Predictors Of Success Research Articles

COVID-19 from symptoms to prediction: A statistical and machine learning approach

During the COVID-19 pandemic, the analysis of patient data has become a cornerstone for developing effective public health strategies. This study leverages a dataset comprising over 10,000 anonymized patient records from various leading medical institutions to predict COVID-19 patient age groups using a suite of statistical and machine learning techniques. Initially, extensive statistical tests including ANOVA and t-tests were utilized to assess relationships among demographic and symptomatic variables. The study then employed machine learning models such as Decision Tree, Naïve Bayes, KNN, Gradient Boosted Trees, Support Vector Machine, and Random Forest, with rigorous data preprocessing to enhance model accuracy. Further improvements were sought through ensemble methods; bagging, boosting, and stacking. Our findings indicate strong associations between key symptoms and patient age groups, with ensemble methods significantly enhancing model accuracy. Specifically, stacking applied with random forest as a meta leaner exhibited the highest accuracy (0.7054). In addition, the implementation of stacking techniques notably improved the performance of K-Nearest Neighbors (from 0.529 to 0.63) and Naïve Bayes (from 0.554 to 0.622) and demonstrated the most successful prediction method. The study aimed to understand the number of symptoms identified in COVID-19 patients and their association with different age groups. The results can assist doctors and higher authorities in improving treatment strategies. Additionally, several decision-making techniques can be applied during pandemic, tailored to specific age groups, such as resource allocation, medicine availability, vaccine development, and treatment strategies. The integration of these predictive models into clinical settings could support real-time public health responses and targeted intervention strategies.

Machine learning prediction of pancreatitis risk with antithyroid drugs: a nationwide retrospective observational study.

In recent years, there has been increasing data showing that the risk of acute pancreatitis (AP) is increased in patients using methimazole (MMI). The aim of this population-based study was to investigate the association between drugs used in the treatment of hyperthyroidism (MMI, PTU, propranolol) and the diagnosis of AP. The database consisted of more than 85 million citizen records between January 1, 2017 and December 31, 2022. Within the scope of the study, the data were examined of patients diagnosed with hyperthyroidism and the individuals who developed acute pancreatitis after being diagnosed with hyperthyroidism, which was accomplished using the International Classification of Diseases-10 (ICD-10) codes. Analyses were carried out using R Studio 4.2.0 software. The test-train technique as a machine learning method was used in cox regression models. A total of 1,329,934 individuals diagnosed with hyperthyroidism were examined. Of these, 10,815 (0.81%) patients developed acute pancreatitis after being diagnosed with hyperthyroidism. The use of propylthiouracil was determined to increase the probability of experiencing AP diagnosis 0.10-fold (10%) (p:0.0009), and the use of propranolol decrease the probability of experiencing AP 0.5-fold (5%) (p:0.032), with a 52.2% predictive success rate. There is no any statistically significant association between MMI use and the probability of experiencing AP according to the model have been build. Although the risk of experiencing AP was not increased by MMI use, PTU use increased and propronolol use decrease the risk of experiencing AP in patients with hyperthyroidism. Although drug-induced acute pancreatitis is relatively rare, a firm understanding of the drugs associated with the condition should alert the clinician to appropriately diagnose and treat patients.

Exploring Gender Differences in Self- Efficacy and Academic Performance among College Students

This study explored the relationship between self-efficacy and academic performance on gender and academic program differences among 204 undergraduate students at a university in Misamis Occidental. This study employed a descriptive-correlational method. The respondents were predominantly female with the majority enrolled in Social Work and Psychology. While they showed a strong belief in their academic abilities, this inconsistently translate into higher academic performance. Significant differences in self-efficacy were observed across academic programs, with Social Work students reporting the highest levels and Psychology students the lowest. However, gender insignificantly impact either self-efficacy or academic performance. This study suggests that self-efficacy must interact with other factors, such as motivation, learning strategies, and program-specific influences, instead of making it a direct predictor of academic success. Investigating the long-term impact of self-efficacy on academic outcomes, the role of external factors and their interaction with self-efficacy, and their contribution to a deeper understanding of its influence on academic outcomes must also be considered for further studies. Institutions should implement targeted interventions to enhance student self-efficacy and academic resilience as additional support for lower-performing programs for a more holistic approach to student development in higher education.

