As the pharmaceutical industry transitions to a patient-centric model, real-world data is increasingly used to inform drug development and regulatory decisions. Including the perspectives of patients, caregivers, and advocates in drug development enhances clinical trial design, endpoint selection, and regulatory review processes. This strategy, where patient voice is not an afterthought, aims to focus research on treatments that address the functional or symptomatic needs of patients, reduce patient burden, and enhance outcomes.

To support this, the Food and Drug Administration (FDA) has issued four methodological guidance documents on Patient-Focused Drug Development (PFDD).

Guidance 1 ¹ provides an overview of methods and approaches for collecting patient experience data. It directs stakeholders on how to ensure that patient input is comprehensive, covering the full range of relevant experiences, and representative, reflecting the diversity of the patient population. It also establishes the relationship between research questions and the selection of appropriate sampling methods and target populations.

Guidance 2 ²  offers a framework for gathering information about what is important to patients, including symptoms, disease impacts, and treatment outcomes. This is achieved through a combination of qualitative, quantitative, and mixed-methods research. Special considerations are suggested for populations such as children, cognitively impaired individuals, and those with rare diseases, including the involvement of caregivers or remote assessments when appropriate.

Guidance 3 ³  focuses on the selection, development, or modification of Clinical Outcome Assessments (COAs) that are considered “fit-for-purpose,” within the context of clinical trials and drug development. The guidance advocates for the use of electronic and digital health technologies for COA data collection. It addresses considerations for employing COAs in special populations, such as children or individuals unable to self-report, emphasizing the significance of observer or clinician input in these scenarios.

Guidance 4 ⁴  constitutes the concluding document in the FDA’s Patient-Focused Drug Development (PFDD) series. It primarily addresses the integration of COAs into clinical trial endpoints utilized for regulatory decision-making. Furthermore, it discusses the challenges associated with implementing COAs and endpoints in special populations, including individuals with rare disorders, and presents potential solutions for conducting robust assessments in these contexts.

The FDA’s PFDD guidelines specifically recognize the unique challenges of rare diseases, such as small patient populations and limited clinical trial sites. Guidance 1 acknowledges that collecting comprehensive and representative input may require different sampling strategies for rare diseases, while Guidance 4 addresses the complexities of evaluating treatment benefits and selecting clinical endpoints in these contexts.

Rare diseases present many challenges due to their low prevalence, which limits data collection, analysis, and sharing.

• Small patient populations: Rare diseases have limited numbers of patients, making it difficult to recruit enough participants for clinical trials and design statistically powered studies.
• Poorly understood natural history: Many rare diseases have incomplete or poorly characterized disease progression, complicating trial design, endpoint selection, and assessment of treatment effects.
• Heterogeneous disease presentation: Variability in symptoms and disease severity within the patient population challenges the identification of sensitive and meaningful clinical endpoints.
• Lack of validated outcome measures: There is often no consensus on clinical outcome measures or fit-for-purpose endpoints, requiring the development and validation of new measures, including patient-reported outcomes that reflect patient and caregiver perspectives.⁵
• Difficulty in patient identification and recruitment: Patients are geographically dispersed and often see multiple specialists before diagnosis, making it challenging to find and enroll eligible patients for trials.
• Limited clinical trial infrastructure and resources: There is often a lack of local infrastructure, funding, and trained researchers specializing in rare diseases, which hinders trial conduct and collaboration.⁶
• Challenges in post-marketing data collection: Long-term data collection and registry development are essential but require clear accountability and coordination among stakeholders.

Integration of comprehensive patient data and advanced AI tools is widely gaining importance for overcoming these barriers and making breakthroughs in advancing precision medicine in the rare disease research landscape.

Establishing comprehensive patient data repositories and streamlining the collection of high-quality, multimodal patient data is paramount to overcoming the current scarcity and fragmentation of rare disease datasets.⁷  AI-based diagnostic algorithms can parse through tons of this comprehensive patient data to facilitate earlier and more accurate identification of rare diseases, often by recognizing subtle clinical or genetic markers that may be missed by conventional methods.⁸ Advanced AI tools, such as machine learning algorithms, can analyze complex datasets to improve diagnostic accuracy, identify novel disease patterns, and support clinical decision-making, particularly in rare disease settings where traditional diagnostic approaches fall short.9 To address the unique challenges of small and heterogeneous patient populations, the adoption of novel clinical trial designs —can optimize patient enrollment, enhance data collection, and increase the generalizability of studies, making rigorous research feasible even in ultra-rare conditions.¹0 These mechanisms not only reduce diagnostic delays but also enable the discovery of novel biomarkers and facilitate the development of personalized therapies tailored to individual patients.

