Decision Tree Tool Research Articles

Enhancing the accuracy of blood-glucose tests by upgrading FTIR with multiple-reflections, quantum cascade laser, two-dimensional correlation spectroscopy and machine learning

The accuracy of screening diabetes from non-diabetes is drastically enhanced by strategically upgrading the bench-marking infrared spectroscopy technique for non-invasive tests of blood-glucose, both with state-of-the-art instrumentation-retrofits and with intelligent spectral-datamining tools. First, the signal-to-noise performance of FTIR in measuring the spectral features of a glucose solution containing bovine serum albumin is improved by 2–3 times with the common single-pass attenuated total-reflection setup replaced by a multi-passes-reflections setup. Second, replacing the ordinary infrared lamp with a quantum cascade laser further improves the signal-to-noise by 3 times. The performance of the upgraded spectrometer in screening hyperglycemia is gauged by the accuracy of such screens derived from 100 repetitive spectral-measurements per glucose concentration, for 24 glucose concentrations spanning the range of 70–300 mg/dL, a range which covers the blood-glucose contents of all non-diabetic and diabetic human-subjects. Third, intelligent datamining methods are exploited to implement decision trees for screening hyperglycemia. Their decisions are mapped into a confusion matrix and the matrix-elements are used to calculate the accuracy merits of each method. Evidently, the accuracy of the multi-passes-FTIR with the standard principal-components datamining method is 80 %. The adoptions of the quantum cascade laser and two-dimensional correlation spectroscopy datamining technique raises this to 96.3 %. Finally, a novel machine learning method, which comprises three different decision-tree tools to generate trial screening decisions and a “majority-voting” datamining tool to reach a final screening decision, yields the best accuracy of 98.8 % ever reported in the literature.

QUALITY AND SAFETY MANAGEMENT OF FERMENTED MILK PRODUCTS FROM CAMEL MILK BASED ON HACCP PRINCIPLES

Currently, the main task of domestic producers of milk and dairy products is to provide consumers with high-quality and safe dairy products. At the same time, the main guarantee of safe production is the introduction of the HACCP system at enterprises.The main advantage of the HACCP system is error detection, namely prevention and prevention, through step-by-step control of the entire food production chain.The research work was carried out on the basis of the national standard SS RK 1179-2003 «Quality systems. Food quality management based on the principles of HACCP. General requirements». At the first stage, the necessary information about the fermented milk product from camel milk was collected (composition, organoleptic characteristics, indicators characterizing quality and safety, application, type of packaging, storage and delivery conditions) and a flowchart of its production process was compiled. At the second stage, the results of scientific research by other authors and regulatory documents related to the quality and safety of camel milk and products from it were examined to analyze chemical, biological and physical risks. Then an assessment of the probability of the identified dangerous risks was carried out. Further, using the Decision Tree tool, critical control points in the technology of the research object were identified, allowing to manage safety and improve quality in their production.

Decision tree scoring system to guide selection for consumer preference in sweetpotato breeding trials.

Previously, a lexicon and protocol for quantitative descriptive analysis (QDA) was established for the Uganda sweetpotato breeding program. The implication of QDA scores for priority sensory attributes on consumer preference should be determined to interpret results efficiently and make decisions effectively. The present study aimed to develop a gender-responsive decision tree to obtain an overall sweetpotato eating quality score to facilitate demand-led targeted breeding selection. It focused on Kamuli and Hoima districts (Uganda) and uses pre-lease advanced clones ('NKB3', 'NKB105', 'NKB135', 'D11' and 'D20'), released varieties ('NASPOT 8' and 'NAROSPOT 1') and landraces ('Muwulu-Aduduma', 'Umbrella'). Including boiled sweetpotato sensory characteristics, namely mealy, sweet taste, sweetpotato smell, firm and not fibrous, in breeding design would benefit end-users, especially women given their role in varietal selection, food preparation and marketing. 'D20', 'NASPOT 8' and 'NAROSPOT 1' were most liked in both districts. 'NKB3' and 'D11' were the least liked in Hoima, whereas 'Muwulu-Aduduma' was the least liked in Kamuli. There was a positive correlation between color and overall liking (r2 = 0.8) and consumers liked the color (average rating ≥ 6 on a nine-point hedonic scale) of all genotypes. Threshold values (average rating on 11-point scales) for consumer acceptability were identified (sweet taste = 6, sweetpotato aroma and flavor = 6, firmness = 3, and mealiness = 4). A regression decision tree tool was created to calculate an eating quality selection index when screening lines in breeding programs using the values. Decision trees that include consumer needs and gender considerations would facilitate demand-led breeding and make varietal selection in sweetpotato breeding programs more effective. © 2023 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Perbandingan Performa Cluster Model Algoritma K-Means Dalam Mengelompokkan Penerima Bantuan Program Keluarga Harapan

