Boosting predictive models and augmenting patient data with relevant genomic and pathway information.

The recurrence of low-stage lung cancer poses a challenge due to its unpredictable nature and diverse patient responses to treatments. Personalized care and patient outcomes heavily rely on early relapse identification, yet current predictive models, despite their potential, lack comprehensive genetic data. This inadequacy fuels our research focus-integrating specific genetic information, such as pathway scores, into clinical data. Our aim is to refine machine learning models for more precise relapse prediction in early-stage non-small cell lung cancer. To address the scarcity of genetic data, we employ imputation techniques, leveraging publicly available datasets such as The Cancer Genome Atlas (TCGA), integrating pathway scores into our patient cohort from the Cancer Long Survivor Artificial Intelligence Follow-up (CLARIFY) project. Through the integration of imputed pathway scores from the TCGA dataset with clinical data, our approach achieves notable strides in predicting relapse among a held-out test set of 200 patients. By training machine learning models on enriched knowledge graph data, inclusive of triples derived from pathway score imputation, we achieve a promising precision of 82% and specificity of 91%. These outcomes highlight the potential of our models as supplementary tools within tumour, node, and metastasis (TNM) classification systems, offering improved prognostic capabilities for lung cancer patients. In summary, our research underscores the significance of refining machine learning models for relapse prediction in early-stage non-small cell lung cancer. Our approach, centered on imputing pathway scores and integrating them with clinical data, not only enhances predictive performance but also demonstrates the promising role of machine learning in anticipating relapse and ultimately elevating patient outcomes.

Sexual dysfunction in patients with cancer, a challenge in oncology practice: results of the CLARIFY project.

BACKGROUND: Sexual dysfunction (SD) associated with oncological treatment is a common and understudied disorder. Our aim was to characterize SD in a cohort of Spanish patients. METHODS: Analytic observational study in patients included in the CLARIFY H2020 project at the Hospital Universitario Puerta de Hierro. Clinical variables and validated measures of sexual function were collected from October 2020 to May 2022. Frequency and quality of sexual activity were assessed. Descriptive, trend associations, and logistic regression analyses were performed. RESULTS: A total of 383 patients were included: breast cancer 68.14% (261), lung cancer 26.37% (101), and lymphoma 5.50% (21). Mean age was 56.5 years (range 33-88). 19.58% (75) were men and 80.42% (308) were women. 69% and 31% of men and women, respectively, reported being sexually active. The absolute frequency of overall sexual dissatisfaction was 76% in women and 24% in men. Women with breast cancer were most likely to have severe sexual dysfunction. Those with early disease had resolved complaints after 5 years. In multinomial logistic regression, significant associations were found in women with metastatic breast cancer and severe disorders of arousal (p 0.000), lubrication (p 0.002), orgasm (p 0.000), as well as dissatisfaction with sexual performance (p 0.000) and global sexual dissatisfaction (p 0.000). Women with lung cancer have severe arousal dysfunction (p 0.016) and global sexual dissatisfaction (p 0.044). CONCLUSIONS: Our population has a high prevalence of SD, which supports the need to increase awareness of this disorder among the medical oncology team and the importance of including sexual health assessment in oncological patient follow-up.

Transformers for extracting breast cancer information from Spanish clinical narratives.

The wide adoption of electronic health records (EHRs) offers immense potential as a source of support for clinical research. However, previous studies focused on extracting only a limited set of medical concepts to support information extraction in the cancer domain for the Spanish language. Building on the success of deep learning for processing natural language texts, this paper proposes a transformer-based approach to extract named entities from breast cancer clinical notes written in Spanish and compares several language models. To facilitate this approach, a schema for annotating clinical notes with breast cancer concepts is presented, and a corpus for breast cancer is developed. Results indicate that both BERT-based and RoBERTa-based language models demonstrate competitive performance in clinical Named Entity Recognition (NER). Specifically, BETO and multilingual BERT achieve F-scores of 93.71% and 94.63%, respectively. Additionally, RoBERTa Biomedical attains an F-score of 95.01%, while RoBERTa BNE achieves an F-score of 94.54%. The findings suggest that transformers can feasibly extract information in the clinical domain in the Spanish language, with the use of models trained on biomedical texts contributing to enhanced results. The proposed approach takes advantage of transfer learning techniques by fine-tuning language models to automatically represent text features and avoiding the time-consuming feature engineering process.

