Hasil Pencarian  ::  Simpan CSV :: Kembali

"Dalam dua tahun terakhir pandemi corona virus disease 2019 (COVID-19) telah menginfeksi > 220 juta orang dan 5 juta orang meninggal. Di Indonesia > 4 juta orang terinfeksi dan > 140.000 orang meninggal. Pada puncak pandemi, kebutuhan perawatan tidak seimbang dengan sarana rumah sakit sehingga WHO menganjurkan untuk memprioritaskan pasien secara ekual. Untuk itu diperlukan prediktor luaran pasien COVID-19. Penelitian ini bertujuan menyusun prediktor luaran pasien COVID-19 menggunakan regresi logistik dan machine learning.Penelitian terdiri atas 2 tahap. Tahap pertama adalah kohort retrospektif untuk menyusun prediktor kematian di rumah sakit dengan regresi logistik dan machine learning (decision tree, random forest, support vectore machine, gradient boost and extreme gradient boost). Pasien terkonfirmasi COVID-19 diinput di data registri REG-COVID-19 pada bulan Maret–Juli 2020 di RS Persahabatan (RSP) dan RS Universitas Indonesia (RSUI). Tahap kedua adalah kohort prospektif pada pasien COVID-19 di RSP, RSUI dan RSPI Suliati Saroso pada bulan Maret–Mei 2021. Data yang diinput adalah data demografi, gejala klinis, komorbid, laboratorium, skor Brixia dari radiografi toraks, luaran pasien dari perawatan dan lama rawat.Pada tahap penyusunan diperoleh 271 subjek untuk analisis machine learning, 239 subjek untuk model 1, sebanyak 180 subjek model 2, dan 152 subjek model 3 dan model 4. Hasil analisis regresi logistik model 1 terdiri atas 7 variabel yaitu demam, diabetes melitus, frekuensi napas, saturasi O2, leukosit, SGOT dan CRP dengan AUC 0,930. Model 2 memberikan hasil hampir sama tetapi SGOT menjadi SGPT dengan AUC 0,926. Model 3 memiliki AUC 0,919 dan model 4 memberikan AUC 0,924 dengan variabel D dimer > 2000 menjadi salah satu prediktor. Validasi semua model regresi logistik dan machine learning menunjukkan penurunan AUC, tetapi tidak berbeda bermakna (uji perbandingan AUC, p = 0,683–0,736). Perbandingan model regresi logistik dan machine learning juga tidak berbeda bermakna (uji perbandingan AUC dengan rumus Hanley, p = 0,492–0,923).Disimpulkan prediksi kematian pasien COVID-19 menggunakan regresi logistik dan machine learning memiliki akurasi yang baik sehingga regresi logistik dan machine learning dapat dijadikan prediktor luaran pasien COVID-19.......Corona virus disease 2019 (COVID-19) pandemic has lasted almost 2 years worldwide with more than two hundred million world population were infected and almost 5 million (2%) death. In Indonesia, there have been more than 4 million people were infected with more than 140.000 (3.5%) death. At the peak of the outbreak there were discrepancy between health care facilities and demands. WHO recommended to prioritize patient equally, to avoid patient discrimination by social class, race, and gender. The best prediction tool should be valid, reliable and feasible. Many studies develop assessment with logistic regression and machine learning with the goal to improve accuracy. Some study showed variety of predictors in outcome prediction, in this study we developed and validated assessment tool to predict hospital mortality comparing logistic regression and machine learning, included support vector machine (SVM), decision tree (DT), random forest (RF), gradient boost (GB) and extreme gradient boost (XGB). Our study was conducted in 2 stages. The first stage study was cohort retrospective to develop assessment tool to predict hospital mortality by comparing logistic regression and machine learning among hospitalized COVID-19 patients from March to July 2020. The second was cohort prospective study among the same population, to validate the tools. The development data were collected from Persahabatan hospital and Universitas Indonesia hospital who registered in REG-COVID-19, 271subjects were eligible for machine learning analysis and 239 subjects for logistic regression data set 1; 180 subjects for data set 2; 152 for data set 3 and 4. Analysis of data set 1 resulted in 8 variables as mortality prediction include fever, DM, respiratory rate (RR), oxygen saturation, leucocyte, ALT > 42, CRP > 88, with AUC 0,930. Data set 2 resulted in similar variables except AST, with AUC 0,926. Data set 3 resulted in 6 variables with AUC 0,919 and Data set 4 resulted in 7 variables included fever, HR, RR, leucocyte, age above 52, CRP > 86 and D-dimer > 2000 with AUC 0,924. Validation of all models showed decreasing AUC. Machine learning analysis resulted in 5 models with the best was XGB among all set data with AUC between 0,8–0,9. There were decreasing of AUC of all models, but not statistically different (p 0.683–0.736). Comparing developed models with logistic regression and machine learning showed there were differences but not statistically significant. (p 0.492-0.923)"

