Integrating self-efficacy in the cyclical process of paediatric asthma management: a new perspective.

Asthma management consists of a cyclical process based on clinical assessment of the patient, the implementation of therapeutic adjustments, and evaluation of the patient's response. Self-efficacy is the person's confidence in his or her ability to successfully perform a behaviour and guides the patient's decisions for producing healthy behaviours.Studies have shown that asthma management is related to self-efficacy, which in turn can be influenced by various psychosocial factors. A literature search on the relationship between asthma and self-efficacy in paediatric age, has allowed us to hypothesize that adequate levels of self-efficacy might be achieved through a cyclical process, 'the self-efficacy cycle', taking into account assessment, identification of modifiable risk factors and patient's response. This would make it easier to identify the personal and social aspects on which to intervene to promote a proper management of the disease.

Endotyping allergic rhinitis in children: A machine learning approach.

INTRODUCTION: The diversity of allergic rhinitis (AR) phenotypes is particularly evident in childhood, suggesting the need to analyze and identify new approaches to capture such clinical heterogeneity. Nasal cytology (NC) is a very useful diagnostic tool for identifying and quantifying nasal inflammation. Data-driven approaches such as latent class analysis (LCA) assign subjects to classes based on their characteristics. We hypothesized that LCA based on NC, including the assessment of neutrophils, eosinophils, and mast cells, may be helpful for identifying AR endotypes in children. METHODS: A total of 168 children were enrolled. Sociodemographic characteristics and detailed medical history were obtained from their parents. All children performed NC and skin prick tests. LCA was applied for identifying AR endotypes based on NC, using the R package poLCA. All the statistical analyses were performed using R 4.0.5 software. Statistical significance was set at p ≤ .05. RESULTS: LCA identified two classes: Class 1 (n = 126, 75%): higher frequency of children with moderate/large number of neutrophils (31.45%); almost all the children in this class had no mast cells (91.27%) and Class 2 (n = 42, 25%): higher frequency of children with moderate/large number of eosinophils (45.24%) and moderate/large number of mast cells (50%). CONCLUSIONS: The present study used a machine learning approach for endotyping childhood AR, which may contribute to improve the diagnostic accuracy and to deliver personalized health care in the context of precision medicine.

The Dietary Inflammatory Index and asthma burden in children: A latent class analysis.

INTRODUCTION: Unbalanced dietary intake has been increasingly recognized as an important modifiable risk factor for asthma. In this study, we assessed whether a pro-inflammatory diet is associated with higher asthma burden in three steps: (1) identification of asthma latent classes (LC) based on symptoms, indoor exposures, and pulmonary function; (2) identification of risk factors associated with LC membership; and (3) estimation of the probabilities of LC membership with variation in DII. METHODS: A cross-sectional study on 415 children aged 5-14 years (266 with persistent asthma and 149 controls). LC analysis was performed in asthmatic children. The DII was calculated based on a semiquantitative food frequency questionnaire. Elastic net logistic regression was used to investigate whether increasing DII was associated with worse asthma burden. RESULTS: Two LCs were identified. Children in Class 1, "high burden," had higher symptom burden and worse lung function. Children in Class 2, "low burden," had lower symptom burden and less impaired lung function but were more subject to indoor exposures. DII was the only risk factor significantly associated with Class 1 membership. As the DII increased (from -4.0 to +4.0), the probability of Class 1 membership increased from 32% to 65% when compared with control group, whereas it increased from 41% to 72% when compared with Class 2. CONCLUSIONS: We identified two phenotypes of persistent asthma associated with different disease burden linked to indoor exposures. An increasing DII was associated with high-burden asthma, providing further evidence about the role of a pro-inflammatory diet in asthma morbidity.

Social robots and therapeutic adherence: A new challenge in pediatric asthma?

Social Robots are used in different contexts and, in healthcare, they are better known as Socially Assistive Robots. In the context of asthma, the use of Socially Assistive Robots has the potential to increase motivation and engagement to treatment. Other positive roles proposed for Socially Assistive Robots are to provide education, training regarding treatments, and feedback to patients. This review evaluates emerging interventions for improving treatment adherence in pediatric asthma, focusing on the possible future role of social robots in the clinical practice.

Rhinomanometry: point of care test (POCT) for allergic rhinitis in children?