Examining explainable clinical decision support systems with think aloud protocols.

Machine learning tools are increasingly used to improve the quality of care and the soundness of a treatment plan. Explainable AI (XAI) helps users in understanding the inner mechanisms of opaque machine learning models and is a driver of trust and adoption. Explanation methods for black-box models exist, but there is a lack of user studies on the interpretability of the provided explanations. We used a Think Aloud Protocol (TAP) to explore oncologists' assessment of a lung cancer relapse prediction system with the aim of refining the purpose-built explanation model for better credibility and utility. Novel to this context, TAP is used as a neutral methodology to elicit experts' thought processes and judgements of the AI system, without explicit prompts. TAP aims to elicit the factors which influenced clinicians' perception of credibility and usefulness of the system. Ten oncologists took part in the study. We conducted a thematic analysis of their verbalized responses, generating five themes that help us to understand the context within which oncologists' may (or may not) integrate an explainable AI system into their working day.

Machine Learning-Assisted Recurrence Prediction for Patients With Early-Stage Non-Small-Cell Lung Cancer.

PURPOSE: Stratifying patients with cancer according to risk of relapse can personalize their care. In this work, we provide an answer to the following research question: How to use machine learning to estimate probability of relapse in patients with early-stage non-small-cell lung cancer (NSCLC)? MATERIALS AND METHODS: For predicting relapse in 1,387 patients with early-stage (I-II) NSCLC from the Spanish Lung Cancer Group data (average age 65.7 years, female 24.8%, male 75.2%), we train tabular and graph machine learning models. We generate automatic explanations for the predictions of such models. For models trained on tabular data, we adopt SHapley Additive exPlanations local explanations to gauge how each patient feature contributes to the predicted outcome. We explain graph machine learning predictions with an example-based method that highlights influential past patients. RESULTS: Machine learning models trained on tabular data exhibit a 76% accuracy for the random forest model at predicting relapse evaluated with a 10-fold cross-validation (the model was trained 10 times with different independent sets of patients in test, train, and validation sets, and the reported metrics are averaged over these 10 test sets). Graph machine learning reaches 68% accuracy over a held-out test set of 200 patients, calibrated on a held-out set of 100 patients. CONCLUSION: Our results show that machine learning models trained on tabular and graph data can enable objective, personalized, and reproducible prediction of relapse and, therefore, disease outcome in patients with early-stage NSCLC. With further prospective and multisite validation, and additional radiological and molecular data, this prognostic model could potentially serve as a predictive decision support tool for deciding the use of adjuvant treatments in early-stage lung cancer.

Synergy between imputed genetic pathway and clinical information for predicting recurrence in early stage non-small cell lung cancer.

OBJECTIVE: Lung cancer exhibits unpredictable recurrence in low-stage tumors and variable responses to different therapeutic interventions. Predicting relapse in early-stage lung cancer can facilitate precision medicine and improve patient survivability. While existing machine learning models rely on clinical data, incorporating genomic information could enhance their efficiency. This study aims to impute and integrate specific types of genomic data with clinical data to improve the accuracy of machine learning models for predicting relapse in early-stage, non-small cell lung cancer patients. METHODS: The study utilized a publicly available TCGA lung cancer cohort and imputed genetic pathway scores into the Spanish Lung Cancer Group (SLCG) data, specifically in 1348 early-stage patients. Initially, tumor recurrence was predicted without imputed pathway scores. Subsequently, the SLCG data were augmented with pathway scores imputed from TCGA. The integrative approach aimed to enhance relapse risk prediction performance. RESULTS: The integrative approach achieved improved relapse risk prediction with the following evaluation metrics: an area under the precision-recall curve (PR-AUC) score of 0.75, an area under the ROC (ROC-AUC) score of 0.80, an F1 score of 0.61, and a Precision of 0.80. The prediction explanation model SHAP (SHapley Additive exPlanations) was employed to explain the machine learning model's predictions. CONCLUSION: We conclude that our explainable predictive model is a promising tool for oncologists that addresses an unmet clinical need of post-treatment patient stratification based on the relapse risk while also improving the predictive power by incorporating proxy genomic data not available for specific patients.

Clinical factors influencing long-term survival in a real-life cohort of early stage non-small-cell lung cancer patients in Spain.

