Dive deeper into the aspects covered in this lesson with these readings that expand on the topics discussed. Each reading includes reflective questions to help you focus on key learning points and strengthen your understanding.

Reading: How artificial intelligence might disrupt diagnostics in hematology in the near future.
By Wencke Walter, Claudia Haferlach, Niroshan Nadarajah, Ines Schmidts, Constanze Kühn, Wolfgang Kern, Torsten Haferlach.

AI algorithms not only pick up on details that might escape our eye but also uncover entirely new ways of interpreting crucial clinical data. This reading takes you on a journey through how AI can enhance diagnostic accuracy in hematology by analyzing unstructured data from various sources, including microscopic images. You'll see in more depth how the integration of AI empowers healthcare professionals to make more informed decisions, improving treatment outcomes, speeding up diagnoses, and unlocking exciting new possibilities for personalized medicine—a concept we’ll explore further in the upcoming lessons.

Reading time: ~30 min

   Download the reading

Reflective questions

  • How has next-generation sequencing changed the diagnosis of leukemia and lymphoma?
  • What does the shift from phenotype to genotype mean for patient care?
  • How does AI help doctors predict outcomes for individual patients rather than just grouping them by risk?

Source: Walter W, Haferlach C, Nadarajah N, Schmidts I, Kühn C, Kern W, Haferlach T. How artificial intelligence might disrupt diagnostics in hematology in the near future. Oncogene. 2021 Jun;40(25):4271-4280. doi: 10.1038/s41388-021-01861-y. Epub 2021 Jun 8. PMID: 34103684; PMCID: PMC8225509.  Link

Additional Reading: MOSAIC: An Artificial Intelligence-Based Framework for Multimodal Analysis, Classification, and Personalized Prognostic Assessment in Rare Cancers.
By D'Amico S, Dall'Olio L, Rollo C, Alonso P, Prada-Luengo I, Dall'Olio D, Sala C, Sauta E, Asti G, Lanino L, Maggioni G, Campagna A, Zazzetti E, Delleani M, Bicchieri ME, Morandini P, Savevski V, Arroyo B, Parras J, Zhao LP, Platzbecker U, Diez-Campelo M, Santini V, Fenaux P, Haferlach T, Krogh A, Zazo S, Fariselli P, Sanavia T, Della Porta MG, Castellani G.

Imagine a future where artificial intelligence revolutionizes the way we diagnose and treat rare cancers, offering personalized predictions and treatment strategies tailored to each patient. This reading introduces MOSAIC, an innovative AI-driven approach that integrates diverse data sources—such as clinical records, imaging, and genomic profiles—to enhance cancer classification and prognostic accuracy. By leveraging advanced machine learning models and explainable AI techniques, MOSAIC not only improves predictions but also ensures transparency and trust in its decision-making. Moreover, the framework employs federated learning to protect patient privacy while maintaining high-performance analytics. As you read, consider the transformative potential of AI in precision medicine and how it could reshape the future of rare cancer treatment.

Reading time: ~30 min

Source: D'Amico S, Dall'Olio L, Rollo C, Alonso P, Prada-Luengo I, Dall'Olio D, Sala C, Sauta E, Asti G, Lanino L, Maggioni G, Campagna A, Zazzetti E, Delleani M, Bicchieri ME, Morandini P, Savevski V, Arroyo B, Parras J, Zhao LP, Platzbecker U, Diez-Campelo M, Santini V, Fenaux P, Haferlach T, Krogh A, Zazo S, Fariselli P, Sanavia T, Della Porta MG, Castellani G. MOSAIC: An Artificial Intelligence-Based Framework for Multimodal Analysis, Classification, and Personalized Prognostic Assessment in Rare Cancers. JCO Clin Cancer Inform. 2024 Jun;8:e2400008. doi: 10.1200/CCI.24.00008. PMID: 38875514; PMCID: PMC11371092.  Link