Developing high‑performance prediction models for medical outcomes
Published in Biomedical Research and Statistics
A prediction model can be considered to have high performance when it gives correct predictions in at least 90% of cases for qualitative outcomes, and at least 90% of the differences between the observed and predicted values are within clinical tolerance in the case of quantitative outcomes. A model with an accuracy between 80% and 90% can be possibly tolerated in some situations, but any model with less accuracy implies an unacceptably large error in clinical applications. Most of the models developed so far do not meet these criteria.
Moreover, prediction of the unknown is confused with classification of the known. Sensitivity-specificity-based area under the ROC curve is an inadequate indicator to assess this performance because this area is for classification of the known and not for predicting the unknown. Instead, use PPV and NPV. Similarly, the best cutoff for prediction is not based on Youden index but on Indrayan P-index that maximises PPV+NPV.
Developing high‑performance models requires a lot of extra effort that is rarely seen in the present endeavors. For this, it is imperative that a large number of known and suspected predictors are considered and complexity in terms of interactions and nonlinearity is accepted. Complex models with many predictors are not a big limitation now because of the wide availability of enormous computing power. An app can be easily developed to reside on a mobile phone even if the model is complex. More rigorous validation is needed than is done now, particularly external validation. Artificial intelligence‑based models can be linked to the relevant literature so that they continuously update with new developments under the data science paradigm.
This article (https://pmc.ncbi.nlm.nih.gov/articles/PMC13390955/) highlights the problems with many of the existing models and describes steps to develop a high‑performance model for medical outcomes. Many of the advices we give are rarely available in the literature.
Prof Indrayan is the only biostatistician in India as of 2025 to be honored with the fellowship of the Indian Academy of Sciences (of Dr CV Raman fame). He completed MS and PhD from the Ohio State University in a record time of three years. He established the first Department of Biostatistics and Medical Informatics in India – that too in a non-PG medical institution – in the year 1995, which was later emulated by SGPGI (Lko) and JIPMER (Py). He retired as Head of this department in 2010 and is currently (2025) working as a Biostatistics Consultant at Max Healthcare.
Prof Indrayan is respected as the top biostatistician in the country with more than 300 publications, including a large number of his own research on medical biostatistics. He has authored 6 books, three of which are published in the US for international audience, and more than 20 chapters. He has completed nearly 40 projects for the World Health Organization, the World Bank, and the UNAIDS. He has also been running an online course for an international audience for the past 20 years in collaboration with a US institute. Prof Indrayan has been a Visiting Faculty at the Ohio State University and a Visiting Research Scientist at the University of Massachusetts. He has presented his work in 17 international conferences.
Prof Indrayan is serving biostatistics in several ways. He has developed a medically integrated curriculum of biostatistics for medical under- and postgraduate students that medicalizes the subject of biostatistics. His publications on Personalized Statistical Medicine, medical uncertainties, and the conundrum of P-values are widely acclaimed. Among his original ideas are the smoking index, objective measurement of an individual’s positive health, scoring for assessing the quality of the process of medical research from choosing a problem to its publication, a simple and robust method of measurement of agreement without Bland-Altman limits, correct method for assessing predictive performance of a model, and ‘promote heart disease, stop cancer’ by research on choosing the cause of death in old age.
Follow the Topic
-
BMC Medicine
This journal publishes outstanding and influential research in all areas of clinical practice, translational medicine, medical and health advances, public health, global health, policy, and general topics of interest to the biomedical and sociomedical professional communities.
-
Communications Medicine
A selective open access journal from Nature Portfolio publishing high-quality research, reviews and commentary across all clinical, translational, and public health research fields.
-
European Journal of Clinical Nutrition
An international, peer-reviewed journal covering all aspects of human and clinical nutrition. This may encompass clinical, metabolic and epidemiological studies that describe nutritional interventions for clinical disease and health promotion.
-
Nature Medicine
This journal encompasses original research ranging from new concepts in human biology and disease pathogenesis to new therapeutic modalities and drug development, to all phases of clinical work, as well as innovative technologies aimed at improving human health.
-
Research in Health Services & Regions
This journal provides a forum for scientists focusing on health services research - in and for regions.
-
Journal of Quantitative Criminology
Related Collections
With Collections, you can get published faster and increase your visibility.