Allergic rhinitis (AR) is a global health problem: its prevalence is 23% in Europe, although it is underestimated because as many as 45% of the cases remain undiagnosed. Globally, almost 500 million people suffer from AR, which shows its increasing incidences. The diagnostic course of AR is based on clinical history, supported by anterior rhinoscopy. This inspects the anterior part of the nasal cavity accompanied by allergic sensitivity tests (cutaneous allergic skin tests or specific immunoglobulin E levels). The availability of standardised diagnostic procedures is able to provide objective evaluations of inflammatory situation, and the degree of nasal obstruction may give an advantage in reducing the risk of underestimating the diagnosis of AR. Diagnostic tests with a high level of accuracy are able to provide immediate results, which can sustain the doctor in diagnostic-therapeutic framework. The development of Point of Care Tests (POCTs) could be a useful tool. Considering that nasal obstruction is the most common symptom in patients with AR, the rhinomanometry (RM) test is the most indicated objective evaluation for nasal obstruction. Several studies have also shown the practicability of such diagnostic techniques applied in children. So far, no study has evaluated whether all the applicable requirements are fulfilled by RM in order to be considered as a POCT. The purpose of this perspective was to assess whether all the POCT requirements are fulfilled by RM by conducting a narrative review of the existing literature in which RM has been used in the diagnosis and management of AR in children. A few but encouraging results of studies on children supported the potential use of RM in the area of POCT. However, costs of instruments and the training of personnel involved remain to be explored. The studies support the potential use of RM in POCTs.

RAPP-children: A new tool for assessing quality of life in patients with asthma and rhinitis.

BACKGROUND: RhinAsthma Patient Perspective (RAPP) is a short, validated questionnaire for assessing health-related quality of life (HRQoL) in adult patients with comorbid asthma and rhinitis, while a paediatric version is still not available. OBJECTIVE: The current study aimed to develop and validate the RAPP-children questionnaire. METHODS: RAPP-children was derived by combining RhinAsthma-children subscales into five unique items. At baseline (T0) and after 30 days (T1), 150 children (6-11 years) with comorbid asthma (predominantly intermittent or mild persistent) and rhinitis were given the following: RAPP-children, RhinAsthma-children, Paediatric Asthma Quality of Life Questionnaire (PAQLQ, age >6 years), Paediatric Rhinoconjunctivitis Quality of Life Questionnaire (PRQLQ), Childhood Asthma Control Test (CACT), KiddyKindl® (age 6 years) or KidKindl® (age >6 years), and a Visual Analogue Scale for nasal symptoms (VAS). At the final visit, a Global Rating of Change (GRC) scale was administered. The approved study was registered on the central registration system ClinicalTrials.gov (ID: NCT03276416). RESULTS: RAPP-children fairly reproduced RhinAsthma-children scores (concordance correlation coefficients between 0.91 and 0.95). RAPP-children showed adequate convergent validity (absolute Spearman's rho larger than 0.5 with PAQLQ, PRQLQ, CACT, KiddyKindl/KidKindl, and VAS), internal consistency (Cronbach's alpha > 0.70), repeatability (intra-cluster correlation coefficient between 0.61 and 0.8) in the presence of clinical stability (GRC = 0), discriminant validity (sensitivity to asthma control status and rhinitis severity), and sensitivity to symptom improvements (GRC > 1). The minimal important difference (MID) was -20. Floor and ceiling effects were minimal. RAPP-children showed fair usability also in younger children (6-8 years). CONCLUSION & CLINICAL RELEVANCE: RAPP-children is a valid, five-item questionnaire for assessing HRQoL in children aged 6 to 11 years with concomitant asthma and rhinitis. Although further investigation is required in moderate and severe asthmatics, this tool can be useful in clinical trials and in routine medical practice for improving the management of respiratory allergy in children.

Associations of greenness, greyness and air pollution exposure with children's health: a cross-sectional study in Southern Italy.

