sustainable Urban Mobility Plans applied in the Emilia-Romagna Region in Italy is conducted. The two reviews comparison points out the expected implementation gap between research and practice.

Characterization of environmental drivers influencing the abundance of Anopheles maculipennis complex in Northern Italy

BackgroundIn Italy, malaria was endemic until the 1970s, when it was declared eradicated by WHO. Nowadays, with the persistence of competent mosquito populations, the effect of climate change, and increased possibility of importing malaria parasites from endemic counties due to growing migration, a malaria resurgence in Italy has become more likely. Hence, enhancing the understanding of the current distribution of the Anopheles maculipennis complex and the factors that influence the presence of this malaria vector is crucial, especially in Northern Italy, characterised by a high density of both human population and livestock.MethodsTo assess the presence and abundance of malaria vectors, a 4-year field survey in the plain areas of Lombardy and Emilia-Romagna region in Italy was conducted. Every sampling point was characterised in space by the land use in a 500-m radius and in time considering meteorological data collected in the short and long time periods before sampling. We combined the results of a linear regression model with a random forest analysis to understand the relative importance of the investigated niche dimensions in determining Anopheles mosquito presence and abundance.ResultsThe estimated normalised variable importance indicates that rice fields were the most important land use class explaining the presence of Anopheles, followed by transitional woodlands and shrubland. Farm buildings were the third variable in terms of importance, likely because of the presence of animal shelters, followed by urbanised land. The two most important meteorological variables influencing the abundance of Anopheles in our study area were mean temperature in the 24 h before the sampling date and the sum of degree-days with temperature between 18 °C and 30 °C in the 14 days before the sampling date.ConclusionsThe results obtained in this study could be helpful in predicting the risk of autochthonous malaria transmission, based on local information on land cover classes that might facilitate the presence of malaria vectors and presence of short- and medium-term meteorological conditions favourable to mosquito development and activity. The results can support the design of vector control measures through environmental management.Graphical

Understandings of community participation and empowerment in primary health care in Emilia-Romagna, Italy: A qualitative interview study with practitioners and stakeholders.

Community participation (CP) and empowerment (CE) have long been viewed internationally as cornerstones of comprehensive primary health care (PHC). Accordingly, policies for new PHC models in Italy, such as the Community Health Centres called "Case della Salute" in 2006 and "Case della Comunità" in 2022, highlight the importance of implementing participatory processes with communities and creating opportunities for CE. This study's objective is to identify the understandings of CP and CE that emerge among practitioners and stakeholders who design participatory approaches in PHC practice and policy in the Emilia-Romagna region in Italy. Nineteen semistructured interviews were conducted with practitioners working on CP and CE processes in these Community Health Centres and with stakeholders involved in research on or the coordination of such processes in the context of these health centres. The data were analysed using qualitative content analysis in light of the following two questions, which emerged inductively from the data: (1) How to support CP and CE processes in practical doing (how do CP/CE)? (2) With which function or aim to support CP and CE (why do CP/CE)? This study shows that the participating practitioners and stakeholders exhibited various understandings of CP and CE in the context of PHC. Four main themes were identified: CP and CE as (a) a variety of forms of dialogue and cooperation, (b) tools for service development, (c) levers for empowerment, collectivism, and democracy and (d) stimuli for institutional change and a new level of professionalism. Moreover, the participants defined "the community" in different ways and often chose specific subgroups within the community to promote CP and CE processes. This study elucidates different perspectives on CP and CE and highlights the opportunities and obstacles for policymaking, research and practice that result from these understandings.

Mortality and healthcare assessment among patients with chronic disease over 2 years of COVID-19: a population-based study in a large hard-hit Italian region

ObjectivesWe aimed to provide a region-wide comprehensive account of the indirect effects of COVID-19 on patients with chronic disease, in terms of non-COVID-19 mortality, and access to both inpatient and...

Direct impact of 2 years of COVID-19 on chronic disease patients: a population-based study in a large hard-hit Italian region

ObjectivesWe aimed to provide a region-wide comprehensive account of the direct effects of COVID-19 on chronic disease patients, in terms of disease incidence, severity and mortality, over a 2-year pandemic...