"Introduksi:Untuk menilai apakah kadar defisit basa inisial dapat menjadi prediktor mortalitas di UPIPasien dan metode:Studi retrospektif selama periode November 2004 sampai Oktober 2005 yang dilakukan di UPI medis-bedah. Data diarnbil dari rekam medik: defisit basa dan variabel untuk skor SAPS II serta dinilai keluaran pasien (mati atau hidup). Kurva Receiver Operating dibuat, titik potong optimal ditentukan dan dinilai prognostik dari defisit basa inisial dan SAPS II. Koefisien Pearson digunakan untuk menilai hubungan antara defisit basa inisial dan skor SAPS U.Hasil:Dui 456 pasien yang dievaluasi, 40 pasien (9,4%) meninggal di UPI. Kelompok survivor memiliki rerata defisit basa inisial yang lebih rendah dibandingkan kelompok nonsurvivor. Terdapat perbedaan yang bermakna antara defisit basa inisial dengan mortalitas UPI (p=0,000). Titik potong ditetapkan pada -4,2 mmolll. Analisa ROC menunjukkan defisit basa inisial (AUC=0,711) lebih buruk dibandingkan skor SAPS II (AUC=0,98) sebagai prediktor mortalitas_ Terdapat hubungan yang lemah antara defisit basa inisial dan skor SAPS II.Kesimpulan:Defisit basa inisial dan skor SAPS II yang tinggi secara independen berhubungan dengan peningkatan mortalitas di UPI RSCM.

---

Introduction :

To examine initial base deficit could be used as a predictor of mortality in ICU

Patients & methods:

A retrospective study over a period from November 2004 until Oktober2005 was conducted in a medical-surgical ICU. Data were extracted from ICU medical records: the base deficits and variables for SAPS II score and also the outcome of those patients (survivor or nonsurvivor). Receiver Operating Curve were constructed, the optimal cut offpoint have been obtained and area under curve was used to asses the prognostic value of initial base deficit and SAPS IL The coefficient of Pearson were analyzed to asses the relation between initial base deficit and SAPS II score.

Main outcome:

Of the 456 evaluable patients, 40 patients (9,4%),were died in ICU Survivor had lower mean of initial base deficit than nonsurvivor. There are a significant differences between initial base deficit and ICU mortality (p= 0, 000). The cut off point was obtained at -4,2 mmol II. ROC analysis demonstrated that initial base deficit (AUC=O, 711) is worsen than SAPS II Score (A UC=0, 98) as predictor mortality. There is a weak correlation between initial base deficit and SAPS II score.

Conclusion:

A high initial base deficit and SAPS II score are independently associated with increased ICU mortality in Cipto Mangunkusumo Central Hospital."