A data- and knowledge-driven framework for developing machine learning models to predict soccer match outcomes

The 2023 Soccer Prediction Challenge invited the machine learning community to develop innovative methods to predict the outcomes of 736 future soccer matches. The Challenge included two tasks. Task 1 was to forecast the exact match score, i.e., the number of goals scored by each team. Task 2 was to predict the match outcome as probability vector over the three possible result categories: victory of the home team, draw, and victory of the away team. Here, we present a new data- and knowledge-driven framework for building machine learning models from readily available data to predict soccer match outcomes. A key component of this framework is an innovative approach to modeling interdependent time series data of competing entities. Using this framework, we developed various predictive models based on k-nearest neighbors, artificial neural networks, naive Bayes, and ordinal forests, which we applied to the two tasks of the 2023 Soccer Prediction Challenge. Among all submissions to the Challenge, our machine learning models based on k-nearest neighbors and neural networks achieved top performances. Our main insights from the Challenge are that relatively simple learning algorithms perform remarkably well compared to more complex algorithms, and that the key to successful predictions lies in how well soccer domain knowledge can be incorporated in the modeling process.

Dimensions of predictive success

Dimensions of predictive success

Predictors of success in left bundle branch area pacing with stylet-driven pacing leads: a multicenter investigation.

Although left bundle branch area pacing (LBBAP) is an emerging conduction system pacing modality, it is unclear which parameters predict procedural success and how many implant attempts are acceptable. This study aimed to assess predictors of successful LBBAP, left bundle branch (LBB) capture, and factors associated with the number of LBBAP implant attempts. This retrospective observational multicenter study was conducted in Korea. LBBAP was attempted in 119 patients; 89.3% of patients had bradyarrhythmia (atrioventricular block 82.4%), and 10.7% of patients had heart failure (cardiac resynchronization therapy) indication. Procedural success and electrophysiological and echocardiographic parameters were evaluated. The acute success rate of lead implantation in LBBAP was 95.8% (114 of 119 patients) and that of LBB capture was 82.4% (98 of 119 patients). Fewer implant attempts were associated with LBBAP success (three or fewer vs. over three times, p = 0.014) and LBB capture (three or fewer vs. over three times, p = 0.010). In the multivariate linear regression, the patients with intraventricular conduction delay (IVCD) required a greater number of attempts than those without IVCD [estimates = 2.33 (0.35-4.31), p = 0.02], and the larger the right atrial (RA) size, the more the attempts required for LBBAP lead implantation [estimates = 2.08 (1.20-2.97), p < 0.001]. An increase in the number of implant attempts was associated with LBBAP procedural failure and LBB capture failure. The electrocardiographic parameter IVCD and the echocardiographic parameter RA size may predict the procedural complexity and the number of lead implant attempts for LBBAP.

Smokers' Characteristics Associated with Successful Smoking Cessation Undergoing Pharmacotherapy in Slovenia.

Tobacco use is a major global health problem, contributing to premature death and disability. In Slovenia, the prevalence of smoking is higher than the EU average, emphasizing the need for effective tobacco control measures. The aim of this study was to identify the characteristics of patients most likely to benefit from pharmacotherapy for smoking cessation. We performed cross-sectional analysis of factors associated with successful smoking cessation using pharmacotherapy for Slovenian smokers. A total of 176 (24.6%) smokers with an average age of 50 years agreed to receive pharmacotherapy for their smoking cessation attempt and were enrolled in the study. Participants were followed up at 4-week intervals during treatment and for 24 weeks after completion of pharmacotherapy. Attempts to quit smoking with prescription medications were successful in 24.4% of those willing to try. Female smokers, older persons, those with more children, with a lower self-perception of health, a higher number of cigarettes per day and a higher nicotine dependence were more likely to attempt to quit smoking. However, the strongest predictors of smoking cessation success were lower nicotine dependence, which was tested using the Fagerström test for nicotine dependence, and higher adherence to pharmacotherapy. Nicotine dependence and adherence to pharmacotherapy are the strongest predictors of a successful smoking cessation attempt. Identification of potential responders, prescription of pharmacotherapy and follow-up are applicable in the primary healthcare setting.

