Jag deltar för närvarande i undervisningen av laborationspassen i kursen Foundations of Data Science under höstterminen. Under vårterminen är jag tillgänglig för handledning av masteruppsatser.

Mina föreslagna uppsatsämnen fokuserar på tillämpningen av maskininlärning på dyadiska interaktioner i psykoterapi, cancerutveckling samt dataanalys av elektroniska patientjournaler (EHRs). Jag är dock även öppen för att handleda projekt inom andra områden, förutsatt att studenten visar ett starkt intresse och engagemang för det valda ämnet. Jag handleder endast studenter som skriver sin uppsats på engelska.

Några av de uppsatsprojekt som jag har handlett eller bihandlett under de senaste åren:

• Predicting the Onset of Metastasis by Multimodal Machine Learning in Lung cancer and Melanoma patients
• Evaluating Explainability Techniques for Machine Learning in Healthcare

• Predicting Chronic Kidney Disease in Jalisco - An XAI-Enhanced Multimodal Approach with Geospatial and Demographic Data

• Predicting Symptom Change in Functional Somatic Syndromes through Multimodal Machine Learning and Explainability

• Integrating Genetics and Epigenetics for Predicting the Mutational Landscape in Lung Adenocarcinoma

 

Min forskning fokuserar på utveckling och tillämpning av maskininlärningsmetoder inom vård och psykoterapi. Jag är särskilt intresserad av dyadiska interaktioner i psykoterapi, där jag undersöker hur maskininlärning kan fånga och modellera de komplexa dynamikerna mellan patienter och terapeuter. Parallellt tillämpar jag maskininlärning på elektroniska patientjournaler (EHRs) för att förutsäga sjukdomsförlopp, med målet att stödja tidiga insatser och förbättra kliniska resultat.

En central del av mitt arbete är utvecklingen av nya metoder för förklarbarhet som gör maskininlärningsmodeller mer transparenta och tillförlitliga för praktiker. Inom dessa områden fokuserar jag på multimodala data och modellering av interaktioner mellan olika modaliteter, eftersom jag menar att integrationen av mångsidiga informationskällor ger djupare insikter och mer robusta prediktioner.

I urval från Stockholms universitets publikationsdatabas

• A Workflow for Generating Patient Counterfactuals in Lung Transplant Recipients

  2023. Franco Rugolon, Maria Bampa, Panagiotis Papapetrou. Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 291-306

  Konferens

  Lung transplantation is a critical procedure performed in end-stage pulmonary patients. The number of lung transplantations performed in the USA in the last decade has been rising, but the survival rate is still lower than that of other solid organ transplantations. First, this study aims to employ machine learning models to predict patient survival after lung transplantation. Additionally, the aim is to generate counterfactual explanations based on these predictions to help clinicians and patients understand the changes needed to increase the probability of survival after the transplantation and better comply with normative requirements. We use data derived from the UNOS database, particularly the lung transplantations performed in the USA between 2019 and 2021. We formulate the problem and define two data representations, with the first being a representation that describes only the lung recipients and the second the recipients and donors. We propose an explainable ML workflow for predicting patient survival after lung transplantation. We evaluate the workflow based on various performance metrics, using five classification models and two counterfactual generation methods. Finally, we demonstrate the potential of explainable ML for resource allocation, predicting patient mortality, and generating explainable predictions for lung transplantation.

  Läs mer om A Workflow for Generating Patient Counterfactuals in Lung Transplant Recipients

• A Workflow for Creating Multimodal Machine Learning Models for Metastasis Predictions in Melanoma Patients

  2025. Franco Rugolon (et al.). Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 87-102

  Konferens

  Melanoma is the most common form of skin cancer, responsible for thousands of deaths annually. Novel therapies have been developed, but metastases are still a common problem, increasing the mortality rate and decreasing the quality of life of those who experience them. As traditional machine learning models for metastasis prediction have been limited to the use of a single modality, in this study we aim to explore and compare different unimodal and multimodal machine learning models to predict the onset of metastasis in melanoma patients to help clinicians focus their attention on patients at a higher risk of developing metastasis, increasing the likelihood of an earlier diagnosis.

  We use a patient cohort derived from an Electronic Health Record, and we consider various modalities of data, including static, time series, and clinical text. We formulate the problem and propose a multimodal ML workflow for predicting the onset of metastasis in melanoma patients. We evaluate the performance of the workflow based on various classification metrics and statistical significance. The experimental findings suggest that multimodal models outperform the unimodal ones, demonstrating the potential of multimodal ML to predict the onset of metastasis.

  Läs mer om A Workflow for Creating Multimodal Machine Learning Models for Metastasis Predictions in Melanoma Patients

• MASICU: A Multimodal Attention-based classifier for Sepsis mortality prediction in the ICU

  2024. Lena Mondrejevski (et al.). 2024 IEEE 37th International Symposium on Computer-Based Medical Systems (CBMS), 326-331

  Konferens

  Sepsis poses a significant threat to public health, causing millions of deaths annually. While treatable with timely intervention, accurately identifying at-risk patients remains challenging due to the condition’s complexity. Traditional scoring systems have been utilized, but their effectiveness has waned over time. Recognizing the need for comprehensive assessment, we introduce MASICU, a novel machine learning model architecture tailored for predicting ICU sepsis mortality. MASICU is a novel multimodal, attention-based classification model that integrates interpretability within an ICU setting. Our model incorporates multiple modalities and multimodal fusion strategies and prioritizes interpretability through different attention mechanisms. By leveraging both static and temporal features, MASICU offers a holistic view of the patient’s clinical status, enhancing predictive accuracy while providing clinically relevant insights.

  Läs mer om MASICU

• Let’s talk about non-verbal communication: using AI and Machine learning for the investigation of interpersonal psychotherapeutic interactions

  2025. Stephan Hau (et al.). Scandinavian Psychoanalytic Review, 1-12

  Artikel

  The transmissions in the interpersonal communication in psychotherapy is very complex as both parties are simultaneous senders and recipients of non-verbal and verbal messages. To learn more about these transmissions, it is important in psychotherapy research to link the non-verbal communication to the verbal content and to explore the communication patterns that arise over time. Non-verbal communication is multimodal and includes, for example, body/head position and movements, facial expressions, eye movements or emotional prosody. These non-verbal signals also form part of the complex interactional synchronization patterns that include reflections of emotional expression. First results will be presented of an interdisciplinary project, in which the fields of psychology and data science are brought together. The aim of the study is to analyze all sessions of video-recorded psychodynamic psychotherapy with the help of AI-based methods such as machine learning and time series analyses to investigate what is transmitted non-verbally and which nonverbal interactive behavioral patterns develop between patient and therapist.

  Läs mer om Let’s talk about non-verbal communication: using AI and Machine learning for the investigation of interpersonal psychotherapeutic interactions

Visa alla publikationer av Franco Rugolon vid Stockholms universitet