Background: Current prognosis in oncology is reduced to the tumour stage and performance status, leaving out many other factors that may impact the patient´s management. Prognostic stratification of early stage non-small-cell lung cancer (NSCLC) patients with poor prognosis after surgery is of considerable clinical relevance. The objective of this study was to identify clinical factors associated with long-term overall survival in a real-life cohort of patients with stage I-II NSCLC and develop a prognostic model that identifies features associated with poor prognosis and stratifies patients by risk. Methods: This is a cohort study including 505 patients, diagnosed with stage I-II NSCLC, who underwent curative surgical procedures at a tertiary hospital in Madrid, Spain. Results: Median OS (in months) was 63.7 (95% CI, 58.7-68.7) for the whole cohort, 62.4 in patients submitted to surgery and 65 in patients submitted to surgery and adjuvant treatment. The univariate analysis estimated that a female diagnosed with NSCLC has a 0.967 (95% CI 0.936 - 0.999) probability of survival one year after diagnosis and a 0.784 (95% CI 0.712 - 0.863) five years after diagnosis. For males, these probabilities drop to 0.904 (95% CI 0.875 - 0.934) and 0.613 (95% CI 0.566 - 0.665), respectively. Multivariable analysis shows that sex, age at diagnosis, type of treatment, ECOG-PS, and stage are statistically significant variables (p<0.10). According to the Cox regression model, age over 50, ECOG-PS 1 or 2, and stage ll are risk factors for survival (HR>1) while adjuvant chemotherapy is a good prognostic variable (HR<1). The prognostic model identified a high-risk profile defined by males over 71 years old, former smokers, treated with surgery, ECOG-PS 2. Conclusions: The results of the present study found that, overall, adjuvant chemotherapy was associated with the best long-term OS in patients with resected NSCLC. Age, stage and ECOG-PS were also significant factors to take into account when making decisions regarding adjuvant therapy.

Long-term outcomes in Hodgkin lymphoma survivors. Temporary trends and comparison with general population.

The high cure rates of Hodgkin lymphoma (HL) make this oncological disease among those with the greatest number of long-term survivors. This single-institution study including 383 HL patients with up to 45 years of follow-up, analyses the morbidity and mortality of this population after treatments in comparison with the overall Spanish population, and investigates whether it has changed over time stratifying by periods of time, as a consequence of therapeutic optimization. The median age was 34.8 years (range 15-87) with median overall survival of 30 years, significantly higher in women (HR 0.58, 95% CI 0.42-0.79) (p = 0.0002). 185 late-stage diseases were noted (35% patients), cardiovascular disease (CVD) being the most frequent (23.2%). 30% of patients developed at least one second malignant neoplasm (SMN) to give a total of 174 SMNs. 20.9% of the patients died from HL and 67.0% died from non-HL causes (32.2% from SMN, 17% from CVD). The overall standardized mortality ratio (SMR) was 3.57 (95% CI: 3.0-4.2), with striking values of 7.73 (95% CI: 5.02-8.69) and of 14.75 (95% CI: 11.38-19.12) for women and patients <30 years at diagnosis, respectively. Excluding HL as the cause of death, the SMRs of those diagnosed before 2000 and from 2000 were proved to be similar (3.88 vs 2.73), maintaining in this last period an unacceptable excess of mortality due to secondary toxicity in patients cured of HL. Our study confirm that HL treatment substantially reduces the life expectancy of patients cured of HL. In recent periods, despite therapeutic optimization, deaths from toxicity continue to occur, mainly from CVD and SMN. Risk-factor monitoring should be intensified, prevention programs developed, and therapeutic optimization of LH investigated, especially in two vulnerable groups: those aged <30 years at diagnosis, and women.

Cost-effectiveness of diagnostic tests during follow-up in lung cancer patients: an evidence-based study.

