Ditemukan 30226 dokumen yang sesuai dengan query :: Simpan CSV
Dua dekade telah berlalu sejak kematian maternal diangkat sebagai isu global, namun hingga kini secara umum, angka kernatian ibu (AKI) di berbagai belahan dunia masih tetap tinggi. Di Indonesia, estimasi AK1 pada tahun 2002/2003 sebesar 307 per 100.000 kelahiran hidup, jauh lebih tinggi dibandingkan negara-negara tetangga seperti Srilanka (58), Thailand (110), dan Malaysia (62). Tingginya AKI hanya menggambarkan sebagian dari masalah kesehatan ibu, Diperkirakan, di luar 529.000 kernatian ibu di dunia, sekitar 9,5 juta perempuan mengalami kesakitan yang berhubungan dengan kehamilan dan 1,4 juta mengalami near-miss/nyaris meninggal. Kesakitan dan kematian ibu menggambarkan masih rendahnya kualitas pelayanan kcsehatan ibu. Berbagai pendekatan dilakukan untuk menilai kualitas pelayanan, salah satunya dengan menghubungkan waktu-waktu tertentu yang berpotensi tenjadi penurunan kualitas pelayanan dengan outcome negatifpasien. Dengan metode kohort retrospektif peneliti menilai pengaruh waktu masuk atau menerima tindakan tcrhadap kejadian komplikasi ohstctrik yang mengancam jiwa. Hasil penelitian menunjukkan bahwa ibu hamil/bersalin/nifas yang masuk atau menerima tindakan di RS pada waktu seputar pergantian shift berisiko 1,75 kali Iebih tinggi mengalami komplikasi obstetrik yang mengancarn jiwa dibandingkan jika masuk atau menerima tindakan pada waktu lainnya (RR 1,75; 95%CI=l,02 - 3,0). Hasil tersebut mengimplikasikan penlingnya evaluasi terhadap pmktck pelayanan kesehatan di RS. Selain itu, selarna periode Desember 2005 - Mei 2006, diketahui rasio kematian ibu terhadap kasus near-miss di RSU Serang dan Pandeglang sebesar 1:11, yang menunjukkan bahwa upaya pencegahan komplikasi obstetrik yang mengancam jiwa dapat menyelamatkan lebih banyak jiwa, dibandingkan jika hanya berfokus pada pencegahan kematian ibu.
Two decades has passed by since maternal mortality being raised as a global issue. But until now, matemal mortality ratio (MMR) in most part of the worlds remains high. In Indonesia, the estimate MMR for 2002/2003 is 307 per 100,000 livebirth, considerably higher that other countries such as Srilanka (58), Thailand (110), and Malaysia (62). The high MMR only reflects a part of matemal health problem. It is estimated that beside 529,000 matemal deaths, there are approximately 9.5 miilon women suffer from pregnancy-related morbidity, and 1,4 million of them survive fiom near-miss. Matemal morbidity and mortality related with the low quality of matemal health care. Various approaches can be used to assess quality of care, one is by relating certain potentially dangerous time, which have the potential of low quality of care, with the negative outcomes of patients. Using retrospective cohort, the effect of time of admission or time receiving definite intervention to the incidence of obstetric life-threatening complication was investigated. The result shows that pregnant/delivery/post partum women who admitted or received definite intervention around the time for handover had 1,75 higher risk to develop obstetric life-threatening complication, compared to admission or receiving intervention at different times (RR 1,75; 95%CI=l,02 - 3,0). The result implies the need for evaluation of the practice of health care delivery in the hospital. Between December 2005 - May 2006, the maternal death to near-miss ration in both hospitals was 1:11, implies the need for prevention of obstetric life-threatening complication which would save more lives, compared to focusing effort only on matemal death.
Latar belakang: Preeklamsia merupakan sindroma kompleks yang timbul pada ibu hamil yang disebabkan oleh perubahan fisiologi pembuluh darah pada saat konsepsi. Dampak kesehatan yang timbul dari kehamilan dengan preeklamsia sangat luas. Sejauh ini berbagai upaya telah ditempuh untuk dapat melakukan prediksi akan terjadinya preeklamsia. Keterbatasan kemampuan statistik mengolah berbagai jenis prediktor saat ini bisa ditingkatkan dengan menggunakan metode machine learning (ML).
Tujuan: Penelitian ini bertujuan untuk melakukan pemodelan prediksi terhadap kejadian preeklamsia menggunakan ML menggunakan fitur yang serupa dengan fitur yang ada di fasyankes primer
Metodologi: Penelitian ini menggunakan disain restrospektif kohort dengan menggunakan data sekunder dari ibu hamil yang melakukan pemeriksaan antenatal di RS Budi Kemuliaan Jakarta yang direkrut pada periode waktu Juli 2012 hingga April 2015 dan diikuti hingga terjadi persalinan. Data tersebut adalah data yang dikumpulkan pada penelitian sebelumnya untuk melihat berbagai faktor risiko dari terjadinya hipertensi dalam kehamilan. Faktor risiko yang diteliti meliputi riwayat diabetes melitus (DM) sebelumnya, riwayat hipertensi sebelumnya, riwayat DM dalam keluarga, riwayat hipertensi dalam keluarga, riwayat merokok, primigraviditas, rerata tekanan arteri (MAP), indeks masa tubuh (BMI) sebelum kehamilan, terhadap kejadian preeklamsia. Permodelan dilakuan dengan menggunakan beberapa model dalam pembelajaran mesin: Random Forest, Logistic Regression, Support Vector Machine (SVM), Decision Tree, dan K-Nearest Neighbour (KKN) untuk mendapatkan model terbaik.