Exploring the Use of Pattern Classification Approaches for the Recognition of Landslide-Triggering Rainfalls

Rainfall-triggered landslides are well-known natural hazards that pose significant risks, and lot of effort has been invested to reduce the risk associated with this type of phenomenon. One approach to reduce such risk is the establishment of landslide early warning systems (LEWSs). LEWSs are designated to proactively identify conditions favorable to the initiation of landslides. When dealing with regional scale works, LEWSs are usually based on statistical methodologies to determine the minimum amount of rainfall required to trigger a landslide. This amount is often expressed in terms of minimum intensity or cumulative rainfall in a given time period. This research explores the use of artificial intelligence, specifically Long Short-Term Memory (LSTM) networks to analyze rainfall time series as either likely or not likely to result in a landslide. Various lengths of time series and different configurations of the model were tested to identify the best setting of the model. To develop the research, the selected test site was the Emilia-Romagna region in Italy, which has a robust landslide inventory, with assessed accuracy. Model performances were evaluated using several statistical indicators, including sensitivity (0.9), specificity (0.8), positive prediction power (0.82), negative prediction power (0.89), Efficiency (0.85) and misclassification rate (0.15). These results showed that the defined model correctly identified the rainfall conditions associated with landslide initiation with a high degree of accuracy and a low rate of false positives. In summary, this research demonstrates the potential of artificial intelligence, particularly LSTM networks, in improving the accuracy of LEWSs by analyzing rainfall time series data, ultimately enhancing our ability to predict and mitigate the risks of rainfall-triggered landslides.

Comorbidity and in-hospital mortality in peritoneal dialysis patients: data of the Emilia Romagna region of Italy.

Kidney failure increases in-hospital mortality (IHM); however, comorbidity is crucial for predicting mortality in dialysis patients. Our aim was to evaluate the impact of comorbidity, assessed by modified Elixhauser index (mEI), Charlson Comorbidity Index (CCI), and age-adjusted CCI, on IHM in a cohort of peritoneal dialysis patients admitted to hospitals of the Emilia Romagna region (ERR) of Italy. All hospital admissions of peritoneal dialysis patients recorded between 2007 and 2021 in the ERR database were analyzed. The International Classification of Diseases, 9th Revision, Clinical Modification (ICD-9-CM) was used for detecting diagnoses and procedures, and the inclusion criterion was code 5498. Comorbidity burden was evaluated by three different scores, and hemodialysis (HD) treatment need was considered. IHM was our outcome. During the 15 years of the study, 3,242 hospitalized peritoneal dialysis patients (62.7% males) were evaluated. Mean age was 62.8±20.6 years, 9.6% underwent HD, and IHM was 5.9% (n=192). IHM mortality was stable throughout the study period. Deceased subjects were older, were hospitalized longer, had a higher comorbidity burden, and had a higher percentage of HD treatment needs than survivors. Age, male sex, comorbidity burden, and HD treatment were predictors of IHM. Receiver operating characteristics (ROC) analysis confirmed the impact of comorbidity burden on IHM, especially when age was considered. We conclude that in male, elderly hospitalized peritoneal dialysis patients with failing dialysis technique, comorbidity burden should be considered being a predictor of IHM.

From entrepreneurial and innovation ecosystems to the social economy ecosystem

Despite the broad academic and political interest aroused by the ecosystem concept, little scientific attention has been paid to its social dimension and especially to the social economy enterprises ecosystems. This paper aims to conceptualize the latter by establishing its defining features and its goals, and to provide empirical evidence from two worldwide known social economy ecosystems, one in the Valencia region of Spain and the other in the Emilia Romagna region of Italy. The results show that the balance between the economic objectives and the creation of social value and social innovation, collective social entrepreneurship and specific institutional components are key features of social economy ecosystems. The proactive role of the axiological, cognitive and institutional elements of these ecosystems, embedded in knowledge and culture, enable, when properly applied to an operational sphere, the achievement of social value and the start-up and scaling up of the social economy model.