Background: Many patients with non-metastatic non-small cell lung cancer (NSCLC) are cured by surgery but part of them develop recurrence. Strategies are needed to identify these relapses. Currently, there is no consensus on the follow-up schedule after curative resection for patients with NSCLC. The objective of this study is to analyze the diagnostic capacity of the tests performed during follow-up after surgery. Methods: We retrospectively reviewed 392 patients with stage I-IIIA NSCLC who underwent surgery. Data were collected from patients diagnosed between January 1st, 2010 and December 31st, 2020. Demographic and clinical data were analyzed, as well as the tests performed during their follow-up. We identified as relevant in the diagnosis of relapses those tests that prompted further investigation and change of treatment. Results: The number of tests matches those included in clinical practice guidelines. A total of 2,049 clinical follow-up consultations were performed, of which 2,004 were scheduled (0.59% informative). A total of 1,796 blood tests were performed, of which 1,756 were scheduled (0.17% informative). A total of 1,940 chest computer tomography (CT) scans were performed, of which 1,905 were scheduled and 128 were informative (6.7%). A total of 144 positron emission tomography (PET)-CT scans were performed, 132 of which were scheduled, of which 64 (48%) were informative. In all cases, the tests performed by unscheduled request exceeded the informative result of the scheduled ones several fold. Conclusions: Most of the scheduled follow-up consultations were not relevant for the patients' management, and only body CT scan exceeded the threshold of 5% profitability, without reaching 10% even in stage IIIA. The profitability of the tests increased when performed in unscheduled visits. New follow-up strategies based on scientific evidence must be defined and follow-up schemes should be tailored focused on agile attention of the unscheduled demand.

Assessing the risk of cardiovascular events in patients receiving immune checkpoint inhibitors.

Background: Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment. However, despite their excellent therapeutic effect, these medications typically result in a broad spectrum of toxicity reactions. Immune-related cardiotoxicity is uncommon but can be potentially fatal, and its true incidence is underestimated in clinical trials. The aim of this study is to assess the incidence and identify risk factors for developing a cardiac event in patients treated with ICIs. Methods: We conducted a single-institution retrospective study, including patients treated with ICIs in our center. The main outcomes were cardiac events (CE) and cardiovascular death. Results: A total of 378 patients were analyzed. The incidence of CE was 16.7%, during a median follow-up of 50.5 months. The multivariable analysis showed that age, a history of arrhythmia or ischemic heart disease, and prior immune-related adverse events were significantly associated with CE. Conclusion: CE during ICI treatment are more common than currently appreciated. A complete initial cardiovascular evaluation is recommended, especially in high-risk patients, being necessary a multidisciplinary approach of a specialized cardio-oncology team.

Optimal vaccination in a SIRS epidemic model.

We propose and solve an optimal vaccination problem within a deterministic compartmental model of SIRS type: the immunized population can become susceptible again, e.g. because of a not complete immunization power of the vaccine. A social planner thus aims at reducing the number of susceptible individuals via a vaccination campaign, while minimizing the social and economic costs related to the infectious disease. As a theoretical contribution, we provide a technical non-smooth verification theorem, guaranteeing that a semiconcave viscosity solution to the Hamilton-Jacobi-Bellman equation identifies with the minimal cost function, provided that the closed-loop equation admits a solution. Conditions under which the closed-loop equation is well-posed are then derived by borrowing results from the theory of Regular Lagrangian Flows. From the applied point of view, we provide a numerical implementation of the model in a case study with quadratic instantaneous costs. Amongst other conclusions, we observe that in the long-run the optimal vaccination policy is able to keep the percentage of infected to zero, at least when the natural reproduction number and the reinfection rate are small.

An Artificial Intelligence-Based Tool for Data Analysis and Prognosis in Cancer Patients: Results from the Clarify Study.

BACKGROUND: Artificial intelligence (AI) has contributed substantially in recent years to the resolution of different biomedical problems, including cancer. However, AI tools with significant and widespread impact in oncology remain scarce. The goal of this study is to present an AI-based solution tool for cancer patients data analysis that assists clinicians in identifying the clinical factors associated with poor prognosis, relapse and survival, and to develop a prognostic model that stratifies patients by risk. MATERIALS AND METHODS: We used clinical data from 5275 patients diagnosed with non-small cell lung cancer, breast cancer, and non-Hodgkin lymphoma at Hospital Universitario Puerta de Hierro-Majadahonda. Accessible clinical parameters measured with a wearable device and quality of life questionnaires data were also collected. RESULTS: Using an AI-tool, data from 5275 cancer patients were analyzed, integrating clinical data, questionnaires data, and data collected from wearable devices. Descriptive analyses were performed in order to explore the patients' characteristics, survival probabilities were calculated, and a prognostic model identified low and high-risk profile patients. CONCLUSION: Overall, the reconstruction of the population's risk profile for the cancer-specific predictive model was achieved and proved useful in clinical practice using artificial intelligence. It has potential application in clinical settings to improve risk stratification, early detection, and surveillance management of cancer patients.

Determination of essential biomarkers in lung cancer: a real-world data study in Spain with demographic, clinical, epidemiological and pathological characteristics.