Generative AI and Crime
Generative AI is reshaping how we live, work, and produce knowledge. Its influence on scientific research is accelerating across every discipline, and criminology is no exception. In light of the profound transformation that this technological revolution entails, this special Collectiion of articles for the Journal of Quantitative Criminology seeks to explore the intersection of generative AI and crime. It is the first of its kind in the discipline.
See the full Call for Papers here.
Editors:
- Gian Maria Campedelli (University of Trento and Fondazione Bruno Kessler, Italy)
- George Mohler (Boston College, Boston, United States)
- P. Jeffrey Brantingham (University of California, Los Angeles, Los Angeles, United States)
Publishing Model: Hybrid
Deadline: Feb 15, 2027
Challenges and opportunities in obesity treatment
BMC Medicine is calling for submissions to our new Collection on the challenges and opportunities in obesity treatment. As we advance our collective understanding of obesity treatment, future opportunities abound. Recent advances in pharmacotherapy, particularly with GLP-1 agonists and SGLT2 inhibitors, offer novel avenues for managing weight and metabolic health. The rise of telehealth provides new methods for delivering care and support. These technological advances facilitate ongoing engagement and accountability in weight management, especially for individuals in remote or underserved areas. Addressing the multifactorial nature of obesity requires a comprehensive strategy that considers biological, behavioral, and environmental factors. This Collection aims to foster discourse among researchers, clinicians, and policymakers about effective intervention strategies, while also considering the social determinants that contribute to obesity disparities.
Medications such as GLP-1 agonists and SGLT2 inhibitors have significantly changed the landscape of obesity treatment by facilitating weight loss or contributing to diabetes management, while also protecting various organ systems and reducing risks for other diseases. Emerging evidence points to potential other suitable indications of such medications, for instance in treating substance addiction. Such innovations highlight the potential of various obesity interventions to offer health benefits, although challenges in offering and maintaining these benefits remain.
Additionally, understanding health equity in obesity treatment is pivotal. Research has shown that socioeconomic status, education, and access to healthcare significantly influence individual and community health outcomes. The interplay between social determinants and obesity underscores the necessity of interdisciplinary approaches that bridge clinical research and public health perspectives.
To support sustained efficiency of treatment, emerging evidence investigates how behavioral science and effective obesity medicine can be integrated for maximum treatment effect and sustainability at scale. Research in nutrition continues to evolve, allowing for a more holistic approach to weight management, recognizing how the quality of food impacts overall health outcomes. Ongoing research is underway to better characterize how access to quality nutrition, characteristics of food environments and personalized nutrition strategies may optimize therapeutic interventions, potentially leading to more sustainable weight management solutions. Addressing nutritional barriers and enhancing food environments can further empower individuals to make healthier choices.
Physical activity remains a cornerstone in obesity treatment. The integration of structured exercise interventions alongside dietary changes enhances weight loss and overall health. However, barriers to physical activity, such as time constraints, safety concerns, and lack of access to suitable facilities, must be systematically addressed through community-wide initiatives and policy changes. Future research on innovative strategies to promote physical activity, exploring the use of technology and community engagement to motivate healthier lifestyles is invited.
Moreover, it is crucial to consider the long-term sustainability of obesity treatment approaches. The rise of telehealth can facilitate ongoing engagement and accountability in weight management, especially for individuals in remote or underserved areas. Future studies may explore the efficacy and challenges of digital platforms in delivering personalized interventions and the potential for remote monitoring to enhance adherence and outcomes.
This Collection invites contributions that explore these critical themes. Topics of interest include but are not limited to:
- Opportunities and challenges of pharmacological/surgical innovations for obesity, diabetes, cardiovascular disorders and other related non-communicable diseases (NCDs)
- Challenges and advantages in integrating behavioral science and pharmacological treatment
- Health equity in obesity management such as differences in treatment effects and access to obesity medications
- Access and barriers to physical activity and nutrition interventions
- Long-term sustainability of treatment approaches
- Telehealth and technology in obesity management
- Community-based approaches to obesity treatment
- Personalized treatment strategies
- Impact of obesity treatments on other health outcomes
All manuscripts submitted to this journal, including those submitted to collections and special issues, are assessed in line with our editorial policies and the journal’s peer review process. Reviewers and editors are required to declare competing interests and can be excluded from the peer review process if a competing interest exists.
This Collection supports and amplifies research related to SDG 3 (Good Health and Well-being) and SDG 10 (Reduced Inequalities).
Publishing Model: Open Access
Deadline: Mar 02, 2027