Clinakos’ Integrated Patient Data™ and Medically Smart AI™ platforms are designed to address data challenges in rare diseases by curating and aggregating high-quality, longitudinal patient data from multiple sources-including historical and real-time records, unstructured EMR notes, patient surveys, interviews, and PROs, into comprehensive profiles to help understand the natural history of disease and identify patients’ journeys. Our AI/ML engine, optimized for healthcare, uses natural language processing to extract insights from unstructured documents and identify patterns that might otherwise be missing. This results in valuable insights such as identifying diagnostic delays, discovering diagnostic algorithms, and uncovering health outcomes. By eliminating data silos, enabling earlier and more accurate diagnoses, supporting patient management, and aiding research and drug development with robust data, Clinakos’ platform helps improve care and quality of life for patients.

This approach provides dynamic, high-quality, real-time insights rather than static, retrospective analyses¹¹  and fully aligns with the FDA’s PFDD initiative, ensuring that the patient voice is central to drug development and regulatory decision-making, especially in the context of oncology, and rare diseases.

References:

1. U.S. Food and Drug Administration. Patient-Focused Drug Development: Collecting Comprehensive and Representative Input. Guidance for Industry, Food and Drug Administration Staff, and Other Stakeholders. Published 2020. Accessed August 11, 2025. https://www.fda.gov/media/139088/download
2. U.S. Food and Drug Administration. Patient-Focused Drug Development: Methods to Identify What Is Important to Patients. Guidance for Industry, Food and Drug Administration Staff, and Other Stakeholders. Published February 2022. Accessed August 11, 2025. https://www.fda.gov/regulatory-information/search-fda-guidance-documents/patient-focused-drug-development-methods-identify-what-important-patients
3. U.S. Food and Drug Administration. Patient-Focused Drug Development: Collecting Comprehensive and Representative Input. Guidance for Industry, Food and Drug Administration Staff, and Other Stakeholders. Published 2020. Accessed August 11, 2025. https://www.fda.gov/media/139088/download
4. U.S. Food and Drug Administration. Patient-Focused Drug Development: Surveying Clinical Trial Participants and Other Patients to Obtain Patient-Focused Trial Endpoints. Guidance for Industry, Food and Drug Administration Staff, and Other Stakeholders. Published March 2025. Accessed August 11, 2025. https://www.fda.gov/drugs/development-approval-process-drugs/fda-patient-focused-drug-development-guidance-series-enhancing-incorporation-patients-voice-medical
5. Berg AT, Ludwig NN, Wojnaroski M, Chapman CAT, Hommer R, Conecker G, Hecker JZ, Downs J. FDA Patient-Focused Drug Development Guidances: Considerations for Trial Readiness in Rare Developmental and Epileptic Encephalopathies. Neurology. 2024;102(1):e207958. https://www.neurology.org/doi/10.1212/WNL.0000000000207958
6. DLRC Group. Rare Disease Day: Regulatory Challenges in Rare Disease Drug Development. Published February 28, 2024. Accessed August 11, 2025. https://www.dlrcgroup.com/rare-disease-day-regulatory-challenges-in-rare-disease-drug-development/.
7. Johnson KB, Wei WQ, Weeraratne D, et al. Precision medicine, AI, and the future of personalized health care. Clin Transl Sci. 2021;14(1):86-93. doi:10.1111/cts.12884 .  https://pmc.ncbi.nlm.nih.gov/articles/PMC7877825/
8. Gangwal A, Lavecchia A. AI-Driven Drug Discovery for Rare Diseases. J Chem Inf Model. 2025;65(5):2214-2231. doi:10.1021/acs.jcim.4c01966. Published online 2024 Dec 17. Accessed August 11, 2025. https://pubs.acs.org/doi/abs/10.1021/acs.jcim.4c01966
9. Rajasimha HK, Dubey D. AI’s role in advancing rare disease research. Applied Clinical Trials. Published March 15, 2024. Accessed August 11, 2025. https://www.appliedclinicaltrialsonline.com/view/ai-s-role-in-advancing-rare-disease-research
10. Mills JA, Marini JC, Alvero R, et al. Novel Clinical Trial Design With Stratum-Specific Endpoints and Global Test Methods for Rare Diseases With Heterogeneous Clinical Manifestations. Stat Med. 2025;44(15):2554-2573. doi:10.1002/sim.9278. Published August 8, 2025. Accessed August 11, 2025. https://pubmed.ncbi.nlm.nih.gov/40772797/
11. https://clinakos.com/