BACKGROUND: The survival of patients with lung cancer has substantially increased in the last decade by about 15%. This increase is, basically, due to targeted therapies available for advanced stages and the emergence of immunotherapy itself. This work aims to study the situation of biomarker testing in Spain. PATIENTS AND METHODS: The Thoracic Tumours Registry (TTR) is an observational, prospective, registry-based study that included patients diagnosed with lung cancer and other thoracic tumours, from September 2016 to 2020. This TTR study was sponsored by the Spanish Lung Cancer Group (GECP) Foundation, an independent, scientific, multidisciplinary oncology society that coordinates more than 550 experts and 182 hospitals across the Spanish territory. RESULTS: Nine thousand two hundred thirty-nine patients diagnosed with stage IV non-small cell lung cancer (NSCLC) between 2106 and 2020 were analysed. 7,467 (80.8%) were non-squamous and 1,772 (19.2%) were squamous. Tumour marker testing was performed in 85.0% of patients with non-squamous tumours vs 56.3% in those with squamous tumours (p-value < 0.001). The global testing of EGFR, ALK, and ROS1 was 78.9, 64.7, 35.6% respectively, in non-squamous histology. PDL1 was determined globally in the same period (46.9%), although if we focus on the last 3 years it exceeds 85%. There has been a significant increase in the last few years of all determinations and there are even close to 10% of molecular determinations that do not yet have targeted drug approval but will have it in the near future. 4,115 cases had a positive result (44.5%) for either EGFR, ALK, KRAS, BRAF, ROS1, or high PDL1. CONCLUSIONS: Despite the lack of a national project and standard protocol in Spain that regulates the determination of biomarkers, the situation is similar to other European countries. Given the growing number of different determinations and their high positivity, national strategies are urgently needed to implement next-generation sequencing (NGS) in an integrated and cost-effective way in lung cancer.

Negation and uncertainty detection in clinical texts written in Spanish: a deep learning-based approach.

Detecting negation and uncertainty is crucial for medical text mining applications; otherwise, extracted information can be incorrectly identified as real or factual events. Although several approaches have been proposed to detect negation and uncertainty in clinical texts, most efforts have focused on the English language. Most proposals developed for Spanish have focused mainly on negation detection and do not deal with uncertainty. In this paper, we propose a deep learning-based approach for both negation and uncertainty detection in clinical texts written in Spanish. The proposed approach explores two deep learning methods to achieve this goal: (i) Bidirectional Long-Short Term Memory with a Conditional Random Field layer (BiLSTM-CRF) and (ii) Bidirectional Encoder Representation for Transformers (BERT). The approach was evaluated using NUBES and IULA, two public corpora for the Spanish language. The results obtained showed an F-score of 92% and 80% in the scope recognition task for negation and uncertainty, respectively. We also present the results of a validation process conducted using a real-life annotated dataset from clinical notes belonging to cancer patients. The proposed approach shows the feasibility of deep learning-based methods to detect negation and uncertainty in Spanish clinical texts. Experiments also highlighted that this approach improves performance in the scope recognition task compared to other proposals in the biomedical domain.

Chronodisruption and Ambulatory Circadian Monitoring in Cancer Patients: Beyond the Body Clock.

PURPOSE OF REVIEW: Circadian rhythms impose daily rhythms a remarkable variety of metabolic and physiological functions, such as cell proliferation, inflammation, and DNA damage response. Accumulating epidemiological and genetic evidence indicates that circadian rhythms' disruption may be linked to cancer. The integration of circadian biology into cancer research may offer new options for increasing cancer treatment effectiveness and would encompass the prevention, diagnosis, and treatment of this disease. RECENT FINDINGS: In recent years, there has been a significant development and use of multi-modal sensors to monitor physical activity, sleep, and circadian rhythms, allowing, for the very first time, scaling accurate sleep monitoring to epidemiological research linking sleep patterns to disease, and wellness applications providing new potential applications. This review highlights the role of circadian clock in tumorigenesis, cancer hallmarks and introduces the state-of-the-art in sleep-monitoring technologies, discussing the eventual application of insights in clinical settings and cancer research.

Integration of Clinical Information and Imputed Aneuploidy Scores to Enhance Relapse Prediction in Early Stage Lung Cancer Patients.