Poverty has so far played a role as a problem faced by residents of the Mentawa Baru sub-district, Ketapang. The inability of this community is related to the need to meet education and health needs in social welfare. In assisting the grouping of beneficiary data is carried out using the K-Means algorithm. Apart from that, to increase performance, those who have gone through the first grouping process are then continued using feature selection in the decision tree tool. The algorithm used aims to classify PKH beneficiary data to help the government find out about the handling of the aid program in Mentawa Baru Ketapang sub-district. As for the results obtained from this study, namely, the accuracy of the initial clustering obtained a DBI value of -0.994 at K=8 while the second clustering value that had gone through feature selection with K=3 obtained a DBI value of -0.865. It is known from the performance testing of the comparison of the two clustering that the best performance value is found in the second cluster after going through feature selection.

Perfil das áreas técnicas de alimentação e nutrição de Mato Grosso do Sul, Brasil: organização para tomadas de decisão

Abstract The aim of the present study was to analyze the management organization of food and nutrition actions in the municipalities of Mato Grosso do Sul. This is a descriptive-exploratory study carried out in Mato Grosso do Sul, in which each municipal food and nutrition manager answered questions about performance, governance and financing profile. Data analysis applied frequency, chi-square test and decision tree tools. All cities were included (n=79). Most of the participants were female (92.4%), white (62%), nurses (45.6%) or nutritionists (36.7%). Financial management proved to be so incipient in the state since specific food and nutrition funding was neglected. The absence of a technical area in the municipality’s organizational chart was consistent with the lack of knowledge of actions, goals and resource allocation. Their presence coincided with having formally appointed technical managers, municipal food and nutrition policy, goals and elaboration of specialized materials. The present study also proposed a decision tree pointing that having a nutritionist in the team led to a positive result. The failures found in this study partly clarify the causes of the unsettling situation in the state. Our findings can support the creation of intervention strategies.

Prospects for treated wastewater reuse in agriculture in low- and middle-income countries: Systematic analysis and decision-making trees for diverse management approaches

The Middle East and North Africa (MENA) region is suffering from severe water scarcity. Decision-makers in MENA are tackling this challenge by tapping the potential of reusing treated wastewater in agriculture so that large volumes of freshwater sources can be released for priority domestic needs. This aligns with the global efforts to make wastewater reuse mainstream in developing countries by overcoming the technological, infrastructural, health, and socio-cultural barriers that are limiting the expansion of wastewater reuse in agriculture. In this regard, this paper analyses the management modalities of wastewater reuse practices in agriculture in MENA by studying two case studies from Egypt and Jordan. The result of this analysis is a proposed decision-tree tool to help decision-makers in making optimal wastewater reuse decisions based on contextual factors including agricultural field demands, location, freshwater resources, sanitation coverage, and infrastructure, as well as regulations, policies, and restrictions for wastewater reuse. The decision-tree framework was operationalized and validated using the two case studies. The decision tree proved to be an effective framework in assisting decision-makers in making the optimum choice for wastewater reuse in agriculture. It aided the decision maker in evaluating potential reuse options and selecting between several courses of action.

Predictors of combat training attrition in Israel Defense Forces soldiers.

