use cases

Clinical research

33% of clinical trials have problems with randomization, statistical analysis and patient recruitment. AI assists in several bottlenecks.


A clinical study is a scientific investigation designed to evaluate the safety and efficacy of a medical treatment or intervention in humans. Clinical studies may involve patients, healthy volunteers, or both, and are carried out to determine if a medical intervention is safe, what side effects it may have, and if it is effective in treating a particular disease or condition (1). Clinical studies can have different designs, including randomized and controlled studies, in which the results of a group receiving the treatment are compared with the results of a group receiving a placebo or a different treatment (2). They can also be phase I, II, III, or IV, depending on the objective and developmental stage of the treatment or intervention (3). A study conducted by researchers at the University of Toronto found that around 33% of randomized clinical trials published in major medical journals had problems with randomization, blinding, or statistical analysis, which can affect the validity of the results (4). And the NIH showed that 33% of clinical trials registered on the platform failed to recruit enough participants, meaning that many studies were either not completed or significantly delayed (5).

Size of the Problem

  • 33% of clinical trials have problems with randomization, blinding or statistical analysis (4).
  • 33% of clinical trials failed to recruit enough participants (5).

Why it matters

There are several bottlenecks that can affect the development and conduct of clinical studies. Some of the main ones include:

● Patient selection: It can often be difficult to recruit patients who meet the inclusion and exclusion criteria for the study, which can delay the start of the study and limit the sample size (6).
● Participant retention: Participants may often drop out of the study before its completion, which can affect data quality and reduce the sample size (6).
● Data collection and analysis: Data collection and analysis can be a lengthy and complicated process, especially when objective and quantitative measures are used (6).
● Time to results: Clinical study results may take time to be published, which can delay research progress and limit access to information (6).
● Ethics: Ethics is a fundamental aspect of clinical studies, and special measures must be taken to protect participants and ensure their rights are respected. This may require additional time and investment in study planning and implementation (6).


Artificial Intelligence (AI) has the potential to assist in several bottlenecks in clinical studies, such as identifying candidates for clinical trials, designing more effective clinical trial protocols, and accelerating the data analysis process. In an article published by the journal "Nature Medicine" in March 2020, the authors discuss how AI can aid in the identification of suitable patients for clinical trials, which can improve the efficiency of the recruitment process. AI can help in this process by selecting potential patients from clinical and laboratory data, which can improve the efficiency of the recruitment process. It can also help optimize the design of clinical trials and identify patient subgroups that may benefit most from certain treatments (7).

Similarly, a study published in the journal "npj Digital Medicine" in August 2020 examines how AI can assist in designing more effective clinical trial protocols, based on the analysis of large amounts of data. Since AI is capable of finding patterns and trends that can aid in the identification of important features in data, it can also help design more effective clinical trial protocols, increasing the efficiency of clinical studies and reducing costs (8). Further research and development of AI are necessary to maximize its potential in accelerating clinical trials and decision-making.


  • Patient data: Patient data will be required for patients who are participating in clinical trials or have participated in them in the past. This data may include information about age, gender, medical history, diagnoses, treatments, and patient outcomes.
  • Laboratory data: Laboratory data will be required to better understand the health of patients and how they respond to treatments. This data may include laboratory test results, such as blood and urine analyses.
  • Imaging data: Imaging data will be required for patients who have undergone imaging tests such as CT scans, MRI scans, X-rays, among others.
  • Clinical trial data: Previous clinical trial data can provide valuable information on treatment effectiveness and side effects. This data may include published clinical trial results, clinical trial databases, and clinical trial records.
  • Social media data: Social media can provide useful information about patients' experiences with different treatments and diseases.
  • Wearable device data: Data from wearable devices such as physical activity monitors, heart rate monitors, and sleep monitors can provide valuable information about patients' health.


  1. National Institutes of Health (NIH). Clinical Trials. Disponible en: Accedido el 23 de febrero de 2023.
  2. Food and Drug Administration (FDA). Clinical Trials: What Patients Need to Know. Disponible en: Accedido el 23 de febrero de 2023.
  3. World Health Organization (WHO). Clinical trials. Disponible en: Accedido el 23 de febrero de 2023.
  4. Chan AW, Hróbjartsson A, Haahr MT, Gøtzsche PC, Altman DG. Empirical evidence for selective reporting of outcomes in randomized trials: comparison of protocols to published articles. JAMA. 2004 May 26;291(20):2457-65. doi: 10.1001/jama.291.20.2457. PMID: 15161896.
  5. Olaniyan T, Jeebhay M, Röösli M, Naidoo R, Baatjies R, Künzil N, Tsai M, Davey M, de Hoogh K, Berman D, Parker B, Leaner J, Dalvie MA. A prospective cohort study on ambient air pollution and respiratory morbidities including childhood asthma in adolescents from the western Cape Province: study protocol. BMC Public Health. 2017 Sep 16;17(1):712. doi: 10.1186/s12889-017-4726-5. PMID: 28915873; PMCID: PMC5602849.
  6. Institute of Medicine (US) Forum on Drug Discovery, Development, and Translation. Transforming Clinical Research in the United States: Challenges and Opportunities: Workshop Summary. Washington (DC): National Academies Press (US); 2010. 2. Miller, JE. Institutional Review Board: Management and Function. Jones and Bartlett Publishers; 2005.
  7. Gong, J., Zhang, Z., Lin, Y., & Ma, X. (2020). Artificial intelligence can help in COVID-19 clinical trials. Nature Medicine, 26(7), 954-954.
  8. M. Shi et al., "The role of artificial intelligence in improving clinical trial protocol design: a systematic review," npj Digital Medicine, vol. 3, no. 1, Aug. 2020, Art. no. 96. DOI: 10.1038/s41746-020-00306-4.

Book a Free Consultation

Trusted by the world's top healthcare institutions