BACKGROUND: Due to the complex interplay among different urban-related exposures, a comprehensive approach is advisable to estimate the health effects. We simultaneously assessed the effect of "green", "grey" and air pollution exposure on respiratory/allergic conditions and general symptoms in schoolchildren. METHODS: This study involved 219 schoolchildren (8-10 years) of the Municipality of Palermo, Italy. Data were collected through questionnaires self-administered by parents and children. Exposures to greenness and greyness at the home addresses were measured using the normalized difference vegetation index (NDVI), residential surrounding greyness (RSG) and the CORINE land-cover classes (CLC). RSG was defined as the percentage of buffer covered by either industrial, commercial and transport units, or dump and construction sites, or urban fabric related features. Two specific categories of CLC, namely "discontinuous urban fabric - DUF" - and "continuous urban fabric - CUF" - areas were found. Exposure to traffic-related nitrogen dioxide (NO2) was assessed using a Land-Use Regression model. A symptom score ranging from 0 to 22 was built by summing affirmative answers to twenty-two questions on symptoms. To avoid multicollinearity, multiple Logistic and Poisson ridge regression models were applied to assess the relationships between environmental factors and self-reported symptoms. RESULTS: A very low exposure to NDVI ≤0.15 (1st quartile) had a higher odds of nasal symptoms (OR = 1.47, 95% CI [1.07-2.03]). Children living in CUF areas had higher odds of ocular symptoms (OR = 1.49, 95% CI [1.10-2.03]) and general symptoms (OR = 1.18, 95% CI [1.00-1.48]) than children living in DUF areas. Children living in proximity (≤200 m) to High Traffic Roads (HTRs) had increased odds of ocular (OR = 1.68, 95% CI [1.31-2.17]) and nasal symptoms (OR = 1.49, 95% CI [1.12-1.98]). A very high exposure to NO2 ≥ 60 µg/m3 (4th quartile) was associated with a higher odds of general symptoms (OR = 1.28, 95% CI [1.10-1.48]). No associations were found with RGS. A Poisson ridge regression model on the symptom score showed that children living in proximity to HTRs (≤200 m) had a higher symptoms score (RR = 1.09, 95% CI [1.02-1.17]) than children living > 200 m from HTRs. Children living in CUF areas had a higher symptoms score (RR = 1.11, 95% CI [1.03-1.19]) than children living in DUF areas. CONCLUSIONS: Multiple exposures related to greenness, greyness (measured by CORINE) and air pollution within the urban environment are associated with respiratory/allergic and general symptoms in schoolchildren. No associations were found when considering the individual exposure to greyness measured using the RSG indicator.

Efficacy of Buffered Hypertonic Saline Nasal Irrigation for Nasal Symptoms in Children with Seasonal Allergic Rhinitis: A Randomized Controlled Trial.

BACKGROUND: Saline nasal irrigation is labelled as an add-on treatment in patients with allergic rhinitis (AR). The primary aim of this study was to compare the efficacy of 21-day use of buffered hypertonic saline (BHS) versus normal saline solution (NSS) on reducing nasal symptoms in children with seasonal AR (SAR). Comparing their efficacy on nasal cytology counts (NCC), quality of life, and sleep quality was the secondary aim. METHODS: In this 21-day, open-label, randomized controlled study, 36 SAR children (aged 6-13 years) with a Total 5 Symptom Score (T5SS) ≥5 received twice-daily BHS or NSS delivered through a nasal douche. Efficacy measures were least square mean changes (LSmc) in T5SS, NCC, Paediatric Rhinoconjunctivitis Quality of Life Questionnaire (PRQLQ), and Pittsburgh Sleep Quality Index (PSQI) scores. RESULTS: BHS improved the T5SS total score to a greater extent than NSS (LSmc -6.45 vs. -5.45, p < 0.001). Concerning NCC, BHS significantly reduced the scores of neutrophils (LSmc -0.76, p = 0.004) and eosinophils (LSmc -0.46, p = 0.018), while NSS did not. Similarly, only BHS yielded a significant improvement in the PRQLQ score (LSmc -0.57, p = 0.009), whereas the improvement in PSQI score was comparable between the BHS (LSmc -0.77, p = 0.025) and NSS (LSmc -1.39, p < 0.001) groups. Overall, BHS was well tolerated. CONCLUSIONS: In children with SAR, BHS is effective in improving nasal symptoms and NCC, with an associated beneficial effect on quality of life.

Development of a nomogram to estimate the quality of life in asthmatic children using the Childhood Asthma Control Test.

