Availability and use of cancer decision-support tools: a cross-sectional survey of UK primary care

Determining the feasibility of calculating pancreatic cancer risk scores for people with new-onset diabetes in primary care (DEFEND PRIME): study protocol

INTRODUCTION

Worldwide, pancreatic cancer has a poor prognosis. Early diagnosis may improve survival by enabling curative treatment. Statistical and machine learning diagnostic prediction models using risk factors such as patient demographics and blood tests are being developed for clinical use to improve early diagnosis. One example is the Enriching New-onset Diabetes for Pancreatic Cancer (ENDPAC) model, which employs patients' age, blood glucose and weight changes to provide pancreatic cancer risk scores. These values are routinely collected in primary care in the UK. Primary care's central role in cancer diagnosis makes it an ideal setting to implement ENDPAC but it has yet to be used in clinical settings. This study aims to determine the feasibility of applying ENDPAC to data held by UK primary care practices.

METHODS AND ANALYSIS

This will be a multicentre observational study with a cohort design, determining the feasibility of applying ENDPAC in UK primary care. We will develop software to search, extract and process anonymised data from 20 primary care providers' electronic patient record management systems on participants aged 50+ years, with a glycated haemoglobin (HbA1c) test result of ≥48 mmol/mol (6.5%) and no previous abnormal HbA1c results. Software to calculate ENDPAC scores will be developed, and descriptive statistics used to summarise the cohort's demographics and assess data quality. Findings will inform the development of a future UK clinical trial to test ENDPAC's effectiveness for the early detection of pancreatic cancer.

ETHICS AND DISSEMINATION

This project has been reviewed by the University of Surrey University Ethics Committee and received a favourable ethical opinion (FHMS 22-23151 EGA). Study findings will be presented at scientific meetings and published in international peer-reviewed journals. Participating primary care practices, clinical leads and policy makers will be provided with summaries of the findings.

A few-shot disease diagnosis decision making model based on meta-learning for general practice

BACKGROUND

Diagnostic errors have become the biggest threat to the safety of patients in primary health care. General practitioners, as the "gatekeepers" of primary health care, have a responsibility to accurately diagnose patients. However, many general practitioners have insufficient knowledge and clinical experience in some diseases. Clinical decision making tools need to be developed to effectively improve the diagnostic process in primary health care. The long-tailed class distributions of medical datasets are challenging for many popular decision making models based on deep learning, which have difficulty predicting few-shot diseases. Meta-learning is a new strategy for solving few-shot problems.

METHODS AND MATERIALS

In this study, a few-shot disease diagnosis decision making model based on a model-agnostic meta-learning algorithm (FSDD-MAML) is proposed. The MAML algorithm is applied in a knowledge graph-based disease diagnosis model to find the optimal model parameters. Moreover, FSDD-MAML can learn learning rates for all modules of the knowledge graph-based disease diagnosis model. For n-way, k-shot learning tasks, the inner loop of FSDD-MAML performs multiple gradient update steps to learn internal features in disease classification tasks using n×k examples, and the outer loop of FSDD-MAML optimizes the meta-objective to find the associated optimal parameters and learning rates. FSDD-MAML is compared with the original knowledge graph-based disease diagnosis model and other meta-learning algorithms based on an abdominal disease dataset.

RESULT

Meta-learning algorithms can greatly improve the performance of models in top-1 evaluation compared with top-3, top-5, and top-10 evaluations. The proposed decision making model FSDD-MAML outperforms all the other models, with a precision@1 of 90.02 %. We achieve state-of-the-art performance in the diagnosis of all diseases, and the prediction performance for few-shot diseases is greatly improved. For the two groups with the fewest examples of diseases, FSDD-MAML achieves relative increases in precision@1 of 29.13 % and 21.63 % compared with the original knowledge graph-based disease diagnosis model. In addition, we analyze the reasoning process of several few-shot disease predictions and provide an explanation for the results.

CONCLUSION

The decision making model based on meta-learning proposed in this paper can support the rapid diagnosis of diseases in general practice and is especially capable of helping general practitioners diagnose few-shot diseases. This study is of profound significance for the exploration and application of meta-learning to few-shot disease assessment in general practice.

Validation of a diagnostic prediction tool for colorectal cancer: a case-control replication study

BACKGROUND

Early detection of colorectal cancer (CRC) is crucial for survival. Primary care, the first point of contact in most cases, needs supportive risk assessment tools. We aimed to replicate the Swedish Colorectal Cancer Risk Assessment Tool (SCCRAT) for non-metastatic CRC in primary care and examine if risk factor patterns depend on sex and age.

METHODS

2,920 adults diagnosed with non-metastatic CRC during the years 2015-2019 after having visited a general practitioner the year before the diagnosis were selected from the Swedish Cancer Register and matched with 11,628 controls, using the same inclusion criteria except for the CRC diagnosis. Diagnostic codes from primary care consultations were collected from a regional health care database. Positive predictive values (PPVs) were estimated for the same 5 symptoms and combinations thereof as in the baseline study.

RESULTS

The results for patients aged ≥50 years old in the present study were consistent with the results of the SCCRAT study. All symptoms and combinations thereof with a PPV >5% in the present study had a PPV >5% in the baseline study. The combination of bleeding with abdominal pain (PPV 9.9%) and bleeding with change in bowel habit (PPV 7.8%) were the highest observed PPVs in both studies. Similar risk patterns were seen for all ages and when men and women were studied separately.

