Trial Outcomes & Findings for Diagnostic Precision of the AI Tool Dermalyzer to Identify Malignant Melanomas in Subjects Seeking Primary Care for Melanoma-suspected Cutaneous Lesions (NCT NCT05172232)

Last Updated: 2025-02-05

Results Overview

The number of correctly classified skin lesions by the Dermalyzer (melanoma vs not melanoma), as compared with the result of the standard diagnostic procedure (dermatologist assessment and histoptahologic analysis).

Recruitment status

COMPLETED

Target enrollment

231 participants

Primary outcome timeframe

12 months

Results posted on

2025-02-05

Participant Flow

Participant milestones

Participant milestones
Measure	Primary Care Patients With Melanoma Suspicious Skin Lesion(s) Patients seeking primary care, having one or more skin lesion that the primary care physician cannot by certainty can rule out as being a possible melanoma.
Overall Study STARTED	231
Overall Study COMPLETED	228
Overall Study NOT COMPLETED	3

Reasons for withdrawal

Reasons for withdrawal
Measure	Primary Care Patients With Melanoma Suspicious Skin Lesion(s) Patients seeking primary care, having one or more skin lesion that the primary care physician cannot by certainty can rule out as being a possible melanoma.
Overall Study Lost to Follow-up	3

Baseline Characteristics

Diagnostic Precision of the AI Tool Dermalyzer to Identify Malignant Melanomas in Subjects Seeking Primary Care for Melanoma-suspected Cutaneous Lesions

Baseline characteristics by cohort

Baseline characteristics by cohort
Measure	Primary Care Patients With Melanoma Suspicious Skin Lesion(s) n=228 Participants Patients seeking primary care, having one or more skin lesion that the primary care physician cannot by certainty can rule out as being a possible melanoma.
Age, Continuous	56 years n=5 Participants
Sex: Female, Male Female	125 Participants n=5 Participants
Sex: Female, Male Male	103 Participants n=5 Participants
Race/Ethnicity, Customized Skin type 1: Pale skin, easily burns, never tans, often blond or red hair (assessed by physician)	19 participants n=5 Participants
Race/Ethnicity, Customized Skin type 2: Fair skin, easily burns, seldom tans (assessed by physician)	145 participants n=5 Participants
Race/Ethnicity, Customized Skin type 3: Darker white skin, sometimes burns, easily tans (assessed by physician)	52 participants n=5 Participants
Race/Ethnicity, Customized Skin type 4: Light brown skin, seldom burns, always tans (assessed by physician)	12 participants n=5 Participants
Region of Enrollment Sweden	228 participants n=5 Participants
Clinical suspicion degree of melanoma (asssessed by examining physician) Low degree of suspicion, but cannot exclude melanoma.	177 Participants n=5 Participants
Clinical suspicion degree of melanoma (asssessed by examining physician) High degree of suspicion of melanoma	51 Participants n=5 Participants

PRIMARY outcome

Timeframe: 12 months

Population: Patients with some degree ov melanoma suspsicion raised by the examining primary care physician.

Outcome measures

Outcome measures
Measure	Diagnostic Accuracy of Dermalyzer to Detect Melanoma n=253 uniqe skin lesions Proportions of melanoma and non-melanoma skin lesions identified by Dermalyser, as compared to the true diagnosis set by the conventional, standard diagnostic procedure.
Diagnostic Accuracy to Detect Melanoma True positives	20 number of skin lesions
Diagnostic Accuracy to Detect Melanoma False positives	92 number of skin lesions
Diagnostic Accuracy to Detect Melanoma False negatives	1 number of skin lesions
Diagnostic Accuracy to Detect Melanoma True negatives	140 number of skin lesions

SECONDARY outcome

Timeframe: Secondary measurement variable data was collected after baseline primary data inclusion was ended in Feb 2022, and completeted within 3 months from that.

Population: Primary care physicians that took part in the recruitment and inclusion of patients (study participants) in the trial.

User experience and perception of the Dermalyzer, in the form of System Usability Scale, to evaluate the usability and applicability in clinical praxis. The validated scale conists of 10 Likert scale based questions (scored 1-5 points), reflecting different aspects of usability, such as easiness to use, complexity, inconsistensy, understandability, etc. It summurizes in a score ranging from 0 - 100 points, where a high score reflects good usability properties.

Outcome measures

Outcome measures
Measure	Diagnostic Accuracy of Dermalyzer to Detect Melanoma n=138 Participants Proportions of melanoma and non-melanoma skin lesions identified by Dermalyser, as compared to the true diagnosis set by the conventional, standard diagnostic procedure.
Instrument Usability of the Device	75 SUS score points Interval 47.5 to 87.5

Adverse Events

Primary Care Patients With Melanoma Suspicious Skin Lesion(s)

Serious events: 0 serious events

Other events: 0 other events

Deaths: 0 deaths

Serious adverse events

Adverse event data not reported

Other adverse events

Adverse event data not reported

Additional Information

Professor Magnus Falk

Linköping University

Phone: +46708106176

Email: [email protected]

Results disclosure agreements

Principal investigator is a sponsor employee
Publication restrictions are in place