BACKGROUND: Pediatric Asthma Quality of Life Questionnaire (PAQLQ) provides detailed information on QoL in asthmatic children, whereas Childhood Asthma Control Test (C-ACT) Questionnaire is the most validated instrument for asthma control. No study assessed the relationship between C-ACT and QoL in children by means of those instruments. The aim of this study was to determine whether a QoL estimation is possible using the C-ACT questionnaire in asthmatic children. METHODS: Medical history, spirometry, C-ACT, and PAQLQ were assessed in 144 (60% male) outpatient asthmatic children from September 2011 to November 2014. A generalized linear model (GLM) for the prediction of PAQLQ was obtained through a stepwise procedure starting from a full model with all C-ACT items, and predictive nomograms were created. RESULTS: Fifty-five (38%) well-controlled (WC) asthma, 37 (26%) partially controlled (PC) asthma, and 52 (36%) uncontrolled asthma (UA) patients were enrolled. Persistent asthmatics (PA) were significantly more uncontrolled (p < 0.0001). A significant reduction in FEV1 , FEV1 /FVC, and FEF25-75 (p = 0.005, p < 0.0001, and p < 0.001, respectively) was found in WC vs. UA. Through a stepwise process, a reduced model showed a positive relationship between the PAQLQ and the four items of C-ACT. The regression equations for predicted PAQLQ were ln(PAQLQ) = 1.17 + 0.05*C-ACT2 + 0.03*C-ACT3 + 0.04*C-ACT6 + 0.03*C-ACT7. Thus, a nomogram was constructed. CONCLUSION: The designed nomogram provides a highly predictive assessment of QoL in individual patients, facilitating a more comprehensive assessment of asthmatic children in usual clinical care.

RHINASTHMA-Adolescents: a new quality of life tool for patients with respiratory allergy.

BACKGROUND: Specific instruments for health-related quality of life (HRQoL) assessment in adolescents with rhinoconjunctivitis or asthma are available. None of them evaluates rhinitis and asthma together, although they often coexist. Our aim was to validate a HRQoL questionnaire for adolescents with rhinoconjunctivitis, asthma, or both. METHODS: A pool of 38 items covering the main symptoms and problems related to respiratory allergy was generated based on literature review, clinical experience, and unstructured interviews to 54 adolescents. The items were randomly listed and presented to 88 consecutive outpatients (44 M; mean age 15.2 ± 3.1). Patients had to indicate which item they had experienced and, for each selected item, its importance on a four-point scale (1 = not at all; 4 = very much). Twelve items were excluded from the list, because of low importance. In the validation phase, 102 patients (54 M; mean age 15.36 ± 1.12) completed the KINDL, a generic HRQoL tool, and the new questionnaire (RHINASTHMA-Adolescents). RESULTS: Factor analysis revealed a five-dimensional structure, which explained up to 71.23% of the total variance. Association between RHINASTHMA-Adolescents and KINDL scores was all in the expected direction. Internal consistency for the extracted factors was satisfactory: Upper Airways (0.81), Lower Airways (0.89), Emotions (0.85), Social Relationship (0.79), Daily life management (0.74). Reliability was good for all factors with a Pearson coefficient ranged from 0.91 to 0.99. CONCLUSIONS: RHINASTHMA-Adolescents is the first tool for evaluating HRQoL in patients with rhinitis and/or asthma. It provides a simple assessment and met the standards of validity, internal consistency, and reliability.

Smoke exposure as a risk factor for asthma in childhood: a review of current evidence.

Asthma is a common chronic multifactorial disease that affects >300 million people worldwide. Outdoor and indoor pollution exposure has been associated with respiratory health effects in adults and children. Smoking still represents a huge public health problem and millions of children suffer the detrimental effects of passive smoke exposure. This study was designed to review the current evidences on exposure to passive smoke as a risk factor for asthma onset in childhood. A review of the most recent studies on this topic was undertaken to provide evidence about the magnitude of the effect of passive smoking on the risk of incidence of asthma in children. The effects of passive smoking are different depending on individual and environmental factors. Environmental tobacco smoke (ETS) is one of the most important indoor air pollutants and can interact with other air pollutants in eliciting respiratory outcomes during childhood. The increased risk of respiratory outcomes in children exposed to prenatal and early postnatal passive smoke might be caused by an adverse effect on both the immune system and the structural and functional development of the lung; this may explain the subsequent increased risk of incident asthma. The magnitude of the exposure is quite difficult to precisely quantify because it is significantly influenced by the child's daily activities. Because exposure to ETS is a likely cause for asthma onset in childhood, there is a strong need to prevent infants and children from breathing air contaminated with tobacco smoke.

Assessing external exposome by implementing an Environmental Data Management System using Open Data.