CONCLUSION

This external validation of the SCCRAT for non-metastatic CRC in primary care replicated the baseline study successfully and identified patients at high risk for CRC.

Ethical and legal implications of implementing risk algorithms for early detection and screening for oesophageal cancer, now and in the future

BACKGROUND

Oesophageal cancer has significant morbidity and mortality but late diagnosis is common since early signs of disease are frequently misinterpreted. Project DELTA aims to enable earlier detection and treatment through targeted screening using a novel risk prediction algorithm for oesophageal cancer (incorporating risk factors of Barrett's oesophagus including prescriptions for acid-reducing medications (CanPredict)), together with a non-invasive, low-cost sampling device (CytospongeTM). However, there are many barriers to implementation, and this paper identifies key ethical and legal challenges to implementing these personalised prevention strategies for Barrett's oesophagus/oesophageal cancer.

METHODS

To identify ethical and legal issues relevant to the deployment of a risk prediction tool for oesophageal cancer into primary care, we adopted an interdisciplinary approach, incorporating targeted informal literature reviews, interviews with expert collaborators, a multidisciplinary workshop and ethical and legal analysis.

RESULTS

Successful implementation raises many issues including ensuring transparency and effective risk communication; addressing bias and inequity; managing resources appropriately and avoiding exceptionalism. Clinicians will need support and training to use cancer risk prediction algorithms, ensuring that they understand how risk algorithms supplement rather than replace medical decision-making. Workshop participants had concerns about liability for harms arising from risk algorithms, including from potential bias and inequitable implementation. Determining strategies for risk communication enabling transparency but avoiding exceptionalist approaches are a significant challenge. Future challenges include using artificial intelligence to bolster risk assessment, incorporating genomics into risk tools, and deployment by non-health professional users. However, these strategies could improve detection and outcomes.

CONCLUSIONS

Novel pathways incorporating risk prediction algorithms hold considerable promise, especially when combined with low-cost sampling. However immediate priorities should be to develop risk communication strategies that take account of using validated risk algorithms, and to ensure equitable implementation. Resolving questions about liability for harms arising should be a longer-term objective.

Colorectal cancer in symptomatic patients: How to improve the diagnostic pathway

Even in countries with national screening programmes for colorectal cancer, most cancers are identified after the patient has developed symptoms. The patients present these symptoms usually to primary care, or in some countries to specialist care. In either healthcare setting, the clinician has to consider cancer to be a possibility, then to perform triage investigations, followed by definitive investigation, usually by colonoscopy. This apparently simple pathway is not simple: most symptoms of colorectal cancer are more likely to represent benign disease than cancer, and each of these stages represents selection of patients into a higher-risk pool. This article summarises a symptom-based approach to selection and initial investigation of such patients in primary care. Some special groups need particular attention, including the younger patient, those with an inherited predisposition to cancer, and those with co-morbidities.

Using an electronic safety netting tool designed to improve safety with respect to cancer referral in primary care: a qualitative service evaluation using rapid appraisal methods

BACKGROUND

This evaluation assesses the impact of an electronic safety netting software (E-SN) package, C the Signs, in primary care services across five boroughs in North East London (NEL).

AIM

This study evaluates the use of E-SN software in primary care, examining its benefits and barriers, safety implications, and overall impact on individual and practice usage.

DESIGN AND SETTING

The study is based on semi-structured interviews with 21 clinical and non-clinical members of staff from all primary care services using the software in NEL.

METHOD

Semi-structured interviews were conducted to gather data on individual use of the software, safety implications and practice use of features such as the monitoring dashboard. Data were analysed using a rapid qualitative methodology.

RESULTS

Two approaches to E-SN software adoption were reported: whole practice adoption and self-directed use. Practices benefitted from shared responsibility for safety netting and using software to track patients' progress in secondary care. Adoption was affected by information technology and administrative resources. Decision-support tools were used infrequently due to a lack of appreciation for their benefits. Selective adoption of different E-SN functions restricted its potential impact on early diagnosis.

CONCLUSION

The use of E-SN software in primary care services in NEL varied among participants. While some found it to be beneficial, others were sceptical of its impact on clinical decision-making. Nonetheless, the software was found to be effective in managing referral processes and tracking patients' progress in other points of care.

Protocol for a pragmatic cluster randomised controlled trial assessing the clinical effectiveness and cost-effectiveness of Electronic RIsk-assessment for CAncer for patients in general practice (ERICA)

INTRODUCTION

The UK has worse cancer outcomes than most comparable countries, with a large contribution attributed to diagnostic delay. Electronic risk assessment tools (eRATs) have been developed to identify primary care patients with a ≥2% risk of cancer using features recorded in the electronic record.