Insight into Elderly ALS Patients in the Emilia Romagna Region: Epidemiological and Clinical Features of Late-Onset ALS in a Prospective, Population-Based Study.

Few studies have focused on elderly (>80 years) amyotrophic lateral sclerosis (ALS) patients, who represent a fragile subgroup generally not included in clinical trials and often neglected because they are more difficult to diagnose and manage. We analyzed the clinical and genetic features of very late-onset ALS patients through a prospective, population-based study in the Emilia Romagna Region of Italy. From 2009 to 2019, 222 (13.76%) out of 1613 patients in incident cases were over 80 years old at diagnosis, with a female predominance (F:M = 1.18). Elderly ALS patients represented 12.02% of patients before 2015 and 15.91% from 2015 onwards (p = 0.024). This group presented with bulbar onset in 38.29% of cases and had worse clinical conditions at diagnosis compared to younger patients, with a lower average BMI (23.12 vs. 24.57 Kg/m2), a higher progression rate (1.43 vs. 0.95 points/month), and a shorter length of survival (a median of 20.77 vs. 36 months). For this subgroup, genetic analyses have seldom been carried out (25% vs. 39.11%) and are generally negative. Finally, elderly patients underwent less frequent nutritional- and respiratory-supporting procedures, and multidisciplinary teams were less involved at follow-up, except for specialist palliative care. The genotypic and phenotypic features of elderly ALS patients could help identify the different environmental and genetic risk factors that determine the age at which disease onset occurs. Since multidisciplinary management can improve a patient's prognosis, it should be more extensively applied to this fragile group of patients.

Post-closure Cost Efficiency in Public Versus Private Landfills: The Case of Emilia-Romagna (Italy)

Waste management systems have developed in recent years toward the adoption of sustainable management principles and practices, such as circular economy, zero waste, resource efficiency, waste avoidance, re-use, and recycling. Nevertheless, landfills continue to be used for waste disposal despite their risks related to contamination and effects on urban development. Most research on landfills focuses on their operational and technical aspects, while the performance and cost efficiency in managing landfills is less commonly studied, especially their post-closure management. However, improving efficiency is very relevant in the context of scarce public sector resources. This paper, therefore, analyzes the efficiency of post-closure management of landfills. Drawing on agency and stewardship theories, we focus on the difference in efficiency between public and private management of post-closure landfills. We use a linear mixed regression model to analyze data from 2015 to 2018 relating to 54 landfills (79% of which are privately managed) in the Emilia-Romagna region of Italy. The results show that public management is more efficient than private management. Results contribute to defining drivers of cost and confirming a disparity in the performance of private and public management. Our results cast doubt on the assumption, which is prevalent in new public management theory, that private operators are more efficient than public ones. We conclude by highlighting that to reach efficiency, it is better to increase the effectiveness of regulation in terms of value for money, without pre-determined preferences for the type of management.

Robots and the productivity of local manufacturing systems in Emilia-Romagna: the mediating role of occupational similarity and complexity

ABSTRACT During the last decade, a growing literature has been assessing the impact of industrial robots on productivity and employment. At the local level, the labour-displacing effect of robot adoption can be counterbalanced by a task reallocation between manufacturing industries characterized by similar/related occupational spaces. This reallocation process can be also influenced by the average degree of occupational complexity of the local labour markets. To test for the mediating role of similarity and complexity in the robot-employment-productivity relationship, we develop a two-step analysis mixing information from different data sources on 15 industries and 39 local labour market areas of the Emilia-Romagna region in Italy, for the period 2008–2017. Our analysis shows that higher exposure to robots does not affect the aggregate level of labour productivity, but, rather, is associated with a decline in (high routine) employment after three years. We further show that the negative relationship between robots and employment decreases, or even vanishes, in local labour markets with high cross-industry occupational similarity and low occupational or task complexity, and within industrial districts.

