Discovery of signatures of fatal neonatal illness in vital signs using highly comparative time-series analysis

To seek new signatures of illness in heart rate and oxygen saturation vital signs from Neonatal Intensive Care Unit (NICU) patients, we implemented highly comparative time-series analysis to discover features of all-cause mortality in the next 7 days. We collected 0.5 Hz heart rate and oxygen saturation vital signs of infants in the University of Virginia NICU from 2009 to 2019. We applied 4998 algorithmic operations from 11 mathematical families to random daily 10 min segments from 5957 NICU infants, 205 of whom died. We clustered the results and selected a representative from each, and examined multivariable logistic regression models. 3555 operations were usable; 20 cluster medoids held more than 81% of the information, and a multivariable model had AUC 0.83. New algorithms outperformed others: moving threshold, successive increases, surprise, and random walk. We computed provenance of the computations and constructed a software library with links to the data. We conclude that highly comparative time-series analysis revealed new vital sign measures to identify NICU patients at the highest risk of death in the next week.

D D The exact sample size (n) for each experimental group/condition, given as a discrete number and unit of measurement D D A statement on whether measurements were taken from distinct samples or whether the same sample was measured repeatedly D D The statistical test(s) used AND whether they are one-or two-sided Only common tests should be described solely by name; describe more complex techniques in the Methods section.

D D
A description of all covariates tested D D A description of any assumptions or corrections, such as tests of normality and adjustment for multiple comparisons D D A full description of the statistical parameters including central tendency (e.g. means) or other basic estimates (e.g. regression coefficient) AND variation (e.g. standard deviation) or associated estimates of uncertainty (e.g. confidence intervals)

□□ □□ □□ □□
For null hypothesis testing, the test statistic (e.g. F, t, r) with confidence intervals, effect sizes, degrees of freedom and P value noted Give P values as exact values whenever suitable.
For Bayesian analysis, information on the choice of priors and Markov chain Monte Carlo settings For hierarchical and complex designs, identification of the appropriate level for tests and full reporting of outcomes Estimates of effect sizes (e.g. Cohen's d, Pearson's r), indicating how they were calculated Our web collection on statistics for biologists contains articles on many of the paints above.

Software and code
Policy information about availability of computer code Data collection

Commercial: Bedmaster
For manuscripts utilizing custom algorithms or software that are central to the research but not yet described in published literature, software must be made available to editors and reviewers. We strongly encourage code deposition in a community repository (e.g. GitHub). See the Nature Portfolio guidelines for submitting code & software for further information.

Data
Policy information about availability of data All manuscripts must include a data availability statement. This statement should provide the following information, where applicable: -Accession codes, unique identifiers, or web links for publicly available datasets -A description of any restrictions on data availability -For clinical datasets or third party data, please ensure that the statement adheres to our QQ!ky_ Anonymized data that support the findings of this study, with the evidence graph for the clustering, are openly available in the University of Virginiaʼs LibraData archive at https://doi.org/10.18130/V3/VJXODP. Python code used to process this data is archived in Zenodo at https://doi.org/10.5281/zenodo.4321332. This version and any future versions are also available in Github at https://github.com/fairscape/hctsa-py. Our code is licensed under terms of the MIT license (https://opensource.org/ licenses/MIT), and is a reimplementation in Python of most of Ben Fulcherʼs original MATLAB code, available here: https://github.com/benfulcher/hctsa. Software for clustering analysis and cross-implementation testing, together with the test data, may be found here: https://doi:10.5281/zenodo.4627625 .
Our code is licensed under terms of the MIT license (https://opensource.org/licenses/MIT), and is a reimplementation in Python of most of Ben Fulcher's original MATLAB code, available here: https://github.com/benfulcher/hctsa. Software for clustering analysis and cross-implementation testing, together with the test data, may be found here: https://doi:10.5281/ zenodo.4627625 .

Field-specific reporting
Please select the one below that is the best fit for your research. If you are not sure, read the appropriate sections before making your selection.

D Life sciences D Behavioural & social sciences D Ecological, evolutionary & environmental sciences
For a reference copy of the document with all sections, see nature.com/documents/nr-reporting-summary-flat.pdf

Life sciences study design
All studies must disclose on these points even when the disclosure is negative.

Sample size
Describe how sample size was determined, detailing any statistical methods used to predetermine sample size OR if no sample-size calculation was performed, describe how sample sizes were chosen and provide a rationale for why these sample sizes are sufficient.

Behavioural & social sciences study design
All studies must disclose on these points even when the disclosure is negative.

Ecological, evolutionary & environmental sciences study design
All studies must disclose on these points even when the disclosure is negative.

Study description
Research sample