METHODS AND ANALYSIS

This is a pragmatic cluster randomised controlled trial in English primary care. Individual general practices will be randomised in a 1:1 ratio to intervention (provision of eRATs for six common cancer sites) or to usual care. The primary outcome is cancer stage at diagnosis, dichotomised to stage 1 or 2 (early) or stage 3 or 4 (advanced) for these six cancers, assessed from National Cancer Registry data. Secondary outcomes include stage at diagnosis for a further six cancers without eRATs, use of urgent referral cancer pathways, total practice cancer diagnoses, routes to cancer diagnosis and 30-day and 1-year cancer survival. Economic and process evaluations will be performed along with service delivery modelling. The primary analysis explores the proportion of patients with early-stage cancer at diagnosis. The sample size calculation used an OR of 0.8 for a cancer being diagnosed at an advanced stage in the intervention arm compared with the control arm, equating to an absolute reduction of 4.8% as an incidence-weighted figure across the six cancers. This requires 530 practices overall, with the intervention active from April 2022 for 2 years.

ETHICS AND DISSEMINATION

The trial has approval from London City and East Research Ethics Committee, reference number 19/LO/0615; protocol version 5.0, 9 May 2022. It is sponsored by the University of Exeter. Dissemination will be by journal publication, conferences, use of appropriate social media and direct sharing with cancer policymakers.

TRIAL REGISTRATION NUMBER

ISRCTN22560297.

A machine learning tool for identifying non-metastatic colorectal cancer in primary care

BACKGROUND

Primary health care (PHC) is often the first point of contact when diagnosing colorectal cancer (CRC). Human limitations in processing large amounts of information warrant the use of machine learning as a diagnostic prediction tool for CRC.

AIM

To develop a predictive model for identifying non-metastatic CRC (NMCRC) among PHC patients using diagnostic data analysed with machine learning.

DESIGN AND SETTING

A case-control study containing data on PHC visits for 542 patients >18 years old diagnosed with NMCRC in the Västra Götaland Region, Sweden, during 2011, and 2,139 matched controls.

METHOD

Stochastic gradient boosting (SGB) was used to construct a model for predicting the presence of NMCRC based on diagnostic codes from PHC consultations during the year before the date of cancer diagnosis and the total number of consultations. Variables with a normalised relative influence (NRI) >1% were considered having an important contribution to the model. Risks of having NMCRC were calculated using odds ratios of marginal effects.

RESULTS

Of the 361 variables used as predictors in the stochastic gradient boosting model, 184 had non-zero influence, with 16 variables having NRI >1% and a combined NRI of 63.3%. Variables representing anaemia and bleeding had a combined NRI of 27.6%. The model had a sensitivity of 73.3% and a specificity of 83.5%. Change in bowel habit had the highest odds ratios of marginal effects at 28.8.

CONCLUSION

Machine learning is useful for identifying variables of importance for predicting NMCRC in PHC. Malignant diagnoses may be hidden behind benign symptoms such as haemorrhoids.

Workload and workflow implications associated with the use of electronic clinical decision support tools used by health professionals in general practice: a scoping review

BACKGROUND

Electronic clinical decision support tools (eCDS) are increasingly available to assist General Practitioners (GP) with the diagnosis and management of a range of health conditions. It is unclear whether the use of eCDS tools has an impact on GP workload. This scoping review aimed to identify the available evidence on the use of eCDS tools by health professionals in general practice in relation to their impact on workload and workflow.

METHODS

A scoping review was carried out using the Arksey and O'Malley methodological framework. The search strategy was developed iteratively, with three main aspects: general practice/primary care contexts, risk assessment/decision support tools, and workload-related factors. Three databases were searched in 2019, and updated in 2021, covering articles published since 2009: Medline (Ovid), HMIC (Ovid) and Web of Science (TR). Double screening was completed by two reviewers, and data extracted from included articles were analysed.

RESULTS

The search resulted in 5,594 references, leading to 95 full articles, referring to 87 studies, after screening. Of these, 36 studies were based in the USA, 21 in the UK and 11 in Australia. A further 18 originated from Canada or Europe, with the remaining studies conducted in New Zealand, South Africa and Malaysia. Studies examined the use of eCDS tools and reported some findings related to their impact on workload, including on consultation duration. Most studies were qualitative and exploratory in nature, reporting health professionals' subjective perceptions of consultation duration as opposed to objectively-measured time spent using tools or consultation durations. Other workload-related findings included impacts on cognitive workload, "workflow" and dialogue with patients, and clinicians' experience of "alert fatigue".

CONCLUSIONS

The published literature on the impact of eCDS tools in general practice showed that limited efforts have focused on investigating the impact of such tools on workload and workflow. To gain an understanding of this area, further research, including quantitative measurement of consultation durations, would be useful to inform the future design and implementation of eCDS tools.

Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A Review

The inclusion of machine-learning-derived models in systematic reviews of risk prediction models for colorectal cancer is rare. Whilst such reviews have highlighted methodological issues and limited performance of the models included, it is unclear why machine-learning-derived models are absent and whether such models suffer similar methodological problems. This scoping review aims to identify machine-learning models, assess their methodology, and compare their performance with that found in previous reviews. A literature search of four databases was performed for colorectal cancer prediction and prognosis model publications that included at least one machine-learning model. A total of 14 publications were identified for inclusion in the scoping review. Data was extracted using an adapted CHARM checklist against which the models were benchmarked. The review found similar methodological problems with machine-learning models to that observed in systematic reviews for non-machine-learning models, although model performance was better. The inclusion of machine-learning models in systematic reviews is required, as they offer improved performance despite similar methodological omissions; however, to achieve this the methodological issues that affect many prediction models need to be addressed.

