Latar Belakang: Depresi merupakan masalah kesehatan mental yang sering terjadi pada lansia dengan persentase sebesar 12%-16%. Depresi dapat menurunkan fungsi kehidupan sehari-hari dan menurunkan kualitas hidup. Tujuan penelitian ini adalah mengetahui efektivitas terapi tawa dalam menurunkan depresi dan meningkatkan kualitas hidup pada lanjut usia serta evaluasi ekonominya. Metode: Penelitian ini merupakan penelitian true experimental dan times series dengan menggunakan desain crossover pada terapi tawa dan terapi puzzle. Lokasi penelitian dilakukan di Panti Werdha Jakarta Timur. Populasi lansia adalah 250 orang dengan jumlah subjek penelitian sebanyak 86 orang yang dipilih menggunakan proporsional random sampling dan randomnisasi untuk dijadikan dua kelompok. Pengumpulan data menggunakan kuesioner Geriatric Depression Scale (GDS) dan Older People’s Quality of Life (OPQOL) modifikasi. Analisis data untuk menilai efektifitas menggunakan uji Different in Different (DID) dan menilai efektifitas biaya menggunakan ICER. Hasil: Terdapat pengaruh terapi tawa terhadap depresi diawal intervensi sebelum crossover secara statistik( p= 0,011), sehingga terapi tawa menurunkan depresi lebih besar dibandingkan terapi puzzle. Setelah crossover tidak terdapat perbedaan terapi tawa dan terapi puzzle sama-sama dapat menurunkan depresi (P=0,347). Pada skor OPQOL tidak terdapat perbedaan pengaruh intervensi terapi tawa dan terapi puzzle secara statistik baik sebelum crossover (p=0,581) maupun setelah crossover (p=0,140), sehingga terapi tawa dan terapi puzzle sama-sama dapat meningkatkan kualitas hidup. Pada efektifitas biaya, terapi tawa lebih efektif (65,1%) dibandingkan terapi puzzle (37,2%) dalam menurunkan tingkat/kategori depresi. Untuk peningkatan efektivitas penurunan tingkat atau kategori depresi sebesar 1% pada kelompok terapi tawa diperlukan tambahan biaya sebesar Rp 5.640,-. Nilai tersebut dianggap sepadan (Worth spent) menurut para klinisi dan memiliki efektivitas penurunan tingkat atau kategori depresi dan efektivitas biaya dibandingkan terapi puzzle dalam menurunkan depresi. Kesimpulan: Terapi tawa dan terapi puzzle memiliki pengaruh pada penurunan tingkat/kategori depresi dan peningkatan kualitas hidup pada lansia namun pengaruh penurunan tingkat/kategori depresi pada terapi tawa lebih banyak dibandingkan dengan terapi puzzle. Biaya yang dikeluarkan sepadan (Worth spent) dengan penurunan tingkat/kategori depresi. Saran: Melakukan advokasi kepada Kementerian Sosial, Dinas Sosial, dan Panti Werdha agar dapat menambahkan program terapi tawa dalam upaya meningkatkan kesehatan lanjut usia khususnya menurunkan depresi.

Background: Depression is a mental health problem that often occurs in people over 65 years old with a percentage of 12%-16%. Depression can decrease the functioning of daily life. The purpose of this study is to determine the effectiveness and cost of laughter therapy in reducing depression and improving the quality of life in the elderly and its economic evaluation. Method: This study uses a crossover design and true experimental research with a time series. The location of the research was carried out at the East Jakarta Nursing Home. The elderly population was 250 with the number of 86 research subjects selected using proportional random sampling and randomization. Data were collected using modified Geriatric Depression Scale (GDS) and Older People's Quality of Life (OPQOL) questionnaires. Data analysis used the Different in Different (DID) test and the calculation of the cost-effectiveness of laughter therapy and puzzle therapy. Results: There was a statistically significant effect of laughter therapy on depression at the beginning of the intervention before crossover (p= 0.011), so that laughter therapy reduced depression more than puzzle therapy. After crossover, there was no difference between laughter therapy and puzzle therapy, both of which could reduce depression (P=0.347). In the OPQOL score, there was no statistically different effect of laughter therapy and puzzle therapy interventions both before the crossover (p=0.581) and after the crossover (p=0.140), so that laughter therapy and puzzle therapy could both improve the quality of life. In terms of cost-effectiveness, laughter therapy more effective (65.1%) than puzzle therapy (37.2%) in lowering the level/category of depression. For an increase in the effectiveness of reducing the level or category of depression by 1% in the laughter therapy group, an additional cost of Rp 5,640 is required, and the value is considered worth spent according to the clinicians and has the effectiveness of reducing the level or category of depression and cost-effectiveness compared to puzzle therapy in reducing depression. Conclusion: The effect of depression reduction on laughter therapy was more than puzzle therapy at the beginning of the intervention before the crossover. Laughter and puzzle therapy has an effect on improving the quality of life in the elderly. The costs incurred are commensurate with the decrease in the level/category of depression. Suggestion: Advocate to the Ministry of Social Affairs, Social Services, and Nursing Homes so that they can add a laughter therapy program in an effort to improve the health of the elderly, especially to reduce depression.