Attrition from combat service carries significant organizational and personal ramifications, but predicting factors associated with attrition remains challenging. To evaluate medical and psychosocial factors associated with attrition from basic combat training (BCT) in the Israel Defense Forces (IDF). In addition, we identify subsets of the recruit population which exhibit certain trends in terms of medical corresponding with a high risk of attrition. A cross-sectional study of IDF combat trainees undergoing infantry BCT between 2012 and 2017. Data were collected from the soldiers' electronic medical and administrative records. We used multivariable logistic regression and the SAS® decision-tree tool to analyse key predictive factors for attrition. A total of 46 472 soldiers enlisted to BCT during the research period. The mean body mass index (BMI) was 21.8 (SD 3.54). The overall attrition rate was 10%. The following factors were associated with attrition from BCT: ethnicity (P < 0.01), BMI (P < 0.01), pre-enlisting motivation score (P < 0.01) and the number of mental health officer visits (P < 0.01). Using a decision-tree model, we found a high attrition rate among soldiers who had >5.2 to primary care physician visits (11% attrition rate versus 3%) or more than 11 sick leave days (59% versus 19%). This study sheds light on unique measures relating to attrition. Attrition is associated with several demographic and psychosocial factors. Early prediction of motivation and monitoring of healthcare utilization may enable early identification and focused interventions targeting soldiers at high risk for attrition. These findings need to be further translated into actionable directives and further investigations.

Decision Tree Tool for Auditors’ Going Concern Assessment in Spain

The COVID-19 pandemic increased uncertainty about the financial future of many organizations, and regulators alerted auditors to be increasingly skeptical in assessing an entity’s ability to continue as a going concern. An auditor’s assessment of an entity’s ability to continue as a going concern is a matter of significant judgment. This paper proposes to use machine learning to construct a Decision Tree Automated Tool, based on both quantitative financial indicators (e.g., Z-scores) and qualitative factors (e.g., partners’ judgment and assessment of industry risk given the pandemic). Considering both quantitative and qualitative factors results in a model that provides additional audit evidence for auditors in their going-concern assessment. An auditing firm in Spain used the model as a supplemental guide, and the model’s suggested results were compared to auditors’ reports to evaluate its effectiveness and accuracy. The model’s predictions were significantly similar to the auditors’ assessments, indicating a high level of accuracy, and differences between the model’s proposed outcomes and auditors’ final conclusions were investigated. This paper also provides insights for regulators on both the use of machine-learning predictive models and additional factors to be considered in future going-concern assessment research.

Identifying Developmental Coordination Disorder in Children with Attention-Deficit/Hyperactivity Disorder: An Evidence-based Decision Tree Tool for Occupational Therapy Clinicians

ABSTRACT Children with attention-deficit/hyperactivity disorder (ADHD) may also have undiagnosed developmental coordination disorder (DCD). Prevalence rates of the ADHD/DCD comorbidity are estimated between 30% and 50%. Given the significant impact these disorders have on a child’s occupational performance, lack of detection of DCD is of concern. Occupational therapists play a key role in screening children for the presence of DCD to provide timely and targeted intervention opportunities. However, despite synthesized research and clinical guidelines being available, inconsistency with identification of DCD continues to be reported. Currently, no clear decision-making support tool is available in Australia to aid DCD identification. We aimed to bridge this research-practice gap by developing an evidence-based decision tree tool (ADITA), to guide this identification process. Mapping of assessment and identification processes for DCD was undertaken, in accordance with DSM-5 diagnostic criteria and the European Academy for Childhood Disability (EACD) clinical practice recommendations. A pilot study was conducted to test agreement in identification of DCD between an occupational therapist and pediatrician when the decision tree tool was applied. The ADITA decision tree tool created was trialed with a sample of 19 children with ADHD, aged 8–12 years. Twenty-six percent of participants were assessed as having likely DCD by the occupational therapist, with 21% of ADHD participants subsequently confirmed with DCD by a pediatrician. An agreement rate of 94% was achieved. Preliminary support is provided for the use of ADITA, an evidence-based decision tree tool, to identify DCD in school-aged children with ADHD. The ADITA supports knowledge translation by facilitating implementation of research evidence for DCD, thereby assisting occupational therapists and health professionals to bridge the existing research-practice gap.

