IDEAL: Artificial Intelligence and Big Data for Early Lung Cancer Diagnosis Study (IDEAL)

• ClinicalTrials.gov Identifier: NCT03753724
• Recruitment Status: Recruiting
• First Posted: November 27, 2018
• Last Update Posted: November 27, 2018
• Sponsor: University of Oxford
• Collaborator: Optellum Ltd.
• Information provided by (Responsible Party): University of Oxford

Study Description

Brief Summary:

This study aims to test the use of novel CT image analysis techniques to enable a better characterisation of small pulmonary nodules. The study will incorporate solid and predominantly solid nodules of 5-15 mm scanned using a variety of scanner types, imaging protocols and patient populations. The investigators hope that the new image processing techniques will improve the accuracy of lung nodule analysis which will in turn reduce the number of unnecessary investigations for benign nodules and may increase the accuracy of the early diagnosis of lung cancer in malignant nodules. This study aims to test this novel analysis software to subsequently allow validation.

Condition or disease
Pulmonary Nodule, Solitary; Pulmonary Nodule, Multiple; Lung Cancer

Detailed Description:

As the commonest cancer with 1.8 million cases diagnosed each year worldwide, early diagnosis of lung cancer is important to reduce mortality. The early diagnosis of lung cancer is contingent on both the detection of a small lung nodule and determining whether it is malignant. Whilst computed tomography (CT) has proven to be a robust way of detecting lung nodules, they are often discovered on routine scanning as an incidental finding or as part of a lung cancer screening program. Hence, determining whether they are benign or malignant is challenging.

Up to 75% of smokers scanned either as part of their clinical care or in lung cancer screening trials have subcentimetre pulmonary nodules detected. This places a substantial burden on scanning facilities, staff and patients. Current methods of determining if lung nodules are benign or malignant are not standardised and unproven. The US National Lung Screening Trial (NLST) showed that up to 95% of lung nodules detected on CT scans of the chest were false positives i.e. they were not malignant. Detection of non-malignant nodules have the unwanted consequences of unnecessary cost as they require follow-up scanning or alternative methods of investigation, cause patient anxiety, may result in increased morbidity potentially by biopsy or resection, and result in increased patient radiation exposure due to follow-up CT scans or from PET-CT scans.

As part of standard care at present, patients with lung nodules greater than 4mm and sub-centimetre are followed up with CT scan(s), up to 5 scans, for up to 24 months, according to the internationally accepted Fleischner guidelines. Additional investigations, such as a positron-emission tomography (PET-CT) scan and biopsy or resection may also be performed based on the size and clinical risk profile of the patient.

Recent studies have shown that incorporating lung nodule characteristics such as size, texture, growth rate, contrast enhancement can improve the accuracy of predicting the risk of malignancy. This allows the stratification of lung nodules into different investigations and/or follow-up pathways based on the predicted risk of malignancy.

This study aims to test the use of novel CT image analysis techniques incorporated into a clinical risk model to characterise small pulmonary nodules. The study will incorporate solid and predominantly solid nodules of 5-15mm scanned using a variety of scanner types, imaging protocols and patient populations.

CT scans from patients referred to the Lung Nodule Clinic or for review by a specialist in nodule assessment as per current clinical practice will be reviewed. Patients who meet the inclusion/exclusion criteria will be contacted by a member of the clinical care team and study participation will be discussed.

Of the nodules detected, their management will be categorised as per standard care into the following groups:

GROUP 1. On review of the scans by an expert, no further follow up or investigation is required, as the nodule(s) has been categorised as benign. As the patient was unaware the scan was being reviewed and no further investigations are required. Patient is invited to take part in the study (by telephone).

GROUP 2. On review, the nodule is indeterminate and further scanning at a later date is required. The patient is informed of this, usually via a telephone call from either the doctor or nurse specialist working in the Lung Nodule Clinic (LNC) or site equivalent. This LNC is usually a virtual clinic - no physical interaction with the patient - and the follow up scan is reviewed and the patient contacted again via the virtual clinic. Patient is invited to take part in the study (by telephone, by post or in clinic if appropriate).

GROUP 3. On review, the nodule is regarded as potentially malignant and further scans and a clinic appointment is made for the patient. Patient is invited to take part in the study (in clinic if appropriate).

Apart from CT images routine care clinical information about the patient (e.g. age, sex, smoking status, family history of lung cancer) and data on nodule characteristics derived from the identified CT scan (and/or prior and subsequent) will be collected and used to test the new software program that will stratify pulmonary nodules in terms of their probability of being malignant or benign. All this data is routine and is collected as part of standard care therefore no study visits will need to be arranged.

As part of the health economics assessment patients will be invited to complete the EQ-5D-5L (quality of life), GAD-7 (anxiety), and productivity loss questionnaires. Patients will also be asked questions about their health utilisation. This data may also be collected from medical notes/electronic patient records.

The initial questionnaires will be completed within 2 weeks (if possible) of having the first scan and a follow-up will be carried out after 1 year for group 1 participants. Group 2 and 3 participants will also be invited to complete these questionnaires 3 months after their initial scan as they will have undergone further investigations during that time. The questionnaires will be completed over the phone for patients in groups 1 and over the phone or face to face when attending routine clinic appointments for groups 2 and 3.