"ABSTRAKLatar Belakang. Terdapat gangguan sistem imun pada sepsis. Fase awal ditandaidengan hiperinflamasi, sedangkan fase lanjut ditandai dengan imunosupresi.Kematian kumulatif lebih banyak pada fase lanjut. Saat ini belum terdapatpenelitian yang secara khusus meneliti faktor prognostik mortalitas sepsis faselanjut dan mengembangkan model prediksi mortalitasnya.Tujuan. Mengetahui faktor prognostik mortalitas sepsis berat fase lanjut di ICUdan mengembangkan sistem skor untuk memprediksi mortalitas.Metode. Penelitian kohort retrospektif dilakukan pada pasien dewasa yangmengalami sepsis berat di ICU RSCM pada periode Oktober 2011 – November2012 dan masih bertahan setelah > 72 jam diagnosis sepsis ditegakkan di ICU.Tujuh faktor prognostik diidentifikasi saat diagnosis sepsis berat ditegakkan diICU. Prediktor independen diidentifikasi dengan analisis Cox’s proportionalhazard. Prediktor yang bermakna secara statistik dikuantifikasi dalam modelprediksi. Kalibrasi model dinilai dengan uji Hosmer-Lemeshow dan kemampuandiskriminasi dinilai dari area under curve (AUC) dari receiver operating curve.Hasil. Subjek penelitian terdiri atas 220 pasien. Mortalitas 28 hari sepsis beratfase lanjut adalah 40%. Faktor prognostik yang bermakna adalah alasan masukICU (medis (HR 2,75; IK95%:1,56-4,84), pembedahan emergensi (HR 1,96;IK95%:0,99 – 3,90), indeks komorbiditas Charlson > 2 (HR 2,07; IK95%:1,32-3,23), dan skor MSOFA > 4 (HR 2,84; IK95%:1,54-5,24). Model prediksimemiliki kemampuan diskriminasi yang baik (AUC 0,844) dan kalibrasi yangbaik (uji Hosmer-Lemeshow p 0,674). Berdasarkan model tersebut risikomortalitas dapat dibagi menjadi rendah (skor 0, mortalitas 5,4%), sedang (skor 1 –2,5, mortalitas 20,6%), dan tinggi (skor > 2,5, mortalitas 73,6%).Simpulan. Alasan masuk medis dan pembedahan emergensi, indeks komorbiditasCharlson > 2, dan skor MSOFA > 4 merupakan faktor prognostik mortalitassepsis berat fase lanjut di ICU RSCM. Sebuah model telah dikembangkan untukmemprediksi dan mengklasifikasikan risiko mortalitas.

---

ABSTRACTBackground. Immune system derrangement occurs during the course of sepsis,characterized by hyperinflamation in early phase and hypoinflamation andimmunosupression in late phase. The number of patient die during late phase islarger than early phase. Until now, there is no study specifically addressingprognostic factors of mortality from late sepsis and developing a mortalityprediction model.Aim. To determine prognostic factors of mortality from late phase of severesepsis in ICU and to develop scoring system to predict mortality.Method. A retrospective cohort study was conducted to identify prognosticfactors associated with mortality. Adult patients admitted to ICU duringNovember 2011 until October 2012 who developed severe sepsis and still alivefor minimum 72 hours were included in this study. Seven predefined prognosticfactors were indentified at the onset of severe sepsis in ICU. Cox’s proportionalhazard ratio was used to identify independent prognostic factors. Eachindependent factors was quantified to develop a prediction model. Calibration ofthe model was tested by Hosmer-Lemeshow, and its discrimination ability wascalculated from area under receiver operating curve.Result. Subjects consist of 220 patients. Twenty eight-day mortality was 40%.Significant prognostic factors indentified were admission source (medical (HR2.75; CI95%: 1.56 – 4.84), emergency surgery (HR 1.96; CI95%:0.99 – 3.90),Charlson comorbidity index > 2(HR 2.07; CI95%:1.32 – 3.23), and MSOFA score> 4 (HR 2.84; CI95% : 1.54 – 5.24). Prediction model developed has gooddiscrimination ability (AUC 0.844) and good calibration (Hosmer-Lemeshow testp 0.674). Based on the model mortality risk can be classified as low (score 0,mortality 5.4%), moderate (score 1 – 2.5, mortality 20.6%), and high (score > 2.5,mortality 73.6%).Conclusion. Medical and emergency surgery admission, Charlson comorbidityindex > 2, and MSOFA score > 4 were prognostic factors of mortality from latephase of severe sepsis in ICU at Dr.Cipto Mangunkusumo general hospital. Amodel has been developed to predict and classify mortality risk."