Salam, rekan Nawala! Semoga kalian selalu dalam keadaan sehat.
Ini adalah IAES Nawala dari Institute of Advanced Engineering and Science. Hari ini kami akan berbagi kabar mengenai peran AI di dunia kesehatan. Penggunaan kecerdasan buatan (artificial intelligence, AI) dalam pelayanan kesehatan diantaranya untuk mengurangi risiko keterlambatan pelayanan kesehatan primer, sekunder, maupun tersier. Apio dkk. (2023) meninjau 22 artikel yang mencakup studi retrospektif, prospektif, dan studi kasus-kontrol. Ditemukan bahwa AI memiliki potensi untuk meningkatkan kepuasan pasien dengan mengurangi waktu tunggu dan mendukung sistem perawatan kesehatan. Namun, penelitian lebih lanjut diperlukan untuk memvalidasi bukti yang ada dan memahami bagaimana AI dapat meningkatkan kesembuhan pasien. Meskipun demikian, penggunaan AI dalam perawatan kesehatan menunjukkan harapan dalam memberikan pelayanan menjadi lebih baik.
A systematic review of artificial intelligence-based methods in healthcare
Anthony Lirase Apio, Jonathan Kissi, Emmanuel Kusi Achampong
Artificial intelligence (AI) in healthcare has enormous potential for transforming healthcare. AI is the ability of machines to learn and exhibit close to human levels of cognition in various specific ways. Leveraging AI software to support activities will improve patient satisfaction which is inextricably tied to the length of time patients spend in waiting queues. Literature searches were conducted in PubMed, Research Gate, BMC Health Services Research, JMIR Publications and Cochrane Central to find related documentation that was published between January 2011 and April 2021. The studies featured and reported on AI technologies that had been used in primary, secondary, or tertiary healthcare situations directed towards reducing waiting times. A total of 22 articles were primarily used, including 8 retrospective studies, 4 prospective studies and 3 case-control studies. AI technologies have enormous potential in the creation of a future with more reliable healthcare systems. It is however clear that more studies in the field are required to validate the existing evidence of its potential. AI in healthcare is crucial to reducing patients’ time at healthcare facilities. The use of AI can also help improve patient outcomes and more research should be geared toward that.
Danuaji dkk. (2023) melakukan sebuah penelitian di RSUD dr. Moewardi di Surakarta, Indonesia. Mereka mengembangkan kerangka kerja AI yang dapat membantu menjadi asisten dokter dengan melakukan screening awal dalam menilai risiko penyakit serebrovaskular. AI dapat mengukur ketebalan media intima karotis dengan akurat dari gambar ultrasonografi. Hasil penelitian yang didapatkan menunjukkan bahwa hasil screening dari AI ini valid dan dapat diandalkan dalam menilai risiko penyakit serebrovaskular yang terkait dengan plak karotis.
Rivan Danuaji, Subandi Subandi, Stefanus Erdana Putra, Muhammad Hafizhan
Carotid plaque is a biomarker of generalized atherosclerosis, and may predict ischemic stroke. Carotid intima-media thickness (C-IMT) measurement with ultrasonography imaging could capture the condition of carotid plaque. However, manual measurement of C-IMT is observer- dependent, resulting in observer bias and low reproducibility. In this study, we develop artificial intelligence (AI) framework that could automatically measure the C-IMT, and compared it with C-IMT measured by board of expert. This is a retrospective study done in Dr. Moewardi General Hospital, Surakarta, Indonesia. Carotid B-mode ultrasonography images were measured by panel of expert and by AI. After annotation process on Neurabot platform, AI could detect region of interest (ROI), and would do segmentation on the area to measure C-IMT autonomously. Dependent T-test was used to evaluate validity, and Cronbach’s alpha was used to find the reliability of C-IMT measured by panel of expert and AI. There was strong correlation (r=0.874; p=0.014) on dependent t-test for C-IMT measured by AI with C-IMT measured by board of expert. The internal consistency reliability coefficients (Cronbach’s alpha) were 0.938 and 0.909, for pretest and posttest, respectively. We also analyzed the test-retest reliability by comparing pretest and posttest score with dependent t-test, and we observed strong correlation with r=0.871 (p=0.000). AI developed on Neurabot platform are valid and reliable to measure C-IMT.
Pada penelitian lain, Sohaib dan Adewunmi (2023) mengembangkan model AI untuk mendeteksi kanker paru-paru pada tahap awal dengan akurasi tinggi menggunakan deep learning berbasis ANN. Model ini berhasil mencapai akurasi 94% dan tingkat kerugian minimum 0,1%. Model yang dikembangkan dapat mengidentifikasi beberapa faktor risiko kanker paru-paru, seperti karsinoma sel skuamosa, adenokarsinoma, dan karsinoma sel besar. Temuan ini menunjukkan bahwa pendekatan kecerdasan buatan (AI) dapat secara efektif mengidentifikasi dan memprediksi faktor-faktor risiko kanker paru-paru.
Artificial intelligence based prediction on lung cancer risk factors using deep learning
Muhammad Sohaib, Mary Adewunmi
In this proposed work, we identified the significant research issues on lung cancer risk factors. Capturing and defining symptoms at an early stage is one of the most difficult phases for patients. Based on the history of patients records, we reviewed a number of current research studies on lung cancer and its various stages. We identified that lung cancer is one of the significant research issues in predicting the early stages of cancer disease. This research aimed to develop a model that can detect lung cancer with a remarkably high level of accuracy using the deep learning approach (convolution neural network). This method considers and resolves significant gaps in previous studies. We compare the accuracy levels and loss values of our model with VGG16, InceptionV3, and Resnet50. We found that our model achieved an accuracy of 94% and a minimum loss of 0.1%. Hence physicians can use our convolution neural network models for predicting lung cancer risk factors in the real world. Moreover, this investigation reveals that squamous cell carcinoma, normal, adenocarcinoma, and large cell carcinoma are the most significant risk factors. In addition, the remaining attributes are also crucial for achieving the best performance.
Beberapa artikel di atas merupakan bagian kecil dari penelitian mengenai peran AI di dunia kesehatan. Untuk mendapatkan informasi lebih lanjut, pembaca dapat mengunjungi laman dan membaca artikel secara GRATIS melalui tautan-tautan berikut: https://ijphs.iaescore.com/ dan https://ijict.iaescore.com/.
Redaksi: I. Busthomi