Hasil: Model Suport Vector Machine (SVM) dengan pembelajaran mesin yang disertai dengan re-sampling (undersampling) pada kumpulan data dan perlakuan hyperparameter tuning berhasil mendapatkan akurasi 70,31 %, sensitifitas 67,5 %, spesifisitas 57,23%, dan AUC 0.68.
Kesimpulan: Model SVM menunjukkan kinerja paling baik di antara model prediksi lain pada kumpulan data dan fitur yang tersedia. Model tersebut menghasilkan akurasi 70% dan AUC sebesar 0,68. Model ini mampu mencapai sensitivitas 67,5% dan spesifisitas 57,23%, dengan presisi (positive predictive value) sebesar 74,98%. Artinya, dari seluruh prediksi positif, sekitar 75% adalah benar, sementara sisanya adalah positif palsu. Temuan ini menunjukkan bahwa model prediksi berbasis SVM memiliki potensi untuk dikembangkan lebih lanjut. Optimasi sensitivitas dan spesifisitas menjadi prioritas pada penelitian lanjutan agar model lebih akurat dalam prediksi dan lebih efektif dalam deteksi dini preeklampsia di layanan primer.
Background: Preeclampsia is a complex syndrome that arises in pregnant women caused by physiological changes in blood vessels at the time of conception. The health impacts arising from pregnancy with preeclampsia are widespread. So far, various efforts have been taken to be able to predict the occurrence of preeclampsia. The limitations of statistical ability to process various types of predictors today can be improved by using machine learning (ML) methods.
Objective: This study aims to model predictions for the incidence of preeclampsia using machine learning based on features found in primary health facilities
Methodology: This study uses a cohort retrospective design using secondary data from pregnant women who underwent antenatal care at Budi Kemuliaan Hospital Jakarta who were recruited in the period from July 2012 to April 2015 and followed until delivery. The data was collected in previous studies to look at various risk factors for the occurrence of hypertension in pregnancy. The risk factors studied included history of diabetes mellitus (DM), history of hypertension, a family history of DM, a family history of hypertension, a history of smoking, primigravidity, mean arterial pressure (MAP), body mass index (BMI) before pregnancy, and the incidence of preeclampsia. The modeling was carried out using several models in machine learning: Random Forest, Logistic Regression, Support Vector Machine (SVM), Decision Tree, and K-Nearest Neighbour (KKN) to get the best model.
Results: The Support Vector Machine (SVM) model with machine learning accompanied by re-sampling (undersampling) on the dataset and hyperparameter tuning treatment managed to obtain an accuracy of 70.31%, sensitivity of 67.5%, specificity of 57.23%, and AUC of 0.68.
Conclusion: The SVM model shows the best performance among other prediction models for the available datasets and features. The model produces 70% accuracy and an AUC of 0.68. This model was able to achieve sensitivity of 67.5% and specificity of 57.23%, with a precision of 74.98% which provide the positive predictions about 75% are true, while the rest are false positives. These findings suggest that SVM prediction models have the potential to be further developed. Sensitivity and specificity optimization are priorities in further research to achieve a more robust model with optimum accuracy to predict preeclampsia and more effective in early detection of preeclampsia in primary care.
Kata kunci: Faktor Risiko; Hipertensi Derajat 1; Suku Bali; Suku Banjar
In 2010, hypertension was one of the risk factors for death globally and it estimated to have caused 9.4 million deaths. In Indonesia, based on data from IFLS 5, in 2014 the prevalence of hypertension stage 1 at the age of ≥18 years was 15.59%. The majority of Banjar Ethnic who are domiciled in South Kalimantan (65%) have the potential to suffer from hypertension stage 1 with reference to the Riskesdas 2013 which has a prevalence of hypertension of 30.8%. The prevalence of hypertension in Bali Province is 19.9%, which is occupied by the majority of the Bali Ethnic (84%). This difference in prevalence encouraged researchers to find out the differences in risk factors for hypertension stage 1 in the Banjar and Bali Ethnic. This study used a cross sectional design. Data from IFLS 5 in 2014. A total of 765 respondents from the Banjar ethnic and 1,087 respondents from the Bali ethnic aged ≥18 years were sampled in this study. Data were analyzed using cox regression test. Prevalence hypertension stage 1 in Banjar Ethnic and Bali Ethnic are 17,3% and 10,8%, respectively. Risk factors of hypertension stage 1 in Banjar Etnic are obesity (PR=2,726; 95%CI; 1,913-3,886), age ≥45 years (PR=2,146; 95%CI;1,482- 3,107) and male (PR=1,641; 95%CI;1,149-2,344). Risk factors of hypertension stage 1 in Bali Ethnic are obesity (PR=2,971; 95%CI;2,025-4,362), age ≥45 years (PR=2,144; 95%CI;1,465-3,136), male (PR=1,985; 95%CI;1,341-2,938), low education (PR=1,585; 95%CI;1,076-2,334) and urban (PR=1,525; 95%CI;1,051-2,212). The need for optimization of prevention and early detection activities to reduce the prevalence of hypertension in the Banjar and Bali Ethnic.
Key words: Banjar Ethnic; Bali Ethnic; Hypertension Stage 1; Risk Factors
