Sistem Diagnosis Berbasis Fuzzy Probabilistik Untuk Pemetaan Kebutuhan Dukungan pada Unit terapi Autisme
Abstract
Behavioral diversity among pediatric autism patients requires therapists to establish functional support standards with high precision. This study aims to develop a clinical decision support system architecture using Probabilistic Fuzzy Logic to map functional support needs at an autism therapy unit in Malang. A quantitative methodology was implemented through a hybrid model integrating structured Planning Matrix observations with a probabilistic fuzzy inference mechanism. The study evaluated three primary clinical variables operationalized into 21 functional indicators. Observational data collected from 38 children generated 798 evaluation indices for system validation. Computational stages consisted of fuzzification, expert rule evaluation, probabilistic weighting, aggregation, and centroid defuzzification. The proposed system successfully classified subjects into three levels of functional support: Level 1, Level 2, and Level 3. Empirical evaluation demonstrated strong performance, achieving a Mean Absolute Percentage Error of 3.11% and an agreement accuracy of 96.89% compared with clinical expert evaluations. The findings indicate that the proposed model effectively synchronizes daily behavioral observations with therapeutic intervention recommendations, thereby supporting more measurable and interpretable therapy planning.
Keywords: Autism spectrum disorder; Clinical decision support; Expert system; Functional support diagnosis; Probabilistic fuzzy logic
Abstrak
Keberagaman perilaku pada anak dengan gangguan spektrum autisme menuntut terapis untuk menetapkan kebutuhan dukungan fungsional secara presisi. Penelitian ini bertujuan mengembangkan arsitektur sistem pendukung keputusan klinis menggunakan Logika Fuzzy Probabilistik untuk memetakan kebutuhan dukungan fungsional pada unit terapi autisme di Malang. Metodologi kuantitatif diterapkan melalui model hibrida yang mengintegrasikan observasi terstruktur berbasis Planning Matrix dengan mekanisme inferensi fuzzy probabilistik. Penelitian ini mengevaluasi tiga variabel klinis utama yang dioperasionalkan menjadi 21 indikator fungsional. Data observasi yang dikumpulkan dari 38 anak menghasilkan 798 indeks evaluasi untuk validasi sistem. Tahapan komputasi meliputi fuzzifikasi, evaluasi aturan pakar, pembobotan probabilistik, agregasi, dan defuzzifikasi centroid. Sistem yang diusulkan berhasil mengklasifikasikan subjek ke dalam tiga tingkat dukungan fungsional, yaitu Level 1, Level 2, dan Level 3. Evaluasi empiris menunjukkan kinerja yang sangat baik dengan Mean Absolute Percentage Error sebesar 3,11% dan tingkat kesesuaian sebesar 96,89% dibandingkan dengan evaluasi pakar klinis. Temuan penelitian menunjukkan bahwa model yang diusulkan mampu menyinkronkan observasi perilaku harian dengan rekomendasi intervensi terapeutik secara efektif, sehingga mendukung perencanaan terapi yang lebih terukur dan mudah diinterpretasikan.
Keywords
References
J. M. Burton, N. A. Creaghead, A. Duncan, N. Silbert, A. D. Breit, and S. M. Grether, “Social Communication, Repetitive Behaviors and Interests, and Adaptive Behavior in Girls With Autism Spectrum Disorder Without Intellectual Disability,” J. Autism Dev. Disord. 2025, pp. 1–16, Sep. 2025, doi: 10.1007/S10803-025-07035-Z.
V. M. Guillén, M. Verdugo, P. Jiménez, V. Aguayo, and A. M. Amor, “Support Needs of Children with Autism Spectrum Disorders: Implications for Their Assessment,” Behav. Sci. 2023, Vol. 13, Page 793, vol. 13, no. 10, p. 793, Sep. 2023, doi: 10.3390/BS13100793.
