GRAFIK RECEIVER OPERATING CURVE (ROC) UNTUK UJI SENSITIVITAS DAN SPESIFISITAS SKOR RISIKO CEDERA REMAJA DI KOTA PALANGKA RAYA
DOI:
https://doi.org/10.51544/jmkm.v10i2.6425Keywords:
sensitivitas, spesifisitas, skor, cedera, ROCAbstract
Latar belakang: Cedera pada remaja masih menjadi masalah kesehatan masyarakat yang signifikan karena berdampak terhadap morbiditas, disabilitas, dan beban sosial-ekonomi keluarga. Diperlukan alat skrining yang valid dan efisien untuk mendeteksi remaja berisiko cedera sejak dini.
Tujuan: Penelitian ini bertujuan menilai sensitivitas, spesifisitas, dan akurasi skor risiko cedera pada remaja di Kota Palangka Raya menggunakan analisis Receiver Operating Characteristic (ROC).
Metode: Desain penelitian adalah cross-sectional dengan melibatkan 265 remaja usia 15–24 tahun dari lima SMA negeri dan komunitas remaja kota Palangka Raya tahun 2023. Data dikumpulkan melalui kuesioner yang mencakup skor kesehatan mental emosional, penggunaan helm, konsumsi alkohol, domisili, dan jenis kelamin, serta dikonfirmasi dengan pemeriksaan fisik dan radiologis sebagai gold standard.
Hasil: Hasil menunjukkan nilai Area Under the Curve (AUC) sebesar 0,714 (CI95% 0,623–0,805; p<0,001), menandakan akurasi sedang-baik. Nilai sensitivitas sebesar 56,8% dan spesifisitas 82,0% diperoleh pada titik potong optimal 13,47.
Kesimpulan: Skor risiko cedera memiliki kemampuan diskriminatif yang cukup baik untuk mengidentifikasi remaja berisiko, namun peningkatan sensitivitas diperlukan agar lebih efektif sebagai alat skrining awal di masyarakat.
Downloads
References
Ward J. Global, regional, and national mortality among young people aged 10–24 years, 1950–2019: a systematic analysis for the Global Burden of Disease Study 2019. The Lancet. 2021;398(10311):1593–698.
WHO. Adolescent and young adult health: risks and solutions. Geneva: WHO; 2024. 2024.
Peden AE, Cullen P, Bhandari B, Testa L, Wang A. A systematic review of the evidence for effectiveness of interventions to address transport and other unintentional injuries among adolescents. J Safety Res. 2023;85:321–38.
WHO. Global School-based Student Health Survey: Indonesia 2015 Fact Sheet. Geneva: WHO. 2017.
Kurniasih, Setiawan, Nurhidayah. Adolescent injury prevalence and associated risk behaviors in Indonesia: analysis of the Global School-based Student Health Survey 2007–2015. BMC Public Health. 2021;21(1):513–27.
Zainafree I, Hadisaputro S, Suwandono A, Widjanarko B. Adolescent Riding Behavior During the COVID-19 Pandemic in Urban Area, Indonesia: A Cross-sectional Study. Ethiopian Journal of Health Science. 2021;31(6):1133–42.
Ashari A, Siramaneerat I, Robby KNA, Sutinbuk D, Winarni S. Predicting Risk Behaviors among Adolescents in Indonesia: The Role of Socio-Demographic Factors in Smoking, Alcohol Use, and Illicit Substance Use. The Journal of the Medical Association of Thailand. 2025;9:728–38.
Cook T, Karriker-Jaffe K, Parks S, Simon T. Development and validation of an adolescent injury risk score: integrating behavioral and environmental factors. Injury Prevention. 2022;28:439–45.
Sainsbury DA, Downs J, Netto K, McKenna L. Factors Associated With Sports Injuries in Adolescents Who Play Team Sports at a Nonelite Level: A Scoping Review. Journal of Orthopaedic & Sports Physical Therapy. 2023;1(1):15.
Zhou XH, Obuchowski NA, McClish DK. Statistical Methods in Diagnostic Medicine. 2nd ed. New Jersey: John Wiley & Sons, Honoken; 2011.
Raza K, Barh D, Singh D, Ahmad N. Deep Learning Applications in Translational Bioinformatics. Dey Ni, Ashour AS, Fong SJ, editors. Vol. 15. United Kingdom: Elsevier Inc.; 2023.
He Z, Zhang Q, Song M, Tan X, Wangm Wei. Four overlooked errors in ROC analysis: how to prevent and avoid. BMJ Evidence Based Medicine. 2023;30(3):208–11.
Pilka T, Grzelak B, Sadurska A, Gorecki T, Dyczkowski K. Predicting Injuries in Football Based on Data Collected from GPS-Based Wearable Sensors. Multidisciplinary Digital Publishing Institute Journal. 2023;23(3):1591.
Toohey L, Drew M, Fortington L. Injury prediction in sport: the role of multivariate modelling and machine learning. Sportts Med. 2022;52(4):665–81.
Ayala F, Lopes-Valenciano A, Martin JAG, Croix MDS. A Preventive Model for Hamstring Injuries in Professional Soccer: Learning Algorithms. Int J Sports Med. 2019;40(5):344–53.
Robles-Palazon F, Puerta-Callejon JM, Martin JAG, Ste Croix MB. Predicting injury risk using machine learning in male youth soccer players. Chaos Solitons Fractals. 2023;167.
Nugroho S, Praseto W. Motorcycle risky behaviours and road accidents among adolescents in Jakarta metropolitan area, Indonesia. J Prev Med Public Health . 2019;52(5):324–32.
Widodo A. Analisis Validitas Self Reporting Questionnaire (SRQ) Terhadap Kesehatan Mental Pada Remaja. Jurnal Kesehatan Tambusai. 2024;5(1).
Nakas CT, Bantis LE, Gatsonis CA. ROC Analysis for Classification and Prediction in Practice. Abingdon, Oxon: CRC Press Taylor & Francis Group; 2023. 84 p.
Wang X, Wang Y, Tang J, Wang Y, Zhang R, Zhang X, et al. Preplanned Studies: Establishment and Validation of a Risk Prediction Model for Non-Suicidal Self-Injury Among Adolescents Based on Machine Learning Methods — Jiangsu Province, China, 2023. CCDC Weekly Journal. 2025;7(28):952–8.
Teuho A, Ponkilainen V, Koivusilta L, Rimpela A, Mattile VM. Health behaviors, health, sociodemographic factors, and school success in adolescence as risk factors for injury deaths: a longitudinal study. BMC Public Health. 2025;25.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Irene Febriani, Destinady K. Miden, Itma Annah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
.png)