Enhancing predictions of embryo implantation in thin endometrium: a comparative analysis of endometrial thickness in frozen versus fresh IVF cycles

This study investigated whether the difference between endometrial thickness in the frozen embryo transfer (FET) cycle and the preceding fresh stimulated cycle predicts clinical pregnancy in women with thin endometrium. A retrospective analysis of 335 cycles in 227 women (age < 43) with endometrium < 8 mm in the FET cycle was conducted. Endometrial thickness was assessed using the ratio (ETfrozen/fresh) and absolute difference (ETfresh-frozen) between the maximal endometrial thickness measured during the stimulated IVF cycle and that measured in the FET cycle. We hypothesized that a smaller difference and higher ratio during FET will be associated with higher pregnancy rate. No embryo implantation occurred in women with an FET endometrial thickness < 5.9 mm and an ETfrozen/fresh < 0.86. Cycles with a positive beta-human chorionic gonadotropin (ß-hCG) showed a significantly lower mean ETfresh-frozen (1.89 ± 1.78 vs 2.30 ± 1.81, p = 0.03), and a significantly higher ETfrozen/fresh ratio (0.82 ± 0.17 vs. 0.77 ± 0.15, p = 0.024). Endometrial thickness in the FET cycle normalized to the preceding stimulated cycle is associated with implantation and may constitute a novel predictor of FET success in women with thin endometrium.

Analyzing the critical steps in deep learning-based stock forecasting: a literature review

Stock market or individual stock forecasting poses a significant challenge due to the influence of uncertainty and dynamic conditions in financial markets. Traditional methods, such as fundamental and technical analysis, have been limited in coping with uncertainty. In recent years, this has led to a growing interest in using deep learning-based models for stock prediction. However, the accuracy and reliability of these models depend on correctly implementing a series of critical steps. These steps include data collection and analysis, feature extraction and selection, noise elimination, model selection and architecture determination, choice of training-test approach, and performance evaluation. This study systematically examined deep learning-based stock forecasting models in the literature, investigating the effects of these steps on the model’s forecasting performance. This review focused on the studies between 2020–2024, identifying influential studies by conducting a systematic literature search across three different databases. The identified studies regarding seven critical steps essential for creating successful and reliable prediction models were thoroughly examined. The findings from these examinations were summarized in tables, and the gaps in the literature were detailed. This systematic review not only provides a comprehensive understanding of current studies but also serves as a guide for future research.

AI-based prediction of academic success: Support for many, disadvantage for some?

The use of computational tools to predict academic success has become increasingly popular. Machine learning algorithms, trained on past study histories, have been shown to provide valid predictions. However, knowing about biases and unfairness in algorithms, one should take a closer look at these predictions. This paper explores the extent to which the predictive accuracy of academic success varies between specific groups of students, focusing on traditional and non-traditional students (NTS), who have not acquired a higher education entrance qualification at school. In a case study the study compares several popular algorithms and their prediction quality, and investigates whether misclassified NTS show positive or negative biases. Results revealed that the accuracy of predicting academic success for NTS was significantly lower than when considering all students as a whole. The direction of the distortion cannot be determined exactly due to small case numbers. The study emphasizes that the possibility of bias always has to be considered when predicting study success, and the use of such tools must ensure there are no undesirable biases that could affect certain students.