L. Zuhria and A. R. Habibi, “Comparative Analysis of Random Forest and SVM Performance in Asthma Prediction,” Sink. J. dan Penelit. Tek. Inform., vol. 9, no. 1, pp. 347–356, Jan. 2025, doi: 10.33395/SINKRON.V9I1.14346.
Erni Setiawati and Ervin Nurul Affrida, “Implementasi (Planning Matrix) Perencanaan pada Anak Usia 4-5 Tahun dengan Gangguan Lambat Bicara,” Indones. J. Early Child. J. Dunia Anak Usia Dini, vol. 6, no. 1, pp. 51–61, 2024, doi: 10.35473/ijec.v6i1.2830.
S. S. Joudar, A. S. Albahri, and R. A. Hamid, “Intelligent triage method for early diagnosis Autism Spectrum Disorder (ASD) based on integrated fuzzy multi-criteria decision-making methods,” Informatics Med. Unlocked, vol. 36, p. 101131, Jan. 2023, doi: 10.1016/J.IMU.2022.101131.
A. S. Albahri et al., “Explainable Artificial Intelligence Multimodal of Autism Triage Levels Using Fuzzy Approach-Based Multi-criteria Decision-Making and LIME,” Int. J. Fuzzy Syst. 2023 261, vol. 26, no. 1, pp. 274–303, Nov. 2023, doi: 10.1007/S40815-023-01597-9.
A. Bilgiç et al., “Personalized recommendation algorithm for rehabilitation intervention in children with Autism Spectrum Disorder based on the cognitive diagnosis model,” Front. Psychol., vol. 16, p. 1696155, Jan. 2026, doi: 10.3389/FPSYG.2025.1696155.
G. Capitoli, M. S. Nobile, E. L. Ambags, V. L’Imperio, M. Provenzano, and P. Liò, “Assisting clinical diagnosis with interpretable fuzzy probabilistic modelling,” BMC Med. Informatics Decis. Mak. 2025 253, vol. 25, no. 3, pp. 330-, Sep. 2025, doi: 10.1186/s12911-025-03183-5.
R. Saatchi, “Fuzzy Logic Concepts, Developments and Implementation,” Inf. 2024, Vol. 15, Page 656, vol. 15, no. 10, p. 656, Oct. 2024, doi: 10.3390/INFO15100656.
S. Sharif and M. R. Akbarzadeh-T, “Distributed Probabilistic Fuzzy Rule Mining for Clinical Decision Making,” Fuzzy Inf. Eng., vol. 13, no. 4, pp. 436–459, Oct. 2021, doi: 10.1080/16168658.2021.1978803.
T. M. Alam et al., “A Fuzzy Inference-Based Decision Support System for Disease Diagnosis,” Comput. J., vol. 66, no. 9, pp. 2169–2180, Sep. 2023, doi: 10.1093/COMJNL/BXAC068.
L. Widayanti, “Implementation of fuzzy analytical hierarchy process in ranking student learning achievement,” J. Ilm. Teknol. Inf. Asia, vol. 19, no. 1, pp. 35–41, Mar. 2025, doi: 10.32815/JITIKA.V19I1.1112.
M. Hayden-Evans et al., “Validating the International Classification of Functioning, Disability and Health Core Sets for Autism in a Sample of Australian School-Aged Children on the Spectrum,” J. Autism Dev. Disord. 2024 554, vol. 55, no. 4, pp. 1424–1437, Feb. 2024, doi: 10.1007/S10803-024-06295-5.
M. Tohir, F. A. Ahda, and D. A. Sulistyo, “Sistem Pendukung Keputusan Untuk Pemilihan Supplier Buah Di PT.Indomarco Prismatama Menggunakan Metode Analytical Hierarchy Process,” J. Ilm. Teknol. Inf. Asia, vol. 16, no. 2, pp. 113–122, Jul. 2022, doi: 10.32815/JITIKA.V16I2.629.