Latar Belakang Gagal jantung adalah kondisi kronis dan progresif, dengan prevalensi di dunia 1-3% dan di Indonesia 5% (peringkat ke 4 di dunia) dengan kematian 50% dalam 5 tahun. Angka readmisi dalam 90 hari adalah 50%-75% dan dalam 30 hari 2-3%, sedangkan di Indonesia angka readmisi dalam 30 hari adalah 17%. Biaya rawat inap gagal jantung dapat mencapai empat ratus juta rupiah per pasien per tahun. Data BPJS Kesehatan 2018 terdapat 130.275 kejadian rawat inap tingkat lanjut pasien gagal jantung kongestif dan berdasarkan tarif JKN 2023 perkiraan biaya rawat inapnya akan berkisar antara 379 milyar sampai 4,2 triliun rupiah. Dengan memanfaatkan teknologi kekinian dari Artificial Intelligence dan kapabilitas serta kebiasaan masyarakat paska pandemi Covid-19, penelitian ini membuat model prediksi berbasis machine learning dengan menemukan faktor-faktor risiko yang dapat menjadi prediktor rawat inap berulang, yang kemudian diimplementasikan di dalam prototype yang digunakan dalam kolaborasi antara penyedia layanan kesehatan dengan pasien yang turut terlibat melakukan monitoring mandiri sehingga dapat mempertahankan kualitas hidupnya dan mengendalikan biaya perawatan baik yang dibayarkan oleh pasien sendiri, menggunakan asuransi ataupun dengan pendanaan pemerintah. Metode Penelitian ini terdiri atas beberapa tahap, dengan studi kuantitatif dan kualitatif menggunakan data rekam medis pasien gagal jantung di Rumah Sakit Jantung dan Pembuluh Darah Harapan Kita, Jakarta. Dimulai dengan Systematic Literature Review untuk menemukan faktor risiko rawat inap berulang di rumah sakit dan untuk menemukan novelty, pemodelan prediksi dengan studi kohort retrospektif, analisis kebutuhan sistem dengan studi kualitatif, pengembangan prototype, dan uji prototype dengan studi kohort prospektif. Hasil Systematic Literature Review tentang prediktor readmisi gagal jantung dengan machine learning dari PubMed, Science Direct, ProQuest, Scopus, Embase, google scholar menghasilkan 19 artikel terseleksi. 13 studi berasal dari USA, tidak ditemukan studi serupa di Indonesia, dengan algoritma terbaik adalah Neural Network. Pada tahap pemodelan prediksi diperoleh 2738 data pasien gagal jantung paska rawat inap di RS Jantung dan Pembuluh Darah Harapan Kita Jakarta, dengan ketersediaan 64 variabel. Dengan Orange Data Mining, terseleksi sebanyak 31 features. Model terbaik menggunakan Random Forest, dengan AUC 0,976, CA 0,912, F1 0,912, Precision 0,916 dan Recall 0,912, diimplementasikan dalam prototype aplikasi Fineheart dengan fitur aplikasi profil pasien, dashboard, catatan harian jantungku, penilaian kualitas hidup, rencana kontrol, instruksi medis dan obat, catatan asupan makanan dan cairan, edukasi, konsultasi. Uji efikasi prototype menunjukkan angka readmisi pada kelompok intervensi (20%), lebih rendah daripada kelompok kontrol (43,3%). Perubahan signifikan terjadi pada 2 parameter KCCQ yaitu Quality of Life (p=0,029) dan Overall Summary Score (p=0,001). Tingkat kepatuhan menggunakan prototype aplikasi juga berpengaruh signifikan terhadap kedua parameter tersebut dan mencegah readmisi. Kesimpulan Model prediksi readmisi pasien gagal jantung dengan machine learning yang diimplementasikan ke prototype aplikasi dapat digunakan untuk monitoring di rumah untuk mencegah readmisi dan mempertahankan kualitas hidup.