Study Design

• Study Type: Observational
• Estimated Enrollment: 1050 participants
• Observational Model: Other
• Time Perspective: Prospective
• Official Title: IDEAL: Artificial Intelligence and Big Data for Early Lung Cancer Diagnosis Prospective Study (Phase 2)
• Actual Study Start Date: August 29, 2018
• Estimated Primary Completion Date: September 1, 2019
• Estimated Study Completion Date: September 1, 2020

Groups and Cohorts

Group/Cohort
Group 1; On review of the scans by an expert, no further follow up or investigation is required, as the nodule(s) has been categorised as benign. As the patient was unaware the scan was being reviewed and no further investigations are required. Patient is invited to take part in the study (by telephone).
Group 2; On review, the nodule is indeterminate and further scanning at a later date is required. The patient is informed of this, usually via a telephone call from either the doctor or nurse specialist working in the Lung Nodule Clinic (LNC) or site equivalent. This LNC is usually a virtual clinic - no physical interaction with the patient - and the follow up scan is reviewed and the patient contacted again via the virtual clinic. Patient is invited to take part in the study (by telephone, by post or in clinic if appropriate).
Group 3; On review, the nodule is regarded as potentially malignant and further scans and a clinic appointment is made for the patient. Patient is invited to take part in the study (in clinic if appropriate).

Outcome Measures

Primary Outcome Measures :

1. The overall diagnostic performance of a new computer aided prediction (CAP) model for malignancy in small pulmonary nodules (% diagnostic accuracy). [ Time Frame: Up to 1 year. ]
   Area Under the Receiver Operator Characteristic Curve (AUC).

Secondary Outcome Measures :

1. The health economic benefits of the CAP model. [ Time Frame: At 2 weeks, 3 months (group 2 & 3 only) and year 1. ]
   Measured reduction in health care related costs using the CAP model algorithm compared to the current standard of care.
2. The diagnostic performance of the CAP model for malignancy in small pulmonary nodules at a specific operating point relevant to clinical practice. [ Time Frame: Up to 1 year. ]
   Measure of diagnostic performance of the risk model.

Eligibility Criteria

• Ages Eligible for Study: 18 Years and older (Adult, Older Adult)
• Sexes Eligible for Study: All
• Sampling Method: Non-Probability Sample

Study Population

Patients aged 18 years old or older with CT scans reported as having pulmonary nodule(s) of 5-15mm who meet the inclusion criteria and who can be placed into groups 1, 2 or 3.

Criteria

Inclusion Criteria:

• Male or Female, aged 18 years or above
• CT scans identified as having pulmonary nodule(s) of 5-15mm
• Patients with solid or predominantly solid nodules referred to the pulmonary nodule clinic or for CT scan review by a specialist
• CT scan section thickness of 3mm and less

Exclusion Criteria:

• The CT scans are technically inadequate
• Having received treatment for cancer in the last 5 years
• Patient has more than five reported qualifying nodules

Contacts and Locations

Contacts

Contact: Magda Laskawiec-Szkonter, MA; 01865227612 ext 27612; magda.laskawiec@ouh.nhs.uk

Contact: Fergus Gleeson, Prof; 01865235746 ext 35746; Fergus.Gleeson@ouh.nhs.uk

Locations

United Kingdom

Royal Berkshire Nhs Foundation Trust; Not yet recruiting

Reading, Berkshire, United Kingdom, RG1 5AN

Principal Investigator: Tara Barton, MD

Nottingham University Hospitals Nhs Trust; Recruiting

Nottingham, Nottinghamshire, United Kingdom, NG7 2UH

Principal Investigator: David Baldwin, Prof

Oxford University Hospitals NHS Foundation Trust; Recruiting

Oxford, Oxfordshire, United Kingdom, OX3 7LE

Contact: Fergus Gleeson, Prof 01865235746 ext 35746 fergus.gleeson@ouh.nhs.uk

Contact: Magda Laskawiec-Szkonter, MA 01865227612 magda.laskawiec@ouh.nhs.uk

Principal Investigator: Fergus Gleeson, Prof

Leeds Teaching Hospitals Nhs Trust; Not yet recruiting

Leeds, West Yorkshire, United Kingdom, LS9 7TF

Principal Investigator: Matthew Callister, MD

Sponsors and Collaborators

University of Oxford

Optellum Ltd.

Investigators

• Principal Investigator: Fergus Gleeson, Prof; University of Oxford/Oxford University Hospitals NHS Foundation Trust

More Information

• Responsible Party: University of Oxford
• ClinicalTrials.gov Identifier: NCT03753724
• Other Study ID Numbers: 13489
• First Posted: November 27, 2018
• Last Update Posted: November 27, 2018
• Last Verified: November 2018

Individual Participant Data (IPD) Sharing Statement:

• Plan to Share IPD: Undecided
• Plan Description: To be confirmed.

• Studies a U.S. FDA-regulated Drug Product: No
• Studies a U.S. FDA-regulated Device Product: No

Keywords provided by University of Oxford:

pulmonary nodules; lung cancer; artificial intelligence; CAP model

Additional relevant MeSH terms:

Lung Neoplasms; Multiple Pulmonary Nodules; Solitary Pulmonary Nodule; Respiratory Tract Neoplasms; Thoracic Neoplasms; Neoplasms by Site; Neoplasms; Lung Diseases; Respiratory Tract Diseases