Improved patient satisfaction and diagnostic accuracy in skin diseases with a Visual Clinical Decision Support System-A feasibility study with general practitioners

Abstract

Patient satisfaction is an important indicator of health care quality, and it remains an important goal for optimal treatment outcomes to reduce the level of misdiagnoses and inappropriate or absent therapeutic actions. Digital support tools for differential diagnosis to assist clinicians in reaching the correct diagnosis may be helpful, but how the use of these affect patients is not clear. The primary objective of this feasibility study was to investigate patient experience and satisfaction in a primary care setting where general practitioners (GPs) used a visual clinical decision support system (CDSS) compared with standard consultations. Secondary objectives were diagnostic accuracy and length of consultation. Thirty-one patients with a dermatologist-confirmed skin diagnosis were allocated to consult GPs that had been randomized to conduct either standard consultations (SDR, n = 21) or CDSS (n = 16) on two separate study days one week apart. All patients were diagnosed independently by multiple GPs (n = 3-8) in both the SDR and CDSS study arms. Using the CDSS, more patients felt involved in the decision making (P = 0.05). In addition, more patients were exposed to images during the consultations (P = 6.8e-27), and 83% of those that were shown images replied they felt better supported in the consultation. The use of CDSS significantly improved the diagnostic accuracy (34%, P = 0.007), and did not increase the duration of the consultation (median 10 minutes in both arms). This study shows for the first time that compared with standard GP consultations, CDSS assist the GP on skin related diagnoses and improve patient satisfaction and diagnostic accuracy without impacting the duration of the consultations. This is likely to increase correct treatment choices, patient adherence, and overall result in better healthcare outcomes.

Fig 1. CONSORT flow diagram.

Fig 2. In the majority of consultations CDSS improved the accuracy of the diagnostic outcome.

In total there were 21 different diagnoses. In 65% of the individual cases CDSS resulted in a more correct diagnosis than SDR (20/31 for CDSS, 9/31 for SDR). The following diagnoses received a high correctness in both consultation types (CDSS/SDR): atypical pigmented nävi (83/80), chronic venous insufficiency (100/83), lipoma (100/100), multiple nävi (71/80), psoriasis (83/80), rosacea (71/80), urticaria (80/71), vitiligo (100/80). For eight diagnoses of both consultations type the correctness was poor, that being: actinic keratoses (33/20), BCC (0/0), granuloma faciale (25/0), morphea (17/20, 25/50), multiple nävi (0/17), psoriasis (33/0). The largest difference between the two groups was found in 10 diagnoses: BCC (83/40, 83/20), alopecia (71/20), hereditary kaposi's sarcoma (50/17), morphea (25/50), dermal nevus (0/50), poliosis (67/20), pruritus (25/71), psoriasis (100/71, 33/0), rosacea (83/40), stasis dermatitis [Dermatitis varicosa] (100/33). The consultation duration varied across the different diagnoses as well as the diagnostic accuracy per patient. Consultations lasting less than 2 minutes or more than 20 minutes were considered outliers and excluded from analyses.

Fig 3. CDSS improves the patient satisfaction.

After each consultation in either the SDR (n = 175) or CDSS arm (n = 159) the patients were asked 11 questions regarding their experience with the GP (S1 Table). (A) Illustration of the first 6 questions. The overall mean across all questions was not different. For the individual questions there was also no significant difference between the means. In the CDSS compared with the SDR consultations, significantly more patients gave the maximum score (score 5) in question 4 (decision), P = 0.05. (B) Illustration of the last 5 questions. For question: 7) patients were generally not bothered that the GP used the internet or CDSS on a tablet or textbook, and there were no differences between study arms, 8.1) patients experienced that the GP used images with CDSS to a much higher degree (P = 6.78e-27), 8.2) patients felt better supported when the GP used images; 10) and for the CDSS relative to the SDR patients did the diagnose given by the GP to a higher degree match the diagnosis that the patient was given by a dermatologist prior to the study (P = 0.034).

Fig 4. Diagnostic accuracy significantly improved with CDSS compared to SDR.

In total n = 175 and n = 159 independent consultations with the diagnosis and patient information as the outcome were carried out for SDR and CDSS, respectively. (A) The diagnostic correctness as compared with the golden standard of the diagnosis from two independent senior dermatologists, was significantly higher with CDSS compared with SDR with a relative difference of 34% (P = 0.006). (B). Whisker plot for GPs who used CDSS or SDR, and who diagnosed correctly or not with respect to GPs age, experience and length of consultation (no significant differences). (C) Combined for both CDSS and SDR (no significant differences).