Search Result  ::  Save as CSV :: Back

"Perencanaan klinis untuk pengobatan radioterapi memainkan peran krusial dalam memaksimalkan manfaat pemberian radiasi terapi dan menjamin keselamatan pasien. Pada penelitian ini 60 data treatment planning intensity-modulated radiation therapy (IMRT) dari Rumah Sakit MRCCC Siloam Hospital digunakan dalam model pembelajaran machine learning dengan menggunakan algoritma random forest. Data perencanaan radioterapi berupa radiomic dan dosiomic yang telah dinormalisasi diteliti dengan model algorimta random forest. Hasil evaluasi penelitian menunjukkan model random forest dapat memprediksi distribusi dosis pada kasus kanker paru dengan Mean Squared Error (MSE) sebesar 0,0214. Nilai Homogeneity Index (HI) dan Conformity Index (CI) pada hasil prediksi model random forest adalah 0,087±0,004 dan 0,983±0,003 secara berturut-turut, sementara dari perencanaan klinik diperoleh 0,082±0,025 dan 0,978±0,037 dengan nilai p-value pada PTV and OAR > 0,05 yang menunjukkan bahwa model random forest efektif dan mimiliki performa yang baik dalam memprediksi dosis pada PTV dan OAR pada kasus kanker paru.

---

Clinical planning for radiotherapy treatment plays a crucial role in maximizing the benefits of radiation therapy and ensuring patient safety. In this study, 60 intensity-modulated radiation therapy (IMRT) treatment planning data from MRCCC Siloam Hospital were used in a machine learning model using the random forest algorithm. Radioteraphy treatment plan data, radiomic and dosiomic, are normalized and to be learned by random forest model algorithm. Model evaluation results showed that dose distribution predicted by random forest model had a Mean Squared Error (MSE) of 0.0214. Homogeneity Index (HI) and Conformity Index (CI) values for predicted results were 0.087±0.004 and 0.983±0.003, respectively, while the clinical data were 0,082±0,025 and 0,978±0,037, with p-values for PTV and OAR > 0.05, which concludes that random forest model had a good performance and were effective in lung cancer PTV and OAR dose prediction.

"

"Integrative therapies in lung health and sleep provides an overview of integrative therapies to assist clinicians caring for patients with acute or chronic lung diseases and sleep disorders--emphasizing the scientific bases for these therapies; and their implementation into clinical practice. This volume focuses on complementary and alternative medicine (CAM) treatments, modalities, and practices that are integrated with conventional medical treatment and for which there is some evidence of safety and efficacy. Whole medical systems, with a specific focus on traditional Chinese medicine , are also addressed. Individual chapters are devoted to specific health conditions or illnesses, addressing the current state of the science in the four organizing CAM domains, including available information regarding benefits, risks, or safety considerations. Unique aspects of this volume are the chapters related to evaluation of the evidence base for integrative therapies, new animal model research with herbal preparations focused on the serious problem of sepsis in the ICU, guidance for counseling patients with chronic lung illnesses who may be desperate for a cure; and palliative and end-of-life care for patients with chronic lung conditions. "