Early-stage lung cancer is crucial clinically due to its insidious nature and rapid progression. Most of the prediction models designed to predict tumour recurrence in the early stage of lung cancer rely on the clinical or medical history of the patient. However, their performance could likely be improved if the input patient data contained genomic information. Unfortunately, such data is not always collected. This is the main motivation of our work, in which we have imputed and integrated specific type of genomic data with clinical data to increase the accuracy of machine learning models for prediction of relapse in early-stage, non-small cell lung cancer patients. Using a publicly available TCGA lung adenocarcinoma cohort of 501 patients, their aneuploidy scores were imputed into similar records in the Spanish Lung Cancer Group (SLCG) data, more specifically a cohort of 1348 early-stage patients. First, the tumor recurrence in those patients was predicted without the imputed aneuploidy scores. Then, the SLCG data were enriched with the aneuploidy scores imputed from TCGA. This integrative approach improved the prediction of the relapse risk, achieving area under the precision-recall curve (PR-AUC) score of 0.74, and area under the ROC (ROC-AUC) score of 0.79. Using the prediction explanation model SHAP (SHapley Additive exPlanations), we further explained the predictions performed by the machine learning model. We conclude that our explainable predictive model is a promising tool for oncologists that addresses an unmet clinical need of post-treatment patient stratification based on the relapse risk, while also improving the predictive power by incorporating proxy genomic data not available for the actual specific patients.

To burn-out or not to burn-out: a cross-sectional study in healthcare professionals in Spain during COVID-19 pandemic.

OBJECTIVE: To assess the prevalence of burn-out syndrome in healthcare workers working on the front line (FL) in Spain during COVID-19. DESIGN: Cross-sectional, online survey-based study. SETTINGS: Sampling was performed between 21st April and 3rd May 2020. The survey collected demographic data and questions regarding participants' working position since pandemic outbreak. PARTICIPANTS: Spanish healthcare workers working on the FL or usual ward were eligible. A total of 674 healthcare professionals answered the survey. MAIN OUTCOMES AND MEASURES: Burn-out syndrome was assessed by the Maslach Burnout Inventory-Medical Personnel. RESULTS: Of the 643 eligible responding participants, 408 (63.5%) were physicians, 172 (26.8%) were nurses and 63 (9.8%) other technical occupations. 377 (58.6%) worked on the FL. Most participants were women (472 (73.4%)), aged 31-40 years (163 (25.3%)) and worked in tertiary hospitals (>600 beds) (260 (40.4%)). Prevalence of burn-out syndrome was 43.4% (95% CI 39.5% to 47.2%), higher in COVID-19 FL workers (49.6%, p<0.001) than in non- COVID-19 FL workers (34.6%, p<0.001). Women felt more burn-out (60.8%, p=0.016), were more afraid of self-infection (61.9%, p=0.021) and of their performance and quality of care provided to the patients (75.8%, p=0.015) than men. More burn-out were those between 20 and 30 years old (65.2%, p=0.026) and those with more than 15 years of experience (53.7%, p=0.035).Multivariable logistic regression analysis revealed that, working on COVID-19 FL (OR 1.93; 95% CI 1.37 to 2.71, p<0.001), being a woman (OR 1.56; 95% CI 1.06 to 2.29, p=0.022), being under 30 years old (OR 1.75; 95% CI 1.06 to 2.89, p=0.028) and being a physician (OR 1.64; 95% CI 1.11 to 2.41, p=0.011) were associated with high risk of burn-out syndrome. CONCLUSIONS: This survey study of healthcare professionals reported high rates of burn-out syndrome. Interventions to promote mental well-being in healthcare workers exposed to COVID-19 need to be immediately implemented.

On Predicting Recurrence in Early Stage Non-small Cell Lung Cancer.

Early detection and mitigation of disease recurrence in non-small cell lung cancer (NSCLC) patients is a nontrivial problem that is typically addressed either by rather generic follow-up screening guidelines, self-reporting, simple nomograms, or by models that predict relapse risk in individual patients using statistical analysis of retrospective data. We posit that machine learning models trained on patient data can provide an alternative approach that allows for more efficient development of many complementary models at once, superior accuracy, less dependency on the data collection protocols and increased support for explainability of the predictions. In this preliminary study, we describe an experimental suite of various machine learning models applied on a patient cohort of 2442 early stage NSCLC patients. We discuss the promising results achieved, as well as the lessons we learned while developing this baseline for further, more advanced studies in this area.