The Anthropic Pressure on the Grey Water Footprint: The Case of the Vulnerable Areas of the Emilia-Romagna Region in Italy

Nitrogen (N) is an important component of plant development, yet its application and contamination are a global issue. Diffuse source pollution and its effects on ecosystem health are notoriously difficult to track and control. This paper answers the Sustainable development Goal 6 goal focused on reducing water pollution by improving the understanding of nitrate emissions to groundwater and their resulting water pollution level in the Emilia-Romagna region in Italy. The Grey water footprint (GWF) and water pollution level (WPL) were used as indicators and geospatial maps were constructed in order to determine if N levels exceeded groundwater quality demand from 2014 to 2020. Moreover, a selection of specific agricultural sites in the Piacenza district has been performed to better understand the potential anthropogenic nitrate pollution due to the agricultural sector. In the selected sites, the predicted nitrate pollution due to agricultural practice has been compared with the nitrate concentration measured in samples collected across the period 2015–2018. The regional results show that approximately 70% of the analysed sites resulted in a total N load exceeding the estimated agricultural load to groundwater. The analysis conducted in three selected wells in the Piacenza district shows the sporadic exceedances of the legal limit and demonstrates the presence of anthropogenic pressures of various natures insisting on the surrounding area and confirms a potential non-agricultural point or diffuse pollution source.

The impact of Community Health Centers on inappropriate use of emergency services.

Community Health Centers offer coordinated and comprehensive responses to primary care needs. Our study aims at assessing whether the introduction of such organizational model improved health outcomes measured by inappropriate emergency visits among diabetics in the Emilia-Romagna region of Italy. Using difference-in-differences methods within a staggered treatment setting, we estimate the effect of Community Health Center participation on inappropriate hospital emergency visits between year 2010 and year 2016. We distinguish between emergency department admissions for varying time spans, occurring at daytime during working days, at night-time, as well as during weekends. We show that, the causal effect of the adoption of the community care model leads to a reduction in the probability of inappropriate admissions by an amount ranging between 1.6 and 1.7% points during working days at daytime, with large facilities responsible for most gains by experiencing a decrease ranging between 4 and 3% points. Conversely, we detect no difference at night-time and during weekends. Our results point out that the coordinated care model increases appropriateness among vulnerable patients, and that extending opening hours and the range of services can further enhance such benefits.

The Impact of the COVID-19 Pandemic on Childhood Obesity and Lifestyle-A Report from Italy.

During the COVID-19 lockdown, especially in the first wave of pandemic (March 2020), sedentary lifestyle and calorie intake increase in children became considerably more prevalent. The aim of the present paper was to evaluate changes in children’s weights and nutritional habits during the COVID-19 pandemic in Italy. In this cross-sectional observational study, for 3 years, as part of the corporate wellness program (2019–2021) in Emilia Romagna region of Italy, anthropometric data of Ferrari car company employers’ children were collected, analyzed, and compared. Moreover, at the visit of November 2020, performed after the first wave of the pandemic with the most rigorous lockdown rules in Italy, a questionnaire on nutritional and lifestyle habits was administered. We evaluated 307 children (163 M, 10.1 ± 2.3 mean aged in 2019). A significant increase in BMI percentile in 2020 (65.2) compared to 2019 (49.2) was observed; it was confirmed, albeit slightly decreased, in 2021 (64.5). About one-third of participants reported an increase in consumption of fatty condiments and more than half report an increase in consumption of junk food. Levels of physical activity were still high during the COVID-19 lockdown, while sleeping time was significantly reduced. Our findings alert us to the importance of carefully monitoring eating behaviors in young to avoid the adoption of unhealthy food habits and prevent childhood obesity, especially during the period of COVID-19 lockdown.

Epidemiological, Clinical and Genetic Features of ALS in the Last Decade: A Prospective Population-Based Study in the Emilia Romagna Region of Italy.