Adolescents in transition: experiences and appraisals of immigrant students in school education

ABSTRACT Compulsory secondary education is constituted as a stage of high risk or academic vulnerability for the immigrant population. This multiple case study examines difficulties and opportunities faced by seventeen immigrant schoolchildren in compulsory schooling education cycles as elucidated by the evaluative resources they employ as they construct a narrative discourse shaped by academic-professional transitions and expectations. Specifically, we focus on the semantic-discursive component of attitude, analysing its three levels of appraisal: affect, judgement, and appreciation. We conducted in-depth interviews with immigrants attending public high school in Chile and a collective participatory methodology, both of a biographical-narrative nature. The findings highlight the influence of various influential factors on student trajectories: the characteristics of the host country, the challenges posed by the pandemic, family support, racism, the role of teachers, and academic-professional aspirations. Regarding the obstacles, racist bullying is identified between the end of primary school and the beginning of secondary school, which coincides with the results of the literature reviewed. Regarding opportunities, the influential adult figure represented by parents and teachers is positioned as a decisive protective support in the development and progress of educational transitions. Similarly, the configuration of high academic-professional expectations functions as a predictor of educational success.

Operationalizing Predictors of Postschool Success in Secondary Transition: A Delphi Study

To improve postschool outcomes for students with disabilities, research in secondary transition has increasingly aimed to identify in-school experiences that contribute to positive outcomes after high school. Although research on postschool success for this population has recently identified seven new predictors, operational definitions and essential program characteristics remain missing. Therefore, the purpose of this Delphi study was to operationally define the seven newest predictors of postschool success in secondary transition and identify their essential program characteristics. Experts in the field of secondary transition reached consensus on an operational definition and a set of essential program characteristics for each of the seven newest predictors of postschool success. These definitions and essential program characteristics provide additional information needed to develop, implement, and evaluate effective secondary transition programs. Moreover, these results continue to move research to practice in meaningful and actionable ways. Suggestions for further research and implications are discussed.

Comparative Feasibility Analysis of Retrograde Double J Stenting, Antegrade Double J Stenting, and Percutaneous Nephrostomy Tube Placement for Ureteric Obstruction Secondary to Pelvic Malignancies

Background: The management of ureteric obstruction secondary to pelvic malignancies (UOPM) presents a significant challenge. Objectives: Our study aimed to assess the factors affecting the feasibility of interventions for patients with UOPM - including retrograde and antegrade double J (DJ) stenting, and percutaneous nephrostomy (PCN) insertion. Methods: We conducted a retrospective analysis of patients who underwent intervention for UOPM over two years, from January 2022 to December 2023. Patients were categorized into groups based on intervention type: Group 1: Retrograde DJ stenting, group 2: Antegrade DJ stenting, and group 3: PCN insertion. Demographic, clinical, radiological, cystoscopic, and laboratory data were compared between the three groups. Analysis of Variance (ANOVA), logistic regression, and marginal mean plots were utilized for statistical analysis. Results: Fifty–nine patients were included in the study, consisting of 14 males and 45 females, and the mean age of the study population was 60.1 ± 10.8 years. Retrograde DJ stenting was successfully achieved in 59.3% of patients, with 10.2% undergoing antegrade DJ stenting and 30.5% needing PCN insertion. Serum albumin (P = 0.04), serum creatinine (P = 0.02), albumin creatinine ratio (P &lt; 0.001), and severity of hydroureteronephrosis (HDUN) (P = 0.02) were significantly associated with intervention outcomes. There was an increased likelihood of PCN insertion in higher serum creatinine and lower serum albumin levels. Multinomial logistic regression with univariate and multivariate analysis revealed significance among the above-mentioned variables. Conclusions: Even though DJ stenting remains common, a significant proportion of patients require PCN insertion. Serum albumin, serum creatinine, albumin creatinine ratio, and HDUN severity are significant predictors of intervention success. Further research is warranted to validate these findings and enhance management strategies for UOPM.