S. Sukinah and D. B. Taqiyah, “Alternative teaching behaviour management strategies for children with autism: An Approach based on functional behavioral assessment,” J. Kependidikan Penelit. Inov. Pembelajaran, vol. 8, no. 1, pp. 118–128, May 2024, doi: 10.21831/JK.V8I1.66775.
J. F. Lima, A. Patiño-León, M. Orellana, and J. L. Zambrano-Martinez, “Evaluating the Impact of Membership Functions and Defuzzification Methods in a Fuzzy System: Case of Air Quality Levels,” Appl. Sci. 2025, Vol. 15, vol. 15, no. 4, Feb. 2025, doi: 10.3390/APP15041934.
Mufidatul Isamiyah, “Pemodelan Logika Fuzzy Pada Incubator Telur Ayam Kampung Dengan Metode Centroid,” J. Ilm. Teknol. Inf. Asia, vol. 18, no. 02, pp. 17–23, 2024.
A. S. Albahri et al., “Prioritizing complex health levels beyond autism triage using fuzzy multi-criteria decision-making,” Complex Intell. Syst. 2024 105, vol. 10, no. 5, pp. 6159–6188, Jun. 2024, doi: 10.1007/S40747-024-01432-0.
G. Deng, M. Zhang, X. Meng, and J. Yuan, “Research on the problem of aggregation of multiple rules in fuzzy inference systems,” J. Intell. Fuzzy Syst., vol. 45, no. 2, pp. 2393–2408, Jun. 2023, doi: 10.3233/JIFS-230866;WEBSITE:WEBSITE:SAGE;WGROUP: STRING:PUBLICATION.
N. Cao, M. Holčapek, and R. Valášek, “On Inference Mechanisms of Fuzzy-Probabilistic Inference Systems,” Proc. Eighteenth Int. Conf. Fuzzy Set Theory Appl., pp. 41–45, 2026, doi: 10.15452/978-80-7599-515-5.2026.06.
G. Filo, E. Lisowski, P. Lempa, and K. Wisowski, “Modelling a Fuzzy Logic-Based Multiple-Actuator Hydraulic Lifting and Positioning System,” Appl. Sci. 2025, Vol. 15, Page 10747, vol. 15, no. 19, p. 10747, Oct. 2025, doi: 10.3390/APP151910747.
J. J. Cardiel-Ortega and R. Baeza-Serrato, “Probabilistic Fuzzy System for Evaluation and Classification in Failure Mode and Effect Analysis,” Process. 2024, Vol. 12, Page 1197, vol. 12, no. 6, p. 1197, Jun. 2024, doi: 10.3390/PR12061197.
T. Zhan, W. T. Li, B. J. Fan, and S. Liu, “Experimental Evaluation on Defuzzification of TSK-type-based Interval Type-2 Fuzzy Inference Systems,” Int. J. Control. Autom. Syst. 2023 214, vol. 21, no. 4, pp. 1338–1348, Mar. 2023, doi: 10.1007/S12555-021-0370-Z.
T. Mitsuishi, “Definition of Centroid Method as Defuzzification,” Formaliz. Math., vol. 30, no. 2, pp. 125–134, Dec. 2022, doi: 10.2478/FORMA-2022-0010.
I. Wahyuni et al., “Penerapan Metode Hybrid FIS Tsukamoto dan Algoritma Genetika untuk Prediksi Curah Hujan di Daerah Batu,” J. Teknol. Inf. dan Ilmu Komput., vol. 5, no. 4, pp. 483–492, Oct. 2018, doi: 10.25126/JTIIK.201854836.
M. Agustini, K. Fithriasari, and D. D. Prastyo, “An accuracy-level method for robust evaluation in predictive analytics,” Decis. Anal. J., vol. 18, p. 100661, Mar. 2026, doi: 10.1016/J.DAJOUR.2025.100661.