Background Heart failure is a chronic and progressive condition, with a prevalence in the world of 1-3% and in Indonesia 5% (ranked 4th in the world) with a mortality of 50% within 5 years. The readmission rate in 90 days is 50%-75% and in 30 days it is 2-3%, while in Indonesia the readmission rate in 30 days is 17%. The cost of hospitalization for heart failure can reach four hundred million rupiah per patient per year. The government health insurance of Indonesia (BPJS Kesehatan) data for 2018 shows 130,275 advanced hospitalizations for congestive heart failure patients and based on the 2023 tariff, the estimated cost of hospitalization will range from 379 billion to 4.2 trillion rupiah. By utilizing the latest technology from Artificial Intelligence and the capabilities and habits of society after the Covid-19 pandemic, this research creates a machine learning-based predictive model by finding risk factors that can lead to hospital readmission, which are then implemented in the prototype that is used in collaboration between health care providers with patients who are also involved in conducting self-monitoring so that they can maintain their quality of life and control the costs of care whether paid by the patient himself, using insurance or with government funding. Method This research consisted of several stages, with quantitative and qualitative studies using medical records of heart failure patients at the Harapan Kita Cardiovascular Center. Starting with a Systematic Literature Review to find risk factors of readmission and to find novelties, predictive modeling with retrospective cohort study, system requirements analysis with qualitative studies, prototype development, and prototype testing with prospective cohort study. Results A systematic literature review on predictors of heart failure readmission using machine learning from PubMed, Science Direct, ProQuest, Scopus, Embase, Google Scholar resulted in 19 selected articles. 13 studies came from the USA, no similar studies were found in Indonesia, with the best algorithm being Neural Network. At the prediction modeling stage, data was obtained on 2738 post-hospitalization heart failure patients at Harapan Kita Cardiovascular Hospital, Jakarta, with the availability of 64 variables. With Orange Data Mining, 31 features are selected. The best model uses Random Forest, with AUC 0,976, CA 0,912, F1 0,912, Precision 0,916 and Recall 0,912, implemented in the Fineheart application prototype with patient profile application features, dashboard, my heart diary, quality of life assessment, control plan, medical instructions and medication, food and fluid intake records, education, consultation. The prototype efficacy test showed that the readmission rate in the intervention group (20%), was lower than the control group (43.3%). Significant changes occurred in 2 KCCQ parameters, Quality of Life (p=0.029) and Overall Summary Score (p=0.001). The level of presence of application prototypes also has a significant effect on these two parameters and prevents readmissions. Conclusion The readmission prediction model for heart failure patients with machine learning implemented in the application prototype can be used for home monitoring to prevent readmissions and maintain quality of life.

The tuberculosis treatment success rate in Indonesia in 2023 did not reach the 90% target. Treatment success impacts the reduction of infection spread and drug resistance cases, making early prediction of treatment success crucial. This study aims to develop a machine-learning model to predict treatment success. Data from Indonesia's Tuberculosis Information System (SITB) cohort was used. The study included productive-age patients (15-64 years) diagnosed with drug-sensitive tuberculosis who received treatment from January 1, 2020, to December 31, 2023. Data was randomly split into training (80%) and testing (20%) sets for model validation, with cross-validation performed. The algorithms used include decision tree, random forest, multilayer perception, extreme gradient boosting, and logistic regression. A consensus was reached for decision-making variables required in performing machine learning-based modeling of SITB data to predict treatment success using modeling of SITB data to predict treatment success using the Delphi method. The results of the study show that the random forest machine learning algorithm had the best performance and highest accuracy in predicting treatment success. This machine learning–based prediction tool can provide early predictions with SHAP (SHapley Additive ExPlanations) interpretation, helping healthcare workers make informed decisions more easily.