Clinical Prediction Models for Pancreatic Cancer in General and At-Risk Populations: A Systematic Review

INTRODUCTION

Identifying high-risk individuals using a risk prediction model could be a crucial first stage of screening pathways to improve the early detection of pancreatic cancer. A systematic review was conducted to critically evaluate the published primary literature on the development or validation of clinical risk prediction models for pancreatic cancer risk.

METHODS

MEDLINE, Embase, and Web of Science were searched for relevant articles from the inception of each database up to November 2021. Study selection and data extraction were conducted by 2 independent reviewers. The Prediction model Risk Of Bias Assessment Tool (PROBAST) was applied to assess risk of bias.

RESULTS

In total, 33 studies were included, describing 38 risk prediction models. Excluding studies with an overlapping population, this study consist of 15,848,100 participants, of which 58,313 were diagnosed with pancreatic cancer. Eight studies externally validated their model, and 13 performed internal validation. The studies described risk prediction models for pancreatic cancer in the general population (n = 14), patients with diabetes (n = 8), and individuals with gastrointestinal (and other) symptoms (symptoms included abdominal pain, unexplained weight loss, jaundice, and change in bowel habits and indigestion; n = 11). The commonly used clinical risk factors in the model were cigarette smoking (n = 27), age (n = 25), diabetes history (n = 22), chronic pancreatitis (n = 18), and body mass index (n = 14). In the 25 studies that assessed model performance, C-statistics ranged from 0.61 to 0.98. Of the 33 studies included, 6 were rated as being at a low risk of bias based on PROBAST.

DISCUSSION

Many clinical risk prediction models for pancreatic cancer had been developed for different target populations. Although low risk-of-bias studies were identified, these require external validation and implementation studies to ensure that these will benefit clinical decision making.

Lung cancer prediction using machine learning on data from a symptom e-questionnaire for never smokers, formers smokers and current smokers

PURPOSE

The aim of the present study was to investigate the predictive ability for lung cancer of symptoms reported in an adaptive e-questionnaire, separately for never smokers, former smokers, and current smokers.

PATIENTS AND METHODS

Consecutive patients referred for suspected lung cancer were recruited between September 2014 and November 2015 from the lung clinic at the Karolinska University Hospital, Stockholm, Sweden. A total of 504 patients were later diagnosed with lung cancer (n = 310) or no cancer (n = 194). All participants answered an adaptive e-questionnaire with a maximum of 342 items, covering background variables and symptoms/sensations suspected to be associated with lung cancer. Stochastic gradient boosting, stratified on smoking status, was used to train and test a model for predicting the presence of lung cancer.

RESULTS

Among never smokers, 17 predictors contributed to predicting lung cancer with 82% of the patients being correctly classified, compared with 26 predictors with an accuracy of 77% among current smokers and 36 predictors with an accuracy of 63% among former smokers. Age, sex, and education level were the most important predictors in all models.

CONCLUSION

Methods or tools to assess the likelihood of lung cancer based on smoking status and to prioritize investigative and treatment measures among all patients seeking care with diffuse symptoms are much needed. Our study presents risk assessment models for patients with different smoking status that may be developed into clinical risk assessment tools that can help clinicians in assessing a patient's risk of having lung cancer.

Machine Learning for Risk Prediction of Oesophago-Gastric Cancer in Primary Care: Comparison with Existing Risk-Assessment Tools

Simple Summary

Oesophago-gastric cancer is one of the commonest cancers worldwide, yet it can be particularly difficult to diagnose given that initial symptoms are often non-specific and routine screening is not available. Cancer risk-assessment tools, which calculate cancer risk based on symptoms and other risk factors present in the primary care record, can aid decisions on referrals for cancer investigations, facilitating earlier diagnosis. Diagnosing common cancers earlier could help improve survival rates. Using UK primary care electronic health record data, we compared five different machine learning techniques for probabilistic classification of cancer patients against a current widely used UK primary care cancer risk-assessment tool. The machine learning algorithms outperformed the current risk-assessment tool, with a higher overall accuracy and an ability to reasonably identify 11–25% more cancer patients. We conclude that machine-learning-based risk-assessment tools could help better identify suitable patients for further investigation and support earlier diagnosis.

Abstract

Oesophago-gastric cancer is difficult to diagnose in the early stages given its typical non-specific initial manifestation. We hypothesise that machine learning can improve upon the diagnostic performance of current primary care risk-assessment tools by using advanced analytical techniques to exploit the wealth of evidence available in the electronic health record. We used a primary care electronic health record dataset derived from the UK General Practice Research Database (7471 cases; 32,877 controls) and developed five probabilistic machine learning classifiers: Support Vector Machine, Random Forest, Logistic Regression, Naïve Bayes, and Extreme Gradient Boosted Decision Trees. Features included basic demographics, symptoms, and lab test results. The Logistic Regression, Support Vector Machine, and Extreme Gradient Boosted Decision Tree models achieved the highest performance in terms of accuracy and AUROC (0.89 accuracy, 0.87 AUROC), outperforming a current UK oesophago-gastric cancer risk-assessment tool (ogRAT). Machine learning also identified more cancer patients than the ogRAT: 11.0% more with little to no effect on false positives, or up to 25.0% more with a slight increase in false positives (for Logistic Regression, results threshold-dependent). Feature contribution estimates and individual prediction explanations indicated clinical relevance. We conclude that machine learning could improve primary care cancer risk-assessment tools, potentially helping clinicians to identify additional cancer cases earlier. This could, in turn, improve survival outcomes.

