Dataset Information

Short-term local predictions of COVID-19 in the United Kingdom using dynamic supervised machine learning algorithms.

ABSTRACT:

Background

Short-term prediction of COVID-19 epidemics is crucial to decision making. We aimed to develop supervised machine-learning algorithms on multiple digital metrics including symptom search trends, population mobility, and vaccination coverage to predict local-level COVID-19 growth rates in the UK.

Methods

Using dynamic supervised machine-learning algorithms based on log-linear regression, we explored optimal models for 1-week, 2-week, and 3-week ahead prediction of COVID-19 growth rate at lower tier local authority level over time. Model performance was assessed by calculating mean squared error (MSE) of prospective prediction, and naïve model and fixed-predictors model were used as reference models. We assessed real-time model performance for eight five-weeks-apart checkpoints between 1st March and 14th November 2021. We developed an online application (COVIDPredLTLA) that visualised the real-time predictions for the present week, and the next one and two weeks.

Results

Here we show that the median MSEs of the optimal models for 1-week, 2-week, and 3-week ahead prediction are 0.12 (IQR: 0.08-0.22), 0.29 (0.19-0.38), and 0.37 (0.25-0.47), respectively. Compared with naïve models, the optimal models maintain increased accuracy (reducing MSE by a range of 21-35%), including May-June 2021 when the delta variant spread across the UK. Compared with the fixed-predictors model, the advantage of dynamic models is observed after several iterations of update.

Conclusions

With flexible data-driven predictors selection process, our dynamic modelling framework shows promises in predicting short-term changes in COVID-19 cases. The online application (COVIDPredLTLA) could assist decision-making for control measures and planning of healthcare capacity in future epidemic growths.

SUBMITTER: Wang X

PROVIDER: S-EPMC9509378 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Short-term local predictions of COVID-19 in the United Kingdom using dynamic supervised machine learning algorithms.

Wang Xin X Dong Yijia Y Thompson William David WD Nair Harish H Li You Y

Communications medicine 20220924

<h4>Background</h4>Short-term prediction of COVID-19 epidemics is crucial to decision making. We aimed to develop supervised machine-learning algorithms on multiple digital metrics including symptom search trends, population mobility, and vaccination coverage to predict local-level COVID-19 growth rates in the UK.<h4>Methods</h4>Using dynamic supervised machine-learning algorithms based on log-linear regression, we explored optimal models for 1-week, 2-week, and 3-week ahead prediction of COVID- ...[more]

PMID: 36168444

Similar Datasets

Project description:ObjectiveMeningiomas are the most common primary intracranial tumor, and resection is a mainstay of treatment. It is unclear what duration of imaging follow-up is reasonable for WHO grade I meningiomas undergoing complete resection. This study examined recurrence rates, timing of recurrence, and risk factors for recurrence in patients undergoing a complete resection (as defined by both postoperative MRI and intraoperative impression) of WHO grade I meningiomas.MethodsThe authors conducted a retrospective, single-center study examining recurrence risk for adult patients with a single intracranial meningioma that underwent complete resection. Uni- and multivariate nominal logistic regression and Cox proportional hazards analyses were performed to identify variables associated with recurrence and time to recurrence. Two supervised machine learning algorithms were then implemented to confirm factors within the cohort that were associated with recurrence.ResultsThe cohort consisted of 823 patients who met inclusion criteria, and 56 patients (6.8%) had recurrence on imaging follow-up. The median age of the cohort was 56 years, and 77.4% of patients were female. The median duration of head imaging follow-up for the entire cohort was 2.7 years, but for the subgroup of patients who had a recurrence, the median follow-up was 10.1 years. Estimated 1-, 5-, 10-, and 15-year recurrence-free survival rates were 99.8% (95% confidence interval [CI] 98.8%-99.9%), 91.0% (95% CI 87.7%-93.6%), 83.6% (95% CI 78.6%-87.6%), and 77.3% (95% CI 69.7%-83.4%), respectively, for the entire cohort. On multivariate analysis, MIB-1 index (odds ratio [OR] per 1% increase: 1.34, 95% CI 1.13-1.58, p = 0.0003) and follow-up duration (OR per year: 1.12, 95% CI 1.03-1.21, p = 0.012) were both associated with recurrence. Gradient-boosted decision tree and random forest analyses both identified MIB-1 index as the main factor associated with recurrence, aside from length of imaging follow-up. For tumors with an MIB-1 index < 8, recurrences were documented up to 8 years after surgery. For tumors with an MIB-1 index ≥ 8, recurrences were documented up to 12 years following surgery.ConclusionsLong-term imaging follow-up is important even after a complete resection of a meningioma. Higher MIB-1 labeling index is associated with greater risk of recurrence. Imaging screening for at least 8 years in patients with an MIB-1 index < 8 and at least 12 years for those with an MIB-1 index ≥ 8 may be needed to detect long-term recurrences.

Dataset Information

Short-term local predictions of COVID-19 in the United Kingdom using dynamic supervised machine learning algorithms.

Background

Methods

Results

Conclusions

Publications

Short-term local predictions of COVID-19 in the United Kingdom using dynamic supervised machine learning algorithms.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets