Machine Learning in Differentiating Gliomas from Primary CNS Lymphomas: A Systematic Review, Reporting Quality, and Risk of Bias Assessment

BACKGROUND

Differentiating gliomas and primary CNS lymphoma represents a diagnostic challenge with important therapeutic ramifications. Biopsy is the preferred method of diagnosis, while MR imaging in conjunction with machine learning has shown promising results in differentiating these tumors.

PURPOSE

Our aim was to evaluate the quality of reporting and risk of bias, assess data bases with which the machine learning classification algorithms were developed, the algorithms themselves, and their performance.

DATA SOURCES

Ovid EMBASE, Ovid MEDLINE, Cochrane Central Register of Controlled Trials, and the Web of Science Core Collection were searched according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines.

STUDY SELECTION

From 11,727 studies, 23 peer-reviewed studies used machine learning to differentiate primary CNS lymphoma from gliomas in 2276 patients.

DATA ANALYSIS

Characteristics of data sets and machine learning algorithms were extracted. A meta-analysis on a subset of studies was performed. Reporting quality and risk of bias were assessed using the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) and Prediction Model Study Risk Of Bias Assessment Tool.

DATA SYNTHESIS

The highest area under the receiver operating characteristic curve (0.961) and accuracy (91.2%) in external validation were achieved by logistic regression and support vector machines models using conventional radiomic features. Meta-analysis of machine learning classifiers using these features yielded a mean area under the receiver operating characteristic curve of 0.944 (95% CI, 0.898-0.99). The median TRIPOD score was 51.7%. The risk of bias was high for 16 studies.

LIMITATIONS

Exclusion of abstracts decreased the sensitivity in evaluating all published studies. Meta-analysis had high heterogeneity.

CONCLUSIONS

Machine learning-based methods of differentiating primary CNS lymphoma from gliomas have shown great potential, but most studies lack large, balanced data sets and external validation. Assessment of the studies identified multiple deficiencies in reporting quality and risk of bias. These factors reduce the generalizability and reproducibility of the findings.

Patient characteristics associated with enrolment under voluntary programs implemented within fee-for-service systems in British Columbia and Quebec: a cross-sectional study

BACKGROUND

There is a paucity of information on patient characteristics associated with enrolment under voluntary programs (e.g. incentive payments) implemented within fee-for-service systems. We explored patient characteristics associated with enrolment under these programs in British Columbia and Quebec.

METHODS

We used linked administrative data and a cross-sectional design to compare people aged 40 years or more enrolled under voluntary programs to those who were eligible but not enrolled. We examined 2 programs in Quebec (enrolment of vulnerable patients with qualifying conditions [implemented in 2003] and enrolment of the general population [2009]) and 3 in BC (Chronic disease incentive [2003], Complex care incentive [2007] and enrolment of the general population [A GP for Me, 2013]). We used logistic regression to estimate the odds of enrolment by neighbourhood income, rural versus urban residence, previous treatment for mental illness, previous treatment for substance use disorder and use of health care services before program implementation, controlling for characteristics linked to program eligibility.

RESULTS

In Quebec, we identified 1 569 010 people eligible for the vulnerable enrolment program (of whom 505 869 [32.2%] were enrolled within the first 2 yr of program implementation) and 2 394 923 for the general enrolment program (of whom 352 380 [14.7%] were enrolled within the first 2 yr). In BC, we identified 133 589 people eligible for the Chronic disease incentive, 47 619 for the Complex care incentive and 1 349 428 for A GP for Me; of these, 60 764 (45.5%), 28 273 (59.4%) and 1 066 714 (79.0%), respectively, were enrolled within the first 2 years. The odds of enrolment were higher in higher-income neighbourhoods for programs without enrolment criteria (adjusted odds ratio [OR] comparing highest to lowest quintiles 1.21 [95% confidence interval (CI) 1.20-1.23] in Quebec and 1.67 [95% CI 1.64-1.69] in BC) but were similar across neighbourhood income quintiles for programs with health-related eligibility criteria. The odds of enrolment by urban versus rural location varied by program. People treated for substance use disorders had lower odds of enrolment in all programs (adjusted OR 0.60-0.72). Compared to people eligible but not enrolled, those enrolled had similar or higher numbers of primary care visits and longitudinal continuity of care in the year before enrolment.

INTERPRETATION

People living in lower-income neighbourhoods and those treated for substance use disorders were less likely than people in higher-income neighbourhoods and those not treated for such disorders to be enrolled in programs without health-related eligibility criteria. Other strategies are needed to promote equitable access to primary care.

Evaluating the intended and unintended consequences of opioid-prescribing interventions on primary care in British Columbia, Canada: protocol for a retrospective population-based cohort study

INTRODUCTION

Between 2015 and 2018, there were over 40 000 opioid-related overdose events and 4551 deaths among residents in British Columbia (BC). During this time the province mobilised a variety of policy levers to encourage physicians to expand access to opioid agonist treatment and the College of Physicians and Surgeons of British Columbia (CPSBC) released a practice standard establishing legally enforceable minimum thresholds of professional behaviour in the hopes of curtailing overdose events. Our goal is to conduct a comprehensive investigation of the intended and unintended consequences of these policy changes. Specifically, we aim to understand the effects of these measures on physician prescribing behaviours, identify physician characteristics associated with uptake of the new measures, and measure the effects of the policy changes on patients' access to quality primary care.

METHODS AND ANALYSIS

This is a population-level, retrospective cohort study of all BC primary care physicians who prescribed any opioid medication for opioid-use disorder or chronic non-cancer pain during the study period, and their patients. The study period is 1 January 2013-31 December 2018, with a 1-year wash-in period (1 January 2012-31 December 2012) to exclude patients who initiated long-term opioid treatment prior to our study period or whose pain type (ie, 'chronic non-cancer', 'acute', 'cancer or palliative', or 'other') cannot be confirmed. The project combines five administrative health datasets under the authority of the BC Ministry of Health, with the CPSBC's Physician Registry, BC Cancer Agency's Cancer Registry and Vital Statistics' Mortality data. We will create measures of prescribing concordance, access, continuity, and comprehensiveness to assess primary care delivery and quality at both the physician and patient level. We will use generalised estimating equations, interrupted time series, mixed effects models, and funnel plots to identify factors related to changes in prescribing and evaluate the impact of the changes to prescribing policies. Results will be reported using appropriate Enhancing the QUAlity and Transparency Of health Research guidelines (eg, STrengthening the Reporting of OBservational studies in Epidemiology).

ETHICS AND DISSEMINATION

This study has been approved by McGill University's Institutional Review Board (#A11-M55-19A), and the University of British Columbia's Research Ethics Board (#H19-03537). We will disseminate results via a combination of open access peer-reviewed journal publications, conferences, lay summaries and OpEds.