Modeling appeals in university accreditation in Chile: an exploratory study

ABSTRACT In Chile, university administrators may appeal to a secondary agency to challenge the accreditation decisions of the primary national accreditation agency. The study analyzes the appeal judgments, using an empirical approach to identify arguments used by the secondary agency to justify its decisions. The analyses identify several factors, such as improvements since the last accreditation, faculty productivity, and financial standing, as the most relevant predictors of appeal success. The appellate agency, however, tends to emphasize the absence of deficiencies or weaknesses associated with these factors when it grants an appeal, sidestepping the primary agency’s criteria and standards for accreditation. Such an approach may be appropriate given the heterogeneous landscape of the Chilean higher education system, providing leeway to drive excellence in more selective institutions while maintaining some minimum standards in less selective ones.

The S in STEM: gender differences in science anxiety and its relations with science test performance-related variables

BackgroundSTEM education has experienced significant growth due to its pivotal role in innovation and economic development. While cognitive factors like prior knowledge are known predictors of STEM success, non-cognitive factors, including attitudes and demographics, also play vital roles. However, there is a notable scarcity of research focusing on the "S" in STEM—science—compared to extensive studies in fields like mathematics. This study aims to address this gap by exploring gender differences in science test performance and related attitudes, providing insights into this under-researched aspect of STEM education.ResultsThe effective sample comprised 1839 Estonian 12th-grade students who took a computer-assisted science test. The test consisted of tasks combining chemistry, physics, biology, and geography, and a post-test survey was also administered. Across the total sample, the results showed that test performance positively correlated with test-taking duration, effort, and test importance. Test performance was negatively correlated with perceived test difficulty. Interestingly, while general science anxiety was not associated with test performance, subject-specific anxiety, especially chemistry anxiety had a negative association with test performance. While there were no gender differences in test performance, female students scored consistently higher on all science anxiety measures, compared to male students. Furthermore, female students assessed the science test to be more difficult, and they also took more time to complete the test. The correlations in gender subsamples mirrored those observed in the total sample.ConclusionsThe association between science test performance and test-related variables is nuanced: students might not necessarily have a “general” STEM anxiety but it may be associated with a specific subject. Moreover, the findings imply that although there are no gender differences in test performance, girls have a greater anxiety when it comes to natural sciences subjects. These findings indicate the need for investigating the origin of such anxieties, which do not seem to stem from aptitude.

Oral squamous cell carcinoma identification by FTIR spectroscopy of oral biofluids.

This case study evaluated the efficacy of mid-infrared spectroscopy on the identification of oral squamous cell carcinoma, following the assessment of unstimulated whole saliva. The trial follows a matched case-control design. Saliva samples were characterized through mid-infrared spectroscopy, and chemometric tools were applied to distinguish between case and control participants, further identifying the spectral regions that played a pivotal role in the successful identification of oral squamous cell carcinoma. Mid-infrared spectroscopy was capable to discriminate between cancer patients and matched controls with 100% of correct predictions. Additionally, the spectral regions mostly contributing to the successful prediction were identified and found to be potentially associated with significant molecular changes crucial to the carcinogenic process. The application of mid-infrared spectroscopy in saliva analysis may be regarded as an innovative, noninvasive, low cost, and sensitive technique contributing to the identification of oral squamous cell carcionma.

To Assess the Functional outcome of Inflammatory arthritis of Knee following a Total Knee Replacement in a Tertiary Care Centre

Introduction : Inflammatory arthritis, particularly RA, can lead to significant joint destruction and functional impairment, necessitating interventions such as TKA. Despite medical therapy, severe joint damage may occur, warranting surgical intervention. This study assesses the functional outcomes post-TKA in patients having inflammatory arthritis. Materials and Methods: Patients who received TKA for inflammatory arthritis were included in this prospective observational cohort research, specifically RA, between 2019 and 2023 at Saveetha Medical College, Chennai. Clinical, radiological, and functional results have been assessed using the American Knee Society scoring system. IBM SPSS version 22.0 was utilized for analysis of data, p &lt; 0.05 is the threshold for statistical significance. Results:Twenty TKAs have been performed for RA, with all patients successfully followed up. The mean age of the patients was 58.5 years, and the majority were female. Before TKA, the average length of RA was 7.24 years, and all patients were in stage IV illness. Preoperative and postoperative knee society scores showed significant improvement, with average scores of 58.15 and 96.15, respectively. Functional scores also demonstrated substantial enhancement post-TKA, with an average increase of 130%. Radiological assessment revealed no evidence of lysis in any patient. Conclusion: Significant inverse relationship among the postoperative functional score and the length of the disease and the involvement of other joints. Utilizing the American Knee Society and functional scoring systems allows for objective prediction of surgical success. This can motivate surgeons and treating physicians to enhance care for RA patients.

Peripheral Nerve Blocks as a Predictor of Nerve Reconstruction Success After Major Limb Amputation.

Postamputation pain is a spectrum of debilitating sensations that impacts millions of people in the United States. While the development of postamputation pain, including phantom limb pain (PLP), is multifactorial, it has been associated with disorganized axonal sprouting, resulting in a neuroma and subsequent central nervous system changes. Nerve reconstruction surgeries, such as regenerative peripheral nerve interface (RPNI) and targeted muscle reinnervation (TMR), provide transected nerve fibers with proper target organs for reinnervationand have been shown to significantly reduce PLP. This case series aims to describe perioperative peripheral nerve blocks as a diagnostic tool for identifying patients who would benefit from RPNI or TMR. We conducted a retrospective search of patients who underwent major extremity amputation and who received a diagnostic peripheral nerve block before undergoing reconstructive nerve surgery (TMR and/or RPNI). Six patients (58-80 years old) with below-knee amputations (BKA) were examined. All patients experienced a reduction in postamputation pain (PAP), specifically PLP, after a diagnostic peripheral nerve block (PNB). The average time between amputation and revision surgery was approximately two years (Mean: 22.35 months). Following surgical intervention, all patientsreported a reduction in PLP episodes after nerve reconstruction surgery. Two patients no longer reported PLP.Ambulation rates also improved following revision (50% vs 83%). PNBs can be used as an effective diagnostic tool to identify patients that will significantly benefit from amputation revisions with TMR or RPNI.

Assessment of Healthcare Service Quality and Patient Satisfaction Using the SERVQUAL Questionnaire in Khuzestan Province During 2022 - 2023

Background: Hospital service quality is the primary predictor of a hospital's success, and any decrease in patient satisfaction is a cause for concern for the organization. Objectives: This study aimed to evaluate the service quality of Golestan Hospital in Ahvaz, Iran, based on patient satisfaction measured using the SERVQUAL questionnaire. Methods: This cross-sectional study was conducted in 2022 - 2023. Patients over 18 years old who visited the emergency department at Golestan Hospital were evaluated, with the exception of those with mental or multiple chronic disorders. Data collection tools included demographic and SERVQUAL Questionnaires. The data were analyzed using SPSS software, with a significance level set at less than 0.05. Results: A total of 200 subjects participated in the study, comprising 124 females (62%) and 76 males (38%). The results of the SERVQUAL Questionnaire indicated that the highest score was in the tangibility dimension (4.35), while the lowest score was in the assurance dimension (1.38). Negative gaps between perception and expectation were observed in the responsiveness (-0.99) and empathy (-1.22) dimensions. The mean total scores for expectation and perception were 99.55 ± 5.06 and 92.85 ± 5.5, respectively, with the highest scores observed for reliability. No significant association was found between expectation and perception (P-value &gt; 0.05). However, the reliability of the gap and expectation in males was significantly higher (P-value &lt; 0.05). A direct correlation was found between age and tangibility, Assurance, and total score of gaps (P-value &lt; 0.05). Conversely, a reverse correlation was observed between age and tangibility and the total score in perception (P-value &lt; 0.05). Post-hoc analysis revealed that the Assurance and total score of gaps and expectations were significantly higher in married patients compared to single patients (P-value &lt; 0.05). Conclusions: This study revealed a negative gap between patients' expectations and perceptions, highlighting the need for adjustments and improvements in hospital service quality by addressing all five dimensions of service quality.