H. Jabbari and H. Shahbandarzadeh, “Design of Multilevel Fuzzy Inference System to Measure Strategic Capability, Case Study: Municipal Organization,” Commer. Strateg., vol. 17, no. 15, pp. 137–157, Aug. 2020, doi: 10.22070/CS.2020.3194.
R. Y. Coley, Q. Liao, N. Simon, and S. M. Shortreed, “Empirical evaluation of internal validation methods for prediction in large-scale clinical data with rare-event outcomes: a case study in suicide risk prediction,” BMC Med. Res. Methodol. 2023 231, vol. 23, no. 1, pp. 33-, Feb. 2023, doi: 10.1186/S12874-023-01844-5.
R. Sulek et al., “Support Preferences and Clinical Decision Support Systems (CDSS) in the Clinical Care of Autistic Children: Stakeholder Perspectives,” Adv. Neurodev. Disord. 2024 92, vol. 9, no. 2, pp. 355–365, Jul. 2024, doi: 10.1007/S41252-024-00410-4.
R. Sulek, C. Edwards, R. Monk, L. Patrick, S. Pillar, and H. Waddington, “Community Priorities for Outcomes Targeted During Professional Supports for Autistic Children and their Families,” J. Autism Dev. Disord. 2024 555, vol. 55, no. 5, pp. 1890–1901, Apr. 2024, doi: 10.1007/S10803-024-06333-2.
N. Shoaip, S. El-Sappagh, T. Abuhmed, and M. Elmogy, “A dynamic fuzzy rule-based inference system using fuzzy inference with semantic reasoning,” Sci. Reports 2024 141, vol. 14, no. 1, pp. 4275-, Feb. 2024, doi: 10.1038/s41598-024-54065-1.
C. C. Green et al., “An Evaluation of Child and Parent Outcomes Following Community-Based Early Intervention with Randomised Parent-Mediated Intervention for Autistic Pre-Schoolers,” Child Youth Care Forum 2024 535, vol. 53, no. 5, pp. 1213–1233, Feb. 2024, doi: 10.1007/S10566-024-09792-X.
J. T. Megerian et al., “Evaluation of an artificial intelligence-based medical device for diagnosis of autism spectrum disorder,” npj Digit. Med. 2022 51, vol. 5, no. 1, pp. 57-, May 2022, doi: 10.1038/s41746-022-00598-6.
V. N. Rathod, R. H. Goudar, and S. Sangani, “Unified interpretable AI for autism diagnosis and scalable severity-aware personalized adaptive e-learning,” Discov. Appl. Sci. 2026 84, vol. 8, no. 4, pp. 349-, Feb. 2026, doi: 10.1007/S42452-026-08335-4.
Y. Zheng, Z. Xu, T. Wu, and Z. Yi, “A systematic survey of fuzzy deep learning for uncertain medical data,” Artif. Intell. Rev. 2024 579, vol. 57, no. 9, pp. 230-, Aug. 2024, doi: 10.1007/S10462-024-10871-7.
G. Leroy et al., “Transparent deep learning to identify autism spectrum disorders (ASD) in EHR using clinical notes,” J. Am. Med. Informatics Assoc., vol. 31, no. 6, pp. 1313–1321, May 2024, doi: 10.1093/JAMIA/OCAE080.
R. Rosenbacke, Å. Melhus, M. McKee, and D. Stuckler, “How Explainable Artificial Intelligence Can Increase or Decrease Clinicians’ Trust in AI Applications in Health Care: Systematic Review,” JMIR AI, vol. 3, no. 1, p. e53207, Oct. 2024, doi: 10.2196/53207.
A. Aldrees et al., “Data-centric automated approach to predict Autism Spectrum Disorder based on selective features and explainable artificial intelligence,” Front. Comput. Neurosci., vol. 18, p. 1489463, Oct. 2024, doi: 10.3389/fncom.2024.1489463.
How To Cite This :
Refbacks
- There are currently no refbacks.