Early diagnosis of symptomatic ovarian cancer in primary care in the UK: opportunities and challenges

Background:

Ovarian cancer is the sixth most common cause of cancer-related death in the UK amongst women. Ovarian cancer presents particular challenges for general practitioners (GPs) to diagnose due to its rarity and presentation with non-specific symptoms.

Methods:

A narrative overview of the literature was conducted by searching PubMed and Researchgate for relevant articles, using keywords such as “ovarian cancer,” “primary care” and “diagnosis.”

Results and Discussion:

Studies have shown that in the UK, GPs have a lower readiness to refer and investigate potential cancer symptoms compared with their international counterparts; and this has been correlated with reduced survival. Early diagnosis can be facilitated through a people-focussed and system-based approach which involves both educating GPs and using risk algorithms, rapid diagnostic centres/multi-disciplinary centres and being data-driven through the identification of best practice from national audits. Further research is required into the best evidence-based early investigations for ovarian cancer and more effective biomarkers.

Using cancer risk algorithms to improve risk estimates and referral decisions

Background

Cancer risk algorithms were introduced to clinical practice in the last decade, but they remain underused. We investigated whether General Practitioners (GPs) change their referral decisions in response to an unnamed algorithm, if decisions improve, and if changing decisions depends on having information about the algorithm and on whether GPs overestimated or underestimated risk.

Methods

157 UK GPs were presented with 20 vignettes describing patients with possible colorectal cancer symptoms. GPs gave their risk estimates and inclination to refer. They then saw the risk score of an unnamed algorithm and could update their responses. Half of the sample was given information about the algorithm's derivation, validation, and accuracy. At the end, we measured their algorithm disposition. We analysed the data using multilevel regressions with random intercepts by GP and vignette.

Results

We find that, after receiving the algorithm's estimate, GPs' inclination to refer changes 26% of the time and their decisions switch entirely 3% of the time. Decisions become more consistent with the NICE 3% referral threshold (OR 1.45 [1.27, 1.65], p < .001). The algorithm's impact is greatest when GPs have underestimated risk. Information about the algorithm does not have a discernible effect on decisions but it results in a more positive GP disposition towards the algorithm. GPs' risk estimates become better calibrated over time, i.e., move closer to the algorithm.

Conclusions

Cancer risk algorithms have the potential to improve cancer referral decisions. Their use as learning tools to improve risk estimates is promising and should be further investigated.

Clinical Decision Support Systems for Diagnosis in Primary Care: A Scoping Review

Diagnosis is one of the crucial tasks performed by primary care physicians; however, primary care is at high risk of diagnostic errors due to the characteristics and uncertainties associated with the field. Prevention of diagnostic errors in primary care requires urgent action, and one of the possible methods is the use of health information technology. Its modes such as clinical decision support systems (CDSS) have been demonstrated to improve the quality of care in a variety of medical settings, including hospitals and primary care centers, though its usefulness in the diagnostic domain is still unknown. We conducted a scoping review to confirm the usefulness of the CDSS in the diagnostic domain in primary care and to identify areas that need to be explored. Search terms were chosen to cover the three dimensions of interest: decision support systems, diagnosis, and primary care. A total of 26 studies were included in the review. As a result, we found that the CDSS and reminder tools have significant effects on screening for common chronic diseases; however, the CDSS has not yet been fully validated for the diagnosis of acute and uncommon chronic diseases. Moreover, there were few studies involving non-physicians.

Predictive values for different cancers and inflammatory bowel disease of 6 common abdominal symptoms among more than 1.9 million primary care patients in the UK: A cohort study

BACKGROUND

The diagnostic assessment of abdominal symptoms in primary care presents a challenge. Evidence is needed about the positive predictive values (PPVs) of abdominal symptoms for different cancers and inflammatory bowel disease (IBD).

METHODS AND FINDINGS

Using data from The Health Improvement Network (THIN) in the United Kingdom (2000-2017), we estimated the PPVs for diagnosis of (i) cancer (overall and for different cancer sites); (ii) IBD; and (iii) either cancer or IBD in the year post-consultation with each of 6 abdominal symptoms: dysphagia (n = 86,193 patients), abdominal bloating/distension (n = 100,856), change in bowel habit (n = 106,715), rectal bleeding (n = 235,094), dyspepsia (n = 517,326), and abdominal pain (n = 890,490). The median age ranged from 54 (abdominal pain) to 63 years (dysphagia and change in bowel habit); the ratio of women/men ranged from 50%:50% (rectal bleeding) to 73%:27% (abdominal bloating/distension). Across all studied symptoms, the risk of diagnosis of cancer and the risk of diagnosis of IBD were of similar magnitude, particularly in women, and younger men. Estimated PPVs were greatest for change in bowel habit in men (4.64% cancer and 2.82% IBD) and for rectal bleeding in women (2.39% cancer and 2.57% IBD) and lowest for dyspepsia (for cancer: 1.41% men and 1.03% women; for IBD: 0.89% men and 1.00% women). Considering PPVs for specific cancers, change in bowel habit and rectal bleeding had the highest PPVs for colon and rectal cancer; dysphagia for esophageal cancer; and abdominal bloating/distension (in women) for ovarian cancer. The highest PPVs of abdominal pain (either sex) and abdominal bloating/distension (men only) were for non-abdominal cancer sites. For the composite outcome of diagnosis of either cancer or IBD, PPVs of rectal bleeding exceeded the National Institute of Health and Care Excellence (NICE)-recommended specialist referral threshold of 3% in all age-sex strata, as did PPVs of abdominal pain, change in bowel habit, and dyspepsia, in those aged 60 years and over. Study limitations include reliance on accuracy and completeness of coding of symptoms and disease outcomes.