Increased incidence rates of amyotrophic lateral sclerosis (ALS) have been recently reported across various Western countries, although geographic and temporal variations in terms of incidence, clinical features and genetics are not fully elucidated. This study aimed to describe demographic, clinical feature and genotype–phenotype correlations of ALS cases over the last decade in the Emilia Romagna Region (ERR). From 2009 to 2019, our prospective population-based registry of ALS in the ERR of Northern Italy recorded 1613 patients receiving a diagnosis of ALS. The age- and sex-adjusted incidence rate was 3.13/100,000 population (M/F ratio: 1.21). The mean age at onset was 67.01 years; women, bulbar and respiratory phenotypes were associated with an older age, while C9orf72-mutated patients were generally younger. After peaking at 70–75 years, incidence rates, among women only, showed a bimodal distribution with a second slight increase after reaching 90 years of age. Familial cases comprised 12%, of which one quarter could be attributed to an ALS-related mutation. More than 70% of C9orf72-expanded patients had a family history of ALS/fronto-temporal dementia (FTD); 22.58% of patients with FTD at diagnosis had C9orf72 expansion (OR 6.34, p = 0.004). In addition to a high ALS incidence suggesting exhaustiveness of case ascertainment, this study highlights interesting phenotype–genotype correlations in the ALS population of ERR.

Identifying and predicting amyotrophic lateral sclerosis clinical subgroups: a population-based machine-learning study

Amyotrophic lateral sclerosis (ALS) is known to represent a collection of overlapping syndromes. Various classification systems based on empirical observations have been proposed, but it is unclear to what extent they reflect ALS population substructures. We aimed to use machine-learning techniques to identify the number and nature of ALS subtypes to obtain a better understanding of this heterogeneity, enhance our understanding of the disease, and improve clinical care. In this retrospective study, we applied unsupervised Uniform Manifold Approximation and Projection [UMAP]) modelling, semi-supervised (neural network UMAP) modelling, and supervised (ensemble learning based on LightGBM) modelling to a population-based discovery cohort of patients who were diagnosed with ALS while living in the Piedmont and Valle d'Aosta regions of Italy, for whom detailed clinical data, such as age at symptom onset, were available. We excluded patients with missing Revised ALS Functional Rating Scale (ALSFRS-R) feature values from the unsupervised and semi-supervised steps. We replicated our findings in an independent population-based cohort of patients who were diagnosed with ALS while living in the Emilia Romagna region of Italy. Between Jan 1, 1995, and Dec 31, 2015, 2858 patients were entered in the discovery cohort. After excluding 497 (17%) patients with missing ALSFRS-R feature values, data for 42 clinical features across 2361 (83%) patients were available for the unsupervised and semi-supervised analysis. We found that semi-supervised machine learning produced the optimum clustering of the patients with ALS. These clusters roughly corresponded to the six clinical subtypes defined by the Chiò classification system (ie, bulbar, respiratory, flail arm, classical, pyramidal, and flail leg ALS). Between Jan 1, 2009, and March 1, 2018, 1097 patients were entered in the replication cohort. After excluding 108 (10%) patients with missing ALSFRS-R feature values, data for 42 clinical features across 989 patients were available for the unsupervised and semi-supervised analysis. All 1097 patients were included in the supervised analysis. The same clusters were identified in the replication cohort. By contrast, other ALS classification schemes, such as the El Escorial categories, Milano-Torino clinical staging, and King's clinical stages, did not adequately label the clusters. Supervised learning identified 11 clinical parameters that predicted ALS clinical subtypes with high accuracy (area under the curve 0·982 [95% CI 0·980-0·983]). Our data-driven study provides insight into the ALS population substructure and confirms that the Chiò classification system successfully identifies ALS subtypes. Additional validation is required to determine the accuracy and clinical use of these algorithms in assigning clinical subtypes. Nevertheless, our algorithms offer a broad insight into the clinical heterogeneity of ALS and help to determine the actual subtypes of disease that exist within this fatal neurodegenerative syndrome. The systematic identification of ALS subtypes will improve clinical care and clinical trial design. US National Institute on Aging, US National Institutes of Health, Italian Ministry of Health, European Commission, University of Torino Rita Levi Montalcini Department of Neurosciences, Emilia Romagna Regional Health Authority, and Italian Ministry of Education, University, and Research. For the Italian and German translations of the abstract see Supplementary Materials section.