A Decision Tree Approach to Airway Management Pathways in the 2022 Difficult Airway Algorithm of the American Society of Anesthesiologists.

The American Society of Anesthesiologists’ (ASA) Task Force on Management of the Difficult Airway has developed a decision tree tool that uses inductive assessments to guide the anesthesiologist’s choice of pathway in the ASA’s Difficult Airway Algorithm. The tool prompts the anesthesiologist to consider the risk of difficulty with laryngoscopy (direct or indirect) and tracheal intubation, facemask or supraglottic ventilation, gastric contents aspiration, and rapid oxyhemoglobin desaturation. For every airway management event, the approach integrates the anesthesiologist’s unique combination of experience, expertise, patient anatomy and disease, equipment availability, and other contextual conditions into the decision process. Entry into the awake intubation pathway is encouraged when the patient is judged at risk of difficult tracheal intubation and one or more of the following: difficult ventilation, significant aspiration risk, and/or rapid oxyhemoglobin desaturation. The decision tree tool is anticipated to improve communication between anesthesiologists and others by clearly identifying those factors of concern and how decision-making is affected by those concerns.

Prediction of burn wound response to low level laser using artificial intelligence

Background: chronic diseases increased with aging process, chronic wounds also increased, creating a huge load on the health system. Accurate documentation and measurement of wounds healing become critical. More research is required to construct and validate wound predictive measures to guide more accurate treatment plan with better clinical treatment. Artificial intelligence is widely used to help clinician in clinical decisions and save effort and time. A non-parametric supervised learning technique for regression and classification is called a decision tree (DT). The objective is to build a model that, by utilizing basic decision rules deduced from the data features, predicts the value of a target variable. A piecewise constant approximation can be thought of as a tree. Aim: to predict burn wound response to low level laser using artificial intelligence inform of decision tree tool through using the following variables: patients’ age, burn wound size ,wound stage and total burned surface area. Methods: fifty patients (male and female) with partial thickness burn wound were recruited from the burn units. There was only one intervention group receiving low level laser for six weeks divided to 18 sessions (three sessions per week).

127 Caution and Context: COVID-19 as the Educational Focus for Inter-Professional Learning

Traditionally our university-affiliated Office of IPE delivers a 3-phase (exposure, immersion, competence) inter-professional education (IPE) curriculum which is a graduation requirement for students. On 13 March 2020, on-site classes were suspended due to the first confirmed case of COVID-19 in the state. Faculty rapidly implemented alternative methods of instruction to complete coursework for the spring semester utilizing COVID-19 as the educational focus and hosting these learning events on the virtual platform.The aim of the study was to lean into the educational opportunities provided by the global pandemic to continue to provide high-quality IP education including simulation, crafting these educational events to meet the pandemic needs of our community.During the COVID-19 pandemic, healthcare students and faculty stepped forward with a desire to serve during this health crisis. Several public health support programmes were provided by the academic health centre and IP educational activities were crafted around these. Such programmes included: a 1–800 COVID-19 hotline providing rapid access to health screening to assist the community in understanding when and where they should access the healthcare system for testing or care; a Contact Tracing Call Center to identify those with exposure and risk and counsel next steps; and provision of public health information regarding the virus and the vaccine. IP Faculty developed a series of IP simulations to provide students with the knowledge and skills necessary to serve in these public health support areas. These simulations were all structured utilizing an initial brief (detailing Interprofessional Education Collaborative (IPEC) domains and Patient- and Family-Centered Care principles), followed by scenario-specific education such as IP team review of screening algorithm and decision tree for hotline and call centre work, with subsequent standardized patient (SP) interaction, and finally IP debriefing. Five simulations involving 190 students occurred. Evaluation metrics collected included pre-/post-Interprofessional Collaborative Competencies Attainment Survey (ICCAS), evaluation of learning objectives, SP interaction and simulation methodology via Likert scale, and identification of themes from qualitative response items.Inter-professional simulation training activity via an online platform supported student learning for COVID-19 disease information, screening algorithm and decision tree tools and telemedicine delivery. The rapidly implemented virtual training prepares students to graduate whilst also supporting the state during this public health crisis. This work provides a template by which curricula can pivot to meet the needs of all key stakeholders during a time of global crisis.

