Related Experiment Video
Updated: Dec 3, 2025

Collecting Sleep, Circadian, Fatigue, and Performance Data in Complex Operational Environments
Published on: August 8, 2019
An Optimal Time for Treatment-Predicting Circadian Time by Machine Learning and Mathematical Modelling
Janina Hesse1,2, Deeksha Malhan1,2, Müge Yalҫin1,2
1Institute for Theoretical Biology (ITB), Charité-Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany.
Personalized medicine can improve cancer treatment outcomes by timing interventions with a patient's internal biological clock. Machine learning models predict this circadian time using gene expression, aiding individualized treatment timing.
Area of Science:
- Chronobiology
- Oncology
- Bioinformatics
Background:
- Personalized medicine aims to tailor treatments to individual patients and pathologies.
- Optimizing cancer treatment outcomes requires aligning interventions with the patient's internal biological time.
- Accurate characterization of a patient's internal circadian time is crucial for effective chronotherapy.
Purpose of the Study:
- To review the precision of machine learning and mathematical modeling in predicting patient circadian time.
- To explore the potential of using circadian observables for individualized cancer treatment timing.
- To discuss the integration of biological time into personalized cancer care strategies.
Main Methods:
- Reviewing current clinical standards for biological time measurement.
- Assessing general circadian rhythmicity assessment methods.
- Analyzing the use of rhythmic variables and mathematical models to predict biological time.
- Applying machine learning to gene expression data for circadian time prediction.
Main Results:
- Machine learning and mathematical modeling offer alternatives to traditional sleep-laboratory measurements for circadian time prediction.
- Circadian observables derived from gene expression can predict biological time with increasing precision.
- Internal patient time and circadian observables may offer additional indicators for individualized treatment timing.
Conclusions:
- Predicting circadian time via machine learning on accessible observables is a promising approach for personalized chronotherapy.
- Integrating internal patient time into cancer treatment strategies can enhance health outcomes and potentially reduce costs.
- Further research into circadian rhythmicity models and their clinical application is warranted for advancing personalized cancer care.
Related Concept Videos
Chronopharmacokinetics: Circadian Rhythms and Influence on Drug Response
The time of drug administration is an important factor to consider, as it can influence the toxic dose of a drug. For example, a study conducted by Prins et al. in 1997 examined the effects of the timing of...
Circadian Rhythms and Gene Regulation
Management of Insomnia
Biological Clocks and Seasonal Responses