Due to the increasing importance of exposome in environmental epidemiology, feasibility and usefulness of an Environmental Data Management System (EDMS) using Open Data was evaluated. The EDMS includes data from 10 European cities (Celje (Slovenia), Lódz (Poland), Manchester (UK), Palermo (Italy), Paris (France), Porto (Portugal), Regensburg (Germany), Reus (Spain), Rijeka (Croatia), Thessaloniki (Greece)) about external non-specific and specific exposome factors at the city or country level (2017-2020). Findings showed that the highest values of life expectancy were in Reus females (86 years) and Palermo males (81 years). UK had the highest obesity rate (28%), Croatia the highest prescribed drug consumption (62%), Greece and Portugal the highest smoking rates (37%, 42%) and daily alcohol consumption (21%), respectively. The most polluted cities were Thessaloniki for PM10 (38 µg/m3), Lódz for PM2.5 (25 µg/m3), Porto for NO2 (62 µg/m3) and Rijeka for O3 (92 µg/m3). Thessaloniki had the highest grey space (98%) and Lódz the highest cumulative amount of pollen (39,041 p/m3). The highest daily noise levels ≥ 55 dB was in Reus (81% to traffic) and Regensburg (21% to railway). In drinking water, arsenic had the highest value in Thessaloniki (6.4 µg/L), boron in Celje (24 mg/L) and lead in Paris (46.7 µg/L). Portugal and Greece showed the highest pesticide residues in food (7%). In conclusion, utilizing open-access databases enables the translation of research findings into actionable strategies for public health interventions.

Asthma-Related Knowledge and Practices among Mothers of Asthmatic Children: A Latent Class Analysis.

Mothers' knowledge about childhood asthma influences management practices and disease control, but validating knowledge/practice questionnaires is difficult due to the lack of a gold standard. We hypothesized that Latent Class Analysis (LCA) could help identify underlying mother profiles with similar knowledge/practices. A total of 438 mothers of asthmatic children answered a knowledge/practice questionnaire. Using answers to the knowledge/practice questionnaire as manifest variables, LCA identified two classes: Class 1, "poor knowledge" (33%); Class 2, "good knowledge" (67%). Classification accuracy was 0.96. Mothers in Class 2 were more likely to be aware of asthma-worsening factors and indicators of attacks. Mothers in Class 1 were more likely to prevent exposure to tobacco smoke (91.1% vs. 78.8%, p = 0.005). For attacks, mothers in Class 2 were more likely to go to the emergency department and follow the asthma action plan. Mothers in Class 2 more frequently had a high education level (79.5% vs. 65.2%, p = 0.004). Children in Class 2 more frequently had fully controlled asthma (36.7% vs. 25.9%, p = 0.015) and hospitalizations for attacks in the previous 12 months (24.2% vs. 10.7%, p = 0.003). LCA can help discover underlying mother profiles and plan targeted educational interventions.

Asthma Comorbidities: Frequency, Risk Factors, and Associated Burden in Children and Adolescents.

Identifying asthma comorbidities in children is fundamental for improving disease management. We aimed to investigate the frequency of allergy-related comorbidities in children and adolescents with asthma, and to identify associated risk factors and disease burden. Between September 2015 and December 2018, 508 asthmatic patients (5-17 years) were consecutively enrolled. Parents answered a standardized questionnaire on the history of disease and risk factors. Comorbidities were classified based on the involvement of respiratory and/or extra-respiratory districts: asthma only (A, 13%), asthma with respiratory comorbidities (AR, 37%), asthma with extra-respiratory comorbidities (AER, 10%), and asthma with both respiratory and extra-respiratory comorbidities (ARER, 40%). Multinomial logistic regression showed that membership in the AR group was significantly associated with a maternal history of asthma (OR = 3.08, 95% CI: 1.23-7.72), breastfeeding ≥ three months (OR = 1.92, 1.06-3.46), early mold exposure (OR = 2.39, 1.12-5.11), and current environmental tobacco smoke exposure (OR = 2.06, 1.11-3.83). Membership in the AER group was significantly associated with the female gender (OR = 3.43, 1.54-7.68), breastfeeding ≥ three months (OR = 2.77, 1.23-6.22). ARER was significantly associated with all the aforementioned exposures. Patients with AR reported exacerbations in the last 12 months more frequently (p = 0.009). Several personal and environmental risk factors are associated with comorbidities in asthmatic children and adolescents, possibly worsening the disease burden.

Association between Asthma Control and Exposure to Greenness and Other Outdoor and Indoor Environmental Factors: A Longitudinal Study on a Cohort of Asthmatic Children.