Machine Learning Reveals Patient Phenotypes and Stratifies Outcomes in Chronic Graft-Versus-Host Disease

Background: Chronic graft-versus-host disease (cGVHD) contributes to significant morbidity and mortality post hematopoietic stem cell transplant. Establishing a reliable classification system for this biologically and clinically heterogenous disease, remains challenging. Current scoring systems (e.g., NIH consensus criteria) calculate a score of mild, moderate, or severe disease from multiple organ domains. However, important information about the biology of disease and subtypes of patients may be lost when using the aggregate NIH overall severity classification that combines multiple dimensions of organ data. Machine learning may thus reveal subgroups in multi-dimensional data.Aim: We previously utilized a machine learning workflow on a training dataset to cluster cases of cGVHD into seven distinct phenotypes and designed a user-facing prognostic tool organized as a decision tree (Gandelman et al., Haematologica 2018). This decision tree identified clusters of patients with different survival trends that were not explained or stratified by NIH Severity alone. We sought to validate and expand this workflow on an independent cohort of patients from BMT CTN Study #0801.Methods: With permission from CIBMTR, clinical data were obtained from patients enrolled in BMT CTN #0801, a Phase II/III, prospective, multi-center comparative study. The cohort size started at 151 patients; 19 patients were excluded because of missing organ scores, leaving 132 patients in the final analysis. In the training dataset, it was determined that clusters were stable with N=130 patients in the analysis. Therefore, the sample size of the BMT CTN data set was adequate for the validation. At enrollment, NIH 2005 consensus criteria scores were recorded for eye, liver, joint, mouth, gastrointestinal tract, and lung. The percentage of the body surface area with erythema (% erythema) was measured. Skin sclerosis and fascia were assessed using Hopkins scores.Eight organ domains (NIH Scores 0-3: eye, liver, joint, mouth, gastrointestinal tract; Hopkins Scores: Sclerosis 0-4, Fascia 0-3; % erythema) were analyzed via a machine learning workflow consisting of t-distributed stochastic neighbor embedding (t-SNE), self-organizing maps (FlowSOM), and marker enrichment modeling (MEM). These steps allowed for dimensionality reduction, patient clustering, and organ enrichment scoring.Lung scores were not included as they were not found to contribute significantly to patient clustering in the training dataset analysis. All analyses were performed using R v4.0.4 and its libraries.Results: Baseline characteristics of patients in the validation cohort were similar to those of the training dataset except for disease stage, as a greater proportion of patients in the validation cohort had early-stage disease versus intermediate or high risk (p = 0.0004). The machine learning workflow identified similar phenotypic clusters in the validation cohort, with the sclerotic and liver-predominant clusters preserved most robustly (Figure 1A). As with the training dataset, machine learning identified clusters of phenotypes different from severity alone as assessed by the NIH global severity score in the validation cohort.Mean time from stem cell transplant to cGVHD (ie. probability of being cGVHD-free) was comparable between the two cohorts (284 days in validation cohort versus 288 days in training dataset). Notably, as with the training cohort, “Sclerotic” cluster patients in the validation cohort had significantly longer time from stem cell transplant to cGVHD compared to patients from other clusters (Log-rank: p = 0.0032) (Figure 1B).Conclusion: Our machine learning workflow identified phenotypic clusters with high fidelity and stratified time-to-GVHD in a validation cohort of patients. The decision tree tool separated patients into phenotypic clusters as previously designed in R by clustering with FlowSOM on t-SNE axes and using MEM to quantitively describe the clusters based on organ scores. Further studies on other independent cohorts of patients are now needed to delineate the biological basis of cGVHD subtypes and to further define patients in mixed phenotype groups. [Display omitted] DisclosuresJagasia: Iovance Biotherapeutics: Current Employment, Current holder of stock options in a privately-held company.