CONCLUSIONS

Based on evidence from more than 1.9 million patients presenting in primary care, the findings provide estimated PPVs that could be used to guide specialist referral decisions, considering the PPVs of common abdominal symptoms for cancer alongside that for IBD and their composite outcome (cancer or IBD), taking into account the variable PPVs of different abdominal symptoms for different cancers sites. Jointly assessing the risk of cancer or IBD can better support decision-making and prompt diagnosis of both conditions, optimising specialist referrals or investigations, particularly in women.

Combining simple blood tests to identify primary care patients with unexpected weight loss for cancer investigation: Clinical risk score development, internal validation, and net benefit analysis

BACKGROUND

Unexpected weight loss (UWL) is a presenting feature of cancer in primary care. Existing research proposes simple combinations of clinical features (risk factors, symptoms, signs, and blood test data) that, when present, warrant cancer investigation. More complex combinations may modify cancer risk to sufficiently rule-out the need for investigation. We aimed to identify which clinical features can be used together to stratify patients with UWL based on their risk of cancer.

METHODS AND FINDINGS

We used data from 63,973 adults (age: mean 59 years, standard deviation 21 years; 42% male) to predict cancer in patients with UWL recorded in a large representative United Kingdom primary care electronic health record between January 1, 2000 and December 31, 2012. We derived 3 clinical prediction models using logistic regression and backwards stepwise covariate selection: Sm, symptoms-only model; STm, symptoms and tests model; Tm, tests-only model. Fifty imputations replaced missing data. Estimates of discrimination and calibration were derived using 10-fold internal cross-validation. Simple clinical risk scores are presented for models with the greatest clinical utility in decision curve analysis. The STm and Tm showed improved discrimination (area under the curve ≥ 0.91), calibration, and greater clinical utility than the Sm. The Tm was simplest including age-group, sex, albumin, alkaline phosphatase, liver enzymes, C-reactive protein, haemoglobin, platelets, and total white cell count. A Tm score of 5 balanced ruling-in (sensitivity 84.0%, positive likelihood ratio 5.36) and ruling-out (specificity 84.3%, negative likelihood ratio 0.19) further cancer investigation. A Tm score of 1 prioritised ruling-out (sensitivity 97.5%). At this threshold, 35 people presenting with UWL in primary care would be referred for investigation for each person with cancer referred, and 1,730 people would be spared referral for each person with cancer not referred. Study limitations include using a retrospective routinely collected dataset, a reliance on coding to identify UWL, and missing data for some predictors.

CONCLUSIONS

Our findings suggest that combinations of simple blood test abnormalities could be used to identify patients with UWL who warrant referral for investigation, while people with combinations of normal results could be exempted from referral.

Recognising Colorectal Cancer in Primary Care

Colorectal cancer (CRC) is the third most common cancer worldwide. Primary care professionals can play an important role in both prevention and early detection of CRC. Most CRCs are attributed to modifiable lifestyle factors, which can be addressed within primary care, and promotion of population-based screening programmes can aid early cancer detection in asymptomatic patients. Primary care professionals have a vital role in clinically assessing patients presenting with symptoms that may indicate cancer, as most patients with CRC first present with symptoms. These assessments are often challenging—many of the symptoms of CRC are non-specific and commonly occur in patients presenting with non-malignant disease. The range of options for investigating symptomatic patients in primary care is rapidly growing. Simple tests, such as faecal immunochemical testing (FIT), are now being used to guide decisions around referral for more invasive tests, such as colonoscopy, while direct access to specialist investigations is also becoming more common. Clinical decision support tools (CDSTs) which calculate cancer risk based on symptomatology, patient characteristics and test results can provide an additional resource to guide decisions on further investigation. This article explores the challenges of CRC prevention and detection from the primary care perspective, discusses current evidence-based approaches for CRC detection used in primary care (with examples from UK guidelines), and highlights emerging research which may likely alter practice in the future.

Electronic clinical decision support tool for assessing stomach symptoms in primary care (ECASS): a feasibility study

OBJECTIVE

To determine the feasibility of a definitive trial in primary care of electronic clinical decision support (eCDS) for possible oesophago-gastric (O-G) cancer.

DESIGN AND SETTING

Feasibility study in 42 general practices in two regions of England, cluster randomised controlled trial design without blinding, nested qualitative and health economic evaluation.

PARTICIPANTS

Patients aged 55 years or older, presenting to their general practitioner (GP) with symptoms associated with O-G cancer. 530 patients (mean age 68 years, 58% female) participated.

