Implementation of Teledermoscopy and Artificial Intelligence

Sponsor

Region Skane (Other)

Overall Status

Recruiting

CT.gov ID

NCT05033678

Collaborator

Lund University (Other)

8,000

Enrollment

Locations

96.5

Anticipated Duration (Months)

727.3

Patients Per Site

7.5

Patients Per Site Per Month

Study Details

Study Description

Brief Summary

The study has 2 parts. Part 1 will investigate the effects of introducing teledermoscopy in clinical practice, more specifically the change in referral patterns, the risk of undetected skin cancers and the effect on diagnostic accuracy in general practitioners.

Part 2 will investigate how to introduce artificial intelligence (AI) within teledermocsopy. In this study the investigators will measure the effect of displaying the results of artificial intelligence in different ways and at different time points.

Data will be collcted through teledermoscopic referrals, patient records, national registries and questionnairs.

Condition or Disease	Intervention/Treatment	Phase
Skin Cancer	Device: Diagnostic algorithms

Detailed Description

Study objective:

Is teledermoscopy an equally safe method as conventional care for skin cancer patients?
How does teledermoscopy affect current care and organization of skin diseases?
How should the results of diagnostic algorithms be displayed in real-life health care to achieve the proper effect?
In what stage of the assessment of a skin lesion should the results of a diagnostic algorithm be presented to the physician to ensure the highest diagnostic accuracy while minimizing risk of undetected skin cancer?

Material and methods:

Study setting Patients scheduled for a skin examination for a suspected skin lesion can be recruited, both in dermatology clinics and participating primary care clinics.
Data acquisition Patient data and images will be collected with the Dermicus® application. Participating PCP and dermatologists will also fill in a questionnaire about their assessment of the patient. Additional informaiton will be collected from medical records, i.e. histopathological diagnoses, and from national registries. Questionnaires will be entered in a digital data base using REDCap®.
Statistical analyses 4.1. In part 1, the number of consultations send to dermatologists and for pathological analyses before introduction of teledermoscopy and during the first and second year if using teledermoscopy will be analysed. Descriptive statistics will be presented and differences between the different time periods will be tested with t-tests and paired t-tests.

4.2. In part 2, different ways of displaying the results of the artificial intelligence as well as feeding the results at different time points will be compared using analyses of sensitivity, specificity, and Area under ROC-curve (AUROC). The study will also report the impact the results of the artificial intelligence has on the willingness to change a diagnosis or a management plan.

Power set to 0.8 and significance to 0.05. 10% censures. 5.1. Patients recruited to this study can be used in several of the sub-studies. The aim of the study is to collect 8000 patients in total in this study.

5.2. To detect a difference in "unimaged skin cancers" between teledermoscopy and conventional care of patients 1200 cases and 2400 controls need to be included.

5.3. To detect a 10% difference in sensitivity/ specificity of diagnostic ability in PCPs before and after working with teledermoscopy 3400 patients need to be included.

5.4. To investigate how artificial intelligence should be implemented in clinical care the investigators have calculated that 6000 patients are needed to detect a 10% difference in sensitivity and specificity in the subgroups.

Ethical considerations and data management:

Data will be collected using Dermicus®, a CE-certified digital platform and mobile application. With the application downloaded on iPhones®, locked for any other uses, the history of the patients are registered. Then, by connecting the iPhone to a dermoscope, macroscopic and dermoscopic images are captured. All data will be stored on the servers of the health care region of Skåne, where the studies are conducted. Patients participating in the studies will be tagged with a study code enabling the investigators to extract the data from the patients that has agreed to participate in our study. Once a case has been created and sent to the data base all information will be deleted from the iPhone®. Additional data will also be retrieved from relevant medical records, e.g. histopathological diagnosis, and manually registered in an electronic database at a highly secure location (LUSEC/ REDCap provided by Lund University) . Data collected from PCP and dermatologists by questionnaires will also be registered in this data base by means of electronic surveys (REDCap). Information from primary care on total number of visits, referrals to dermatologists and referrals to pathology regarding skin lesions will be extracted from patient administrative systems. Age- and sex matched controls will be used for the study investigating missed skin cancer. These controls will be randomly selected from patients that was referred to a skin clinic by paper referral during the same period as the teledermoscopically referred patients were gathered. Algorithms for skin cancer diagnosis will be implemented in the web platform of Dermicus for the studies of introduction of artificial intelligence. Teledermoscopic assessors will be instructed on when and how to use these different tools.

Every week the newly entered data will be checked for completeness, and in the case of missing data, reminders to participating investigators will be send.

Then the data sets are complete, identifiers (such as personal identification number) will be replaced by a code kept secure at a different location than the data set. Data will thereafter be extracted from the data base to perform statistical analysis.

The study is approved by the Swedish Ethical Review Authority and all relevant approvals for data extraction and data storage has been obtained.

Study Design

Study Type:

Observational [Patient Registry]

Anticipated Enrollment :

8000 participants

Observational Model:

Cohort

Time Perspective:

Prospective

Official Title:

Teledermoscopy and Artificial Intelligence: Effects of Implementation in Clinical Practice

Actual Study Start Date :

Aug 16, 2021

Anticipated Primary Completion Date :

Aug 31, 2029

Anticipated Study Completion Date :

Aug 31, 2029

Outcome Measures

Primary Outcome Measures

Effect on referral patterns [2 years]
Measure how referral patterns are affected by the introduction of teledermoscopy
Effect on diagnostic accurcay in general practioners [2 years]
Measuring how the continuous use of teledermoscopy affects the diagnostic accuracy in general practitioners
Risk of undetected skin cancer [2 years]
Measuring if the risk of undetected skin cancer increases with the use of teledermoscopy
Effect on diagnostic accuracy due to different display of artificial intelligence [8 years]
Measuring if the diagnostic accurcy differs depending on how artificial intelligence is presented to the physician
Artificial intelligence timing and effect on diagnostic accuracy and willingness to rethink the preliminary diagnosis [8 years]
Measuring if the diagnostic accuracy and the willingness to reconsider the preliminary diagnosis differs according to when in the process a physician is presented with the results of the artificial intelligence

Eligibility Criteria

Criteria

Ages Eligible for Study:

15 Years and Older

Sexes Eligible for Study:

All

Accepts Healthy Volunteers:

Yes

Inclusion Criteria:

Has a skin lesion assessed by a physician during a visit
The physician decides to create a teledermoscopy referral

Exclusion Criteria:

inability or unwillingness to participate in the study
the patient is younger than 15 years old

Contacts and Locations

Locations

	Site	City	Country	Postal Code
1	Tabelund vardcentral	Eslov	Sweden
2	Capio vardcentral Helsingborg	Helsingborg	Sweden
3	Lomma vardcentral	Lomma	Sweden
4	Department of dermatology, Skane University Hospital	Lund	Sweden	22185
5	Helsa/ Kry vårdcentral	Lund	Sweden	22223
6	Masen vardcentral	Lund	Sweden	22732
7	Bokskogen vardcentral	Malmö	Sweden
8	Lideta vardcentral	Malmö	Sweden
9	Sjobo vardcentral	Sjobo	Sweden	27531
10	Halsomedicinskt center Staffanstorp	Staffanstorp	Sweden	24532
11	Staffastorps vardcentral	Staffanstorp	Sweden