High School Science Teacher Use of Planning Tools to Integrate Computational Thinking

ABSTRACT In an effort to deepen learning in K-12 science classrooms, there has been a national movement to integrate computational thinking (CT). The purpose of this phenomenographic study was to understand teachers’ perceptions of the function and usefulness of a task analysis and a decision tree tool designed to help them with integration. Teachers participated in a long-term professional development to improve their knowledge and application of CT and then developed lesson plans integrating CT into science investigations. To assist in the integration, teachers used the two unique tools. No one lesson plan or content area addressed all of the CT practices, but all CT practices were addressed in lessons across all four science areas. All 19 teachers found that the task analysis tool helped them to shift their lessons to a student-centered focus and helped them pinpoint data practices so they could systematically integrate CT practices. However, they expressed confusion over the amount of detail to document on the tool. Similarly, teachers found both benefits and barriers to the decision tree tool. Teachers found the decision tree tool to be useful in predicting the ways students may misunderstand a data practice and in reflecting on the level of accomplishment of students. However, teachers were sometimes uncertain with how to efficiently document complex student behaviors when engaged with data practices and CT. Implications for the use of the two lesson planning tools is discussed.

Preparing for skill transfer: a decision tree tool for curriculum design and assessment of virtual offshore emergency egress training

ABSTRACT To prepare personnel for offshore emergencies, safety training should focus on transferability. Virtual environment (VE) training is designed to support the transfer of acquired egress skills to novel offshore emergencies. Decision trees (DT) are useful tools to evaluate training transfer. DTs use performance data collected during VE training to model participants’ behavioural patterns. A DT that reflects ideal behaviour is used as a benchmark to compare the compliance of the participants’ data-informed behavioural patterns. Employing the diagnostic and predictive capabilities of DTs can indicate whether a person is capable of responding to a wide variety of emergencies using inference. This paper demonstrates the use of DTs as a curriculum design and assessment tool to determine if the VE training adequately prepared participants to transfer their egress skills to new emergencies in the same virtual setting.

Recognizing Eruptions of Mount Etna through Machine Learning Using Multiperspective Infrared Images

Detecting, locating and characterizing volcanic eruptions at an early stage provides the best means to plan and mitigate against potential hazards. Here, we present an automatic system which is able to recognize and classify the main types of eruptive activity occurring at Mount Etna by exploiting infrared images acquired using thermal cameras installed around the volcano. The system employs a machine learning approach based on a Decision Tree tool and a Bag of Words-based classifier. The Decision Tree provides information on the visibility level of the monitored area, while the Bag of Words-based classifier detects the onset of eruptive activity and recognizes the eruption type as either explosion and/or lava flow or plume degassing/ash. Applied in real-time to each image of each of the thermal cameras placed around Etna, the proposed system provides two outputs, namely, visibility level and recognized eruptive activity status. By merging these outcomes, the monitored phenomena can be fully described from different perspectives to acquire more in-depth information in real time and in an automatic way.

Creating functional group alternatives in integrated industrial wastewater recycling system: A case study of Toos Industrial Park (Iran)

Integrated industrial wastewater recycling has become an important issue in recent years especially in developing countries, which can be obtained by comprising three aspects of collection system, treatment processes, and reuse target, jointly called “functional group”. The main aim of this study is proposing a framework for creating industrial wastewater recycling functional groups as the alternatives for future sustainability assessment, especially for developing countries. For this purpose, SWOT method (strengths, weaknesses, opportunities, and threats), PESTEL method (political, economic, social, technological, environmental, and legal factors), and decision tree tool are combined with expert ideas and their scoring, and then the methodology is applied to a real case in Iran (Toos Industrial Park, Khorasan Razavi Province). The proposed methodology tries to tackle challenges such as lack of exact data and insufficient experience, which are required to create possible options by other complex tools, such as multi-criteria decision-making processes or optimization procedures.

