Tesis

Uji Diagnostik Karakter Polip Kolorektal Berdasarkan Artificial Intelligence Computer Assisted Diagnosis (CAD Eye Function) = Diagnostic Value ofArtificial Intelligence Computer Assisted Diagnosis (CAD Eye Function) For Colorectal Polyps.

Latar Belakang: Gold standart untuk skrining polip kolorektal saat ini adalah kolonoskopi, namun masih tingginya angka miss rate dan masih rendahnya angka ADR dan PDR, adapun faktor yang mempengaruhi meliputi faktor pasien, operator dan alat yang digunakan. Penggunaan artificial intelligence (AI) dalam kolonoskopi telah mendapatkan popularitas dengan membantu ahli endoskopi dalam deteksi dan karakterisasi polip. Tujuan: Menilai uji diagnostik kolonoskopi dengan menggunakan AI CAD eye function pada polip kolorektal Metode: Penelitian ini menggunakan desain cross sectional yang dilakukan di Pusat Endoscopi Saluran Cerna RSCM pada Januari-Mei 2024 terhadap pasien dewasa dengan kecurigaan polip kolorektal. Hasil: Sebanyak 60 pasien dengan 100 polip dilibatkan pada studi ini. Median (RIK) adalah usia 61,5 (20–76) tahun dengan 50% laki-laki dan 50% perempuan, mayoritas suku Jawa (46.7%), 12% obesitas, 30% memiliki IBD, 20% memiliki diabetes melitus, 13.3% memiliki riwayat polip di keluarga, dan hanya 10% memiliki riwayat kanker kolorektal di keluarga. Mayoritas polip berukuran 1-5 mm (56%), terletak di rektosigmoid (51%) dan memiliki morfologi sessile (75%). Berdasarkan hasil pemeriksaan, didapatkan pemeriksaan AI CAD eye function memiliki sensitivitas 79.17%, spesifisitas 75.00%, PPV 89.06%, NPV 58.33% dan akurasi 78.00%. Pada polip dengan ukuran dimminutive, didapatkan sensitivitas 86.27%, spesifisitas 60.00%, PPV 95.65%, NPV 30.00% dan akurasi 83.93%. Sedangkan, pada polip dengan ukuran non-dimminutive, didapatkan sensitivitas 61.90%, spesifisitas 78.26%, PPV 72.22%, NPV 69.23%, dan akurasi 70.45%. Pada polip sisi kiri kolon, didapatkan sensitivitas 78.85%, spesifisitas 81.25%, PPV 93.18%, NPV 54.17% dan akurasi 79.41%. Sedangkan, pada polip sisi kanan didapatkan sensitivitas 80.00%, spesifisitas 66.67%, PPV 80.00%, NPV 66.67%, dan akurasi 75.00%. Pada polip sessile, didapatkan sensitivitas 81.54%, spesifisitas 50.00%, PPV 91.38% NPV 29.41% dan akurasi 77.33%. Sedangkan, pada polip non-sessile didapatkan sensitivitas 57.14%, spesifisitas 88.89%, PPV 66.67%. NPV 84.21%, dan akurasi 80.00% Simpulan: Pemeriksaan AI CAD eye function memiliki nilai sensitifitas yang tinggi pada polip dimmunitive, sesile dan sisi kanan kolon sedangkan spesifisitas yang tinggi pada polip non dimmunitive, non sesile dan sisi kiri kolon.
Kata kunci: Artificial intelligence, CAD eye function, polip kolorektal


Background: The gold standard for colorectal polyp screening is currently colonoscopy, but the miss rate is still high and the ADR and PDR rates are still low. The risk factors include patient, operators and the tools used. The use of artificial intelligence (AI) in colonoscopy has gained popularity by assisting endoscopists in the detection and characterization of polyps. Objective: To assess the colonoscopy diagnostic test using AI CAD eye function on colorectal polyps Method: This study used a cross-sectional design conducted at the Gastrointestinal Endoscopy Center of RSCM in January-May 2024 on adult patients with suspected colorectal polyps. Results: A total of 60 patients with 100 polyps were involved in this study. Median (RIK) was 61.5 (20–76) years old with 50% male and 50% female, the majority were Javanese (46.7%), 12% obese, 30% had IBD, 20% had diabetes mellitus, 13.3% had a family history of polyps, and only 10% had a family history of colorectal cancer. The majority of polyps were 1-5 mm in size (56%), located in the rectosigmoid (51%) and had a sessile morphology (75%). Based on the results of the examination, it was found that the AI CAD eye function examination had a sensitivity of 79.17%, specificity of 75.00%, PPV of 89.06%, NPV of 58.33% and accuracy of 78.00%. In polyps with dimminutive size, sensitivity was 86.27%, specificity was 60.00%, PPV was 95.65%, NPV was 30.00% and accuracy was 83.93%. Meanwhile, in polyps with nondimminutive size, sensitivity was 61.90%, specificity was 78.26%, PPV was 72.22%, NPV was 69.23%, and accuracy was 70.45%. In polyps on the left side of the colon, sensitivity was 78.85%, specificity was 81.25%, PPV was 93.18%, NPV was 54.17% and accuracy was 79.41%. Meanwhile, in right-sided polyps, the sensitivity was 80.00%, specificity 66.67%, PPV 80.00%, NPV 66.67%, and accuracy 75.00%. In sessile polyps, the sensitivity was 81.54%, specificity 50.00%, PPV 91.38% NPV 29.41% and accuracy 77.33%. Meanwhile, in non-sessile polyps, the sensitivity was 57.14%, specificity 88.89%, PPV 66.67%. NPV 84.21%, and accuracy 80.00% Conclusion: AI CAD eye function examination has a high sensitivity value in dimmunitive, sessile polyps and right sided and high specificity in non-dimmunitive, non-sessile and left sided colon.
Keywords: Artificial intelligence, CAD eye function, colorectal polyps