INTERVENTION

Practices randomised 1:1 to usual care (control) or to receive a previously piloted eCDS tool for suspected cancer (intervention), for use at the discretion of the GPs, supported by a theory-based implementation package and ongoing support. We conducted semistructured interviews with GPs in intervention practices. Recruitment lasted 22 months.

OUTCOMES

Patient participation rate, use of eCDS, referrals and route to diagnosis, O-G cancer diagnoses; acceptability to GPs; cost-effectiveness. Participants followed up 6 months after index encounter.

RESULTS

From control and intervention practices, we screened 3841 and 1303 patients, respectively; 1189 and 434 were eligible, 392 and 138 consented to participate. Ten patients (1.9%) had O-G cancer. eCDS was used eight times in total by five unique users. GPs experienced interoperability problems between the eCDS tool and their clinical system and also found it did not fit with their workflow. Unexpected restrictions on software installation caused major problems with implementation.

CONCLUSIONS

The conduct of this study was hampered by technical limitations not evident during an earlier pilot of the eCDS tool, and by regulatory controls on software installation introduced by primary care trusts early in the study. This eCDS tool needed to integrate better with clinical workflow; even then, its use for suspected cancer may be infrequent. Any definitive trial of eCDS for cancer diagnosis should only proceed after addressing these constraints.

TRIAL REGISTRATION NUMBER

ISRCTN125595588.

Factors shaping the implementation and use of Clinical Cancer Decision Tools by GPs in primary care: a qualitative framework synthesis

OBJECTIVE

Clinical Cancer Decision Tools (CCDTs) aim to alert general practitioners (GPs) to signs and symptoms of cancer, supporting prompt investigation and onward referral. CCDTs are available in primary care in the UK but are not widely utilised. Qualitative research has highlighted the complexities and mechanisms surrounding their implementation and use; this has focused on specific cancer types, formats, systems or settings. This study aims to synthesise qualitative data of GPs' attitudes to and experience with a range of CCDTs to gain better understanding of the factors shaping their implementation and use.

DESIGN

A systematic search of the published (MEDLINE, CINAHL, Web of Science and EMBASE) and grey literature (July 2020). Following screening, selection and assessment of suitability, the data were analysed and synthesised using normalisation process theory.

RESULTS

Six studies (2011 to 2019), exploring the views of GPs were included for analysis. Studies focused on the use of several different types of CCDTs (Risk Assessment Tools (RAT) or electronic version of RAT (eRAT), QCancer and the 7-point checklist). GPs agreed CCDTs were useful to increase awareness of signs and symptoms of undiagnosed cancer. They had concerns about the impact on trust in their own clinical acumen, whether secondary care clinicians would consider referrals generated by CCDT as valid and whether integration of the CCDTs within existing systems was achievable.

CONCLUSIONS

CCDTs might be a helpful adjunct to clinical work in primary care, but without careful development to legitimise their use GPs are likely to give precedence to clinical acumen and gut instinct. Stakeholder consultation with secondary care clinicians and consideration of how the CCDTs fit into a GP consultation are crucial to successful uptake. The role and responsibilities of a GP as a clinician, gatekeeper, health promoter and resource manager affect the interaction with and implementation of innovations such as CCDTs.

Development, validation and effectiveness of diagnostic prediction tools for colorectal cancer in primary care: a systematic review

BACKGROUND

Tools based on diagnostic prediction models are available to help general practitioners (GP) diagnose colorectal cancer. It is unclear how well they perform and whether they lead to increased or quicker diagnoses and ultimately impact on patient quality of life and/or survival. The aim of this systematic review is to evaluate the development, validation, effectiveness, and cost-effectiveness, of cancer diagnostic tools for colorectal cancer in primary care.

METHODS

Electronic databases including Medline and Web of Science were searched in May 2017 (updated October 2019). Two reviewers independently screened titles, abstracts and full-texts. Studies were included if they reported the development, validation or accuracy of a prediction model, or assessed the effectiveness or cost-effectiveness of diagnostic tools based on prediction models to aid GP decision-making for symptomatic patients presenting with features potentially indicative of colorectal cancer. Data extraction and risk of bias were completed by one reviewer and checked by a second. A narrative synthesis was conducted.

RESULTS

Eleven thousand one hundred thirteen records were screened and 23 studies met the inclusion criteria. Twenty-studies reported on the development, validation and/or accuracy of 13 prediction models: eight for colorectal cancer, five for cancer areas/types that include colorectal cancer. The Qcancer models were generally the best performing. Three impact studies met the inclusion criteria. Two (an RCT and a pre-post study) assessed tools based on the RAT prediction model. The third study looked at the impact of GP practices having access to RAT or Qcancer. Although the pre-post study reported a positive impact of the tools on outcomes, the results of the RCT and cross-sectional survey found no evidence that use of, or access to, the tools was associated with better outcomes. No study evaluated cost effectiveness.

CONCLUSIONS

Many prediction models have been developed but none have been fully validated. Evidence demonstrating improved patient outcome of introducing the tools is the main deficiency and is essential given the imperfect classification achieved by all tools. This need is emphasised by the equivocal results of the small number of impact studies done so far.

Understanding the role of GPs' gut feelings in diagnosing cancer in primary care: a systematic review and meta-analysis of existing evidence

BACKGROUND

Growing evidence for the role of GPs' gut feelings in cancer diagnosis raises questions about their origin and role in clinical practice.