A brain connectivity characterization of children with different levels of mathematical achievement based on graph metrics.

Recent studies aiming to facilitate mathematical skill development in primary school children have explored the electrophysiological characteristics associated with different levels of arithmetic achievement. The present work introduces an alternative EEG signal characterization using graph metrics and, based on such features, a classification analysis using a decision tree model. This proposal aims to identify group differences in brain connectivity networks with respect to mathematical skills in elementary school children. The methods of analysis utilized were signal-processing (EEG artifact removal, Laplacian filtering, and magnitude square coherence measurement) and the characterization (Graph metrics) and classification (Decision Tree) of EEG signals recorded during performance of a numerical comparison task. Our results suggest that the analysis of quantitative EEG frequency-band parameters can be used successfully to discriminate several levels of arithmetic achievement. Specifically, the most significant results showed an accuracy of 80.00% (α band), 78.33% (δ band), and 76.67% (θ band) in differentiating high-skilled participants from low-skilled ones, averaged-skilled subjects from all others, and averaged-skilled participants from low-skilled ones, respectively. The use of a decision tree tool during the classification stage allows the identification of several brain areas that seem to be more specialized in numerical processing.

Decision trees in environmental justice research — a case study on the floods of 2001 and 2010 in Hungary

Abstract Environmental justice is a normative framework for the analysis of environmental impacts on the wellbeing of individuals and social groups. According to the framework, the deprived social groups and ethnic minorities are often more exposed to environmental risks and hazards due to their disadvantaged situation, and due to the lack of representation and political power. To manage the impacts of injustices and to include the citizen in the decision-making processes, proper information is needed on local attitudes and decision-making processes. Therefore, this study sought to (i) identify the main factors shaping the attitudes towards environmental injustices and (ii) to analyse the attitudes and perception of the various social groups and (iii) to identify the main factors which are shaping the attitudes and actions of those who were affected by the floods of 2001 and 2010 through the use of decision tree method. The data for the predictive model was acquired from a questionnaire survey conducted in two disadvantaged and flood-hit Hungarian regions. Based on the survey data, a principal component analysis (PCA) was conducted, which resulted in three principal components; fear, social change, and change in the built environment. The study focused only on the elements of the “fear principal component”, due to the decision tree tool homogenous groups identified in relation to this component. Our analysis showed that ethnicity has a determinative role in the emergence and the level of fear from floods; the Roma respondents expressed a significantly higher level of fear than others.

P1.11-36 A Simple Tool to Prioritize US Ever-Smokers for CT Screening Eligibility Assessment

CT lung cancer screening can be more efficient when risk models are used to determine eligibility. However, detailed risk assessment requires time spent by a healthcare provider and may present a barrier to screening when resources are limited. Here, we developed a tool to identify ever-smokers with low probability of risk-based eligibility. We analyzed ever-smokers aged 50-80 in the representative 2015 US National Health Interview Survey. We defined ever-smokers with 6-year risk ≥1.3% by the 12-question PLCOm2012 model as screening-eligible. We considered that detailed risk assessment may be inefficient when the probability of eligibility is less than 5%. Accordingly, we used cross-tabulations of age, cigarettes-per-day, and quit-years to identify groups in whom risk assessment might be avoided. There are approximately 44,140,774 U.S. ever-smokers aged 50-80 who could consider detailed risk assessment. However, a simple decision-tree tool identified 22,293,477 ever-smokers (50.5%) who are less than 5% likely to be screening-eligible (Figure). This includes all those who smoke(d) less than 5 cigarettes-per-day. Over 1 year, approximately 103,512 lung cancers were predicted among eligible ever-smokers. If our tool were used, then 1,784 of these eligible cases (1.7%) would not undergo detailed risk assessment or screening. When resources are limited, a simple decision-tree tool could avoid detailed risk assessment for more than half of U.S. ever smokers aged 50-80, while still identifying 98.3% of eligible cases. Such a tool could be self-administered by patients in the waiting room or applied automatically to electronic health records to optimize use of provider time.