Achieving and maintaining asthma control (AC) is the main goal of asthma management. Indoor and outdoor environmental factors may play an important role on AC. The aim of this longitudinal study was to evaluate the association between AC and exposure to greenness and other outdoor or indoor environmental factors in a cohort of asthmatic children. This study involved 179 asthmatic children (5-16 years). Parents were interviewed through a modified version of the SIDRIA questionnaire. AC was assessed at each visit. Exposure to greenness was measured using the normalized difference vegetation index (NDVI). A logistic regression model was applied for assessing risk factors for uncontrolled asthma (UA). Low NDVI exposure was a risk factor for UA (OR: 2.662, 95% CI (1.043-6.799)); children exposed to passive smoke during pregnancy had a higher risk of UA than those non-exposed to passive smoke during pregnancy (OR: 3.816, 95% CI (1.114-13.064)); and a unit increase in the crowding index was associated with an increased risk of UA (OR: 3.376, 95% CI (1.294-8.808)). In conclusion, the current study provided a comprehensive assessment of urban-related environmental exposures on asthma control in children, using multiple indicators of greenness and other outdoor or indoor environmental factors.

Effects of Polycyclic Aromatic Hydrocarbons on Lung Function in Children with Asthma: A Mediation Analysis.

Studies investigating the association between urinary Polycyclic Aromatic Hydrocarbons (PAHs) and asthma in children provided inhomogeneous results. We aimed to use Mediation Analysis to discover whether a link between urinary PAHs and lung function exists and if it might be ascribed to a direct or a symptom-mediated (indirect) effect in children with asthma. This single-center prospective study was conducted in Palermo, Italy, between March and July 2017 and involved 50 children with persistent mild-moderate asthma, aged 6-11 years. At each time visit (day 0, 30, 60, and 90), physical examination, spirometry, and urine collection for detection of urinary cotinine and PAHs were performed. A symptom score was computed. The sum of individually calculated molar mass of nine PAH metabolites (ΣPAH), naphthalene metabolites (ΣPAHn) and phenanthrene metabolites (ΣPAHp) were calculated. Three children withdrew from the study due to technical problems (n = 1) and adverse events (n = 2). PAHs indirect effects on FEV1 (ΣPAH: -0.011, p = 0.04; ΣPAHn: -0.011, p = 0.04; ΣPAHp: -0.012, p < 0.001) and FVC (ΣPAH: -0.012, p = 0.02; ΣPAHn: -0.0126, p = 0.02; ΣPAHp: -0.013, p < 0.001) were statistically significant. In conclusion, PAHs exposures have significant indirect (symptom-mediated) effects on lung function, emphasizing the role of PAHs-induced respiratory morbidity in decreasing lung function in children with asthma.

Machine Learning: An Overview and Applications in Pharmacogenetics.

This narrative review aims to provide an overview of the main Machine Learning (ML) techniques and their applications in pharmacogenetics (such as antidepressant, anti-cancer and warfarin drugs) over the past 10 years. ML deals with the study, the design and the development of algorithms that give computers capability to learn without being explicitly programmed. ML is a sub-field of artificial intelligence, and to date, it has demonstrated satisfactory performance on a wide range of tasks in biomedicine. According to the final goal, ML can be defined as Supervised (SML) or as Unsupervised (UML). SML techniques are applied when prediction is the focus of the research. On the other hand, UML techniques are used when the outcome is not known, and the goal of the research is unveiling the underlying structure of the data. The increasing use of sophisticated ML algorithms will likely be instrumental in improving knowledge in pharmacogenetics.

A Methodological Framework to Discover Pharmacogenomic Interactions Based on Random Forests.

The identification of genomic alterations in tumor tissues, including somatic mutations, deletions, and gene amplifications, produces large amounts of data, which can be correlated with a diversity of therapeutic responses. We aimed to provide a methodological framework to discover pharmacogenomic interactions based on Random Forests. We matched two databases from the Cancer Cell Line Encyclopaedia (CCLE) project, and the Genomics of Drug Sensitivity in Cancer (GDSC) project. For a total of 648 shared cell lines, we considered 48,270 gene alterations from CCLE as input features and the area under the dose-response curve (AUC) for 265 drugs from GDSC as the outcomes. A three-step reduction to 501 alterations was performed, selecting known driver genes and excluding very frequent/infrequent alterations and redundant ones. For each model, we used the concordance correlation coefficient (CCC) for assessing the predictive performance, and permutation importance for assessing the contribution of each alteration. In a reasonable computational time (56 min), we identified 12 compounds whose response was at least fairly sensitive (CCC > 20) to the alteration profiles. Some diversities were found in the sets of influential alterations, providing clues to discover significant drug-gene interactions. The proposed methodological framework can be helpful for mining pharmacogenomic interactions.