AIM

To explore the origins of GPs' gut feelings for cancer, their use, and their diagnostic utility.

DESIGN AND SETTING

Systematic review and meta-analysis of international research on GPs' gut feelings in primary care.

METHOD

Six databases were searched from inception to July 2019, and internet searches were conducted. A segregated method was used to analyse, then combine, quantitative and qualitative findings.

RESULTS

Twelve articles and four online resources were included that described varied conceptualisations of gut feelings. Gut feelings were often initially associated with patients being unwell, rather than with a suspicion of cancer, and were commonly experienced in response to symptoms and non-verbal cues. The pooled odds of a cancer diagnosis were four times higher when gut feelings were recorded (OR 4.24, 95% confidence interval = 2.26 to 7.94); they became more predictive of cancer as clinical experience and familiarity with the patient increased. Despite being included in some clinical guidelines, GPs had varying experiences of acting on gut feelings as some specialists questioned their diagnostic value. Consequently, some GPs ignored or omitted gut feelings from referral letters, or chose investigations that did not require specialist approval.

CONCLUSION

GPs' gut feelings for cancer were conceptualised as a rapid summing up of multiple verbal and non-verbal patient cues in the context of the GPs' clinical knowledge and experience. Triggers of gut feelings not included in referral guidance deserve further investigation as predictors of cancer. Non-verbal cues that trigger gut feelings appear to be reliant on continuity of care and clinical experience; they tend to remain poorly recorded and are, therefore, inaccessible to researchers.

Rheumatologische paraneoplastische Syndrome

Rheumatologische paraneoplastische Syndrome sind selten, stellten jedoch eine wichtige Differenzialdiagnose zu klassischen rheumatologischen Krankheitsbildern dar. Durch das Erkennen der eindrücklichen Syndrome mit typischen Labor- und Untersuchungsbefunden ist oftmals eine beschleunigte Diagnose der zugrundeliegenden Malignität und kurative Therapie möglich. In dieser Übersichtsarbeit werden die Charakteristika rheumatologischer paraneoplastischer Syndrome vorgestellt.

Head and neck cancer risk calculator (HaNC-RC)-V.2. Adjustments and addition of symptoms and social history factors

OBJECTIVES

Head and neck cancer (HNC) diagnosis through the 2-week wait, urgent suspicion of cancer (USOC) pathway has failed to increase early cancer detection rates in the UK. A head and neck cancer risk calculator (HaNC-RC) has previously been designed to aid referral of high-risk patients to USOC clinics (predictive power: 77%). Our aim was to refine the HaNC-RC to increase its prediction potential.

DESIGN

Following sample size calculation, prospective data collection and statistical analysis of referral criteria and outcomes.

SETTING

Large tertiary care cancer centre in Scotland.

PARTICIPANTS

3531 new patients seen in routine, urgent and USOC head and neck (HaN) clinics.

MAIN OUTCOME MEASURES

Data collected were as follows: demographics, social history, presenting symptoms and signs and HNC diagnosis. Univariate and multivariate regression analysis were performed to identify significant predictors of HNC. Internal validation was performed using 1000 sample bootstrapping to estimate model diagnostics included the area under the receiver operator curve (AUC), sensitivity and specificity.

RESULTS

The updated version of the risk calculator (HaNC-RC v.2) includes age, gender, unintentional weight loss, smoking, alcohol, positive and negative symptoms and signs of HNC. It has achieved an AUC of 88.6% with two recommended triage referral cut-offs to USOC (cut-off: 7.1%; sensitivity: 85%, specificity: 78.3%) or urgent clinics (cut-off: 2.2%; sensitivity: 97.1%; specificity of 52.9%). This could redistribute cancer detection through USOC clinics from the current 60.9%-85.2%, without affecting total numbers seen in each clinical setting.

CONCLUSIONS

The use of the HaNC-RC v.2 has a significant potential in both identifying patients at high risk of HNC early thought USOC clinics but also improving health service delivery practices by reducing the number of inappropriately urgent referrals.

Communicating cancer risk in the primary care consultation when using a cancer risk assessment tool: Qualitative study with service users and practitioners

Background

Cancer risk assessment tools are designed to help detect cancer risk in symptomatic individuals presenting to primary care. An early detection of cancer risk could mean early referral for investigations, diagnosis and treatment, helping to address late diagnosis of cancer. It is not clear how best cancer risk may be communicated to patients when using a cancer risk assessment tool to assess their risk of developing cancer.

Objective

We aimed to explore the perspectives of service users and primary care practitioners on communicating cancer risk information to patients, when using QCancer, a cancer risk assessment tool.

Design

A qualitative study involving the use of individual interviews and focus groups.

Setting and participants

Conducted in primary care settings in Lincolnshire with a convenience sample of 36 participants (19 service users who were members of the public) and 17 primary care practitioners (general practitioners and practice nurses).

Results

Participants suggested ways to improve communication of cancer risk information: personalizing risk information; involving patients in use of the tool; sharing risk information openly; and providing sufficient time when using the tool during consultations.

Conclusion

Communication of cancer risk information is complex and difficult. We identified strategies for improving communication with patients involving cancer risk estimations in primary care consultations.