Abstract C053: Pancreatic cancer patient-derived organoids, preclinical tools for therapeutic profiling, patient response prediction, and tumor evolution

Abstract Pancreatic cancer (PC) is characterized by an aggressive biology and an exceptionally high tumor heterogeneity that causes considerable variations in response to chemotherapies, targeted agents, and immunotherapies. Patient-derived organoids (PDOs) accurately reflect parental tumor biological and molecular features and may represent powerful preclinical avatars to predict drug response and support clinical decision-making. We generated a living organoid biobank of &amp;gt;100 PC PDO lines from treatment-naïve and pretreated primary tumor and metastases with a reliable efficacy (60.8%), and previously developed a pharmacotyping-guided prediction model to prognosticate patient therapy response in an initial feasibility trial (Beutel AK et al, 2021). Real-life chemotherapy responses in 46 patients (for a total of 93 therapy lines) matched to pharmacotyping-informed predictions with overall 73.1% accuracy, 85.4% sensitivity (responsiveness), and 63.5% specificity (non-responsiveness). Overall, our model allowed a successful drug-response prediction in naïve patients with an accuracy of 73.0% and 70.0% for first and second-line regimens. Prediction power was nevertheless lower in pretreated and heavily pretreated patients with a precision of 68.2% and 50.0% for subsequent chemotherapy lines, respectively. Interestingly, PDO-based pharmacotyping also precisely predicted patient clinical outcome in the neoadjuvant and adjuvant settings, with respective accuracies of 83.3% and 71.4%. Retrospective analysis of patient clinical data in palliative setting finally showed that the administration of a regimen predicted to be efficient ultimately translated into a significantly longer progression-free survival. Implementing automation and drug screening miniaturization to our workflow also significantly enhanced our process capacity, reduced time before pharmacotyping, and improved compliance to internal quality controls. Tracking clonal evolution in longitudinal biopsies (a set of seven PDO pairs derived from the same patients at two distinct timepoints) revealed lower mutational burden and therapy-driven genetic alterations upon progression. Notably, this approach revealed a CHEK2-mutated patient responded over time to PARP inhibitor maintenance therapy, aligning with our predictions and underscoring the robustness of our method. Single nucleus-resolved RNA and ATAC-seq analysis of a unique longitudinally-collected case uncovered transcriptomic and epigenetic dynamics associated with an oncogenic FGFR2 fusion and with a subsequent resistance-mediating mutation upon targeted treatment with FGFR2 inhibitors. Particularly, FGFR2 constitutive activation correlated with aberrant epigenetic trace and transcription programs of downstream targets as PI3K-AKT and RAS family members and of RNA polymerase II transcription machinery. Here, we report a robust and clinically-relevant preclinical tool for drug-response prediction, one more step towards a PDO therapeutic profiling-guided personalized medicine in clinical routine. Citation Format: Johann Gout, Yazid J Resheq, Jessica Lindenmayer, Julian D Schwab, Elodie Roger, Johann M Kraus, Thomas Ettrich, Alica K Beutel, Lukas Perkhofer, Hans A Kestler, Thomas Seufferlein, Alexander Kleger. Pancreatic cancer patient-derived organoids, preclinical tools for therapeutic profiling, patient response prediction, and tumor evolution [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Advances in Pancreatic Cancer Research; 2024 Sep 15-18; Boston, MA. Philadelphia (PA): AACR; Cancer Res 2024;84(17 Suppl_2):Abstract nr C053.