人工智慧為近年相當熱門之領域，推測將影響各領域之產業發展，在生醫界，儘管人工智慧尚未在產業發揮其實質影響力，但從研究發展上，已經能夠一窺人工智慧對於生醫未來之發展潛力，除了IBM與Google等人工智慧領頭羊已經發表在生醫界的服務項目，目前以人工智慧結合生醫之運用為核心技術的新創公司則少之又少，本研究是以生醫資料庫內的人工智慧相關研發數量做分析，採集與人工智慧相關之議題，了解這些議題是使用什麼人工智慧演算法，如何使用這些演算法，同時將所有與人工智慧相關之議題進行次分類為影像辨識類、臨床數據分析類、DNA序列分析類、脈波訊號判讀類、藥物資料庫分析類及臨床文字分析類，其中以影像辨識為成熟之分類定且大量使用卷積式類神經網絡，其次為臨床數據分析類偏向使用一般的深度類神經網絡，另外DNA序列分析類之研發常常會使用到循環類神經網絡，這些的發展案例未來勢必將對產業之上中下游發生一定之影響力，並且具備協助產業人員更快速與更正確之完成工作，人工智慧雖然在生醫產業起步較慢，且目前發揮之實質效益仍低，但經由本研究可以看出人工智慧在研發階段的數量正快速增加，並有望在未來產生其效益。

Artificial Intelligence is a very popular field in recent years, and it is expected to affect several industries. In the biomedical field, although artificial intelligence has not yet displayed its substantial influence, from the perspective of research and development, it has been possible to find artificial intelligence’s potential for the future. Some industry leaders such as IBM and Google have launched their medical services sectors using the artificial intelligence, but few start-up biotechnology companies have combined artificial intelligence with the use of biomedical technology as the core technology. This research is to analyze the present biomedical database to evaluate the impact of the artificial intelligence on the field to this day. It collects the cases using artificial intelligence, tries to understand what algorithms are used for these topics, and how to use them. According to the result of this research, all subjects were sub-categorized into 6 fields, which are: image identification, clinical data analysis, DNA sequence analysis, pulse wave signal interpretation, drug database analysis, and clinical text analysis. Among them, the use of convolutional neural networks in the classification of image recognition has been the most well developed application, followed by the use of artificial neural networks for clinical data analysis. Otherwise, the cases regarding DNA sequence analysis often use recurrent neural networks. These fundamental cases are driving the industry in midstream and downstream, and prove the artificial intelligence can assist more and more people in the industry to completing their work quickly and accurately. Although artificial intelligence still develops slowly in the biomedical industry, as well as it only plays a very low substantial role so far, we can see from this study that the number of cases using artificial intelligence in R&D is increasing rapidly and the artificial intelligence is expected to bring benefits in the future.

Acharya UR, O. S., Hagiwara Y, Tan JH, Adam M, Gertych A, Tan RS (2017). "A deep convolutional neural network model to classify heartbeats." Comput Biol Med.89: 389-396.

Alipanahi B, D. A., Weirauch MT, Frey BJ (2015). "Predicting the sequence specificities of DNA-and RNA-binding proteins by deep learning." Nat Biotechnol33(8): 831-838.

Angermueller C, P. T., Parts L, Stegle O (2016). "Deep learning for computational biology." Mol Syst Biol.12(7).

Arthur, J. (2016). "Simple Reinforcement Learning with Tensorflow Part 8: Asynchronous Actor-Critic Agents (A3C)." from https://medium.com/emergent-future/simple-reinforcement-learning-with-tensorflow-part-8-asynchronous-actor-critic-agents-a3c-c88f72a5e9f2.

Atzori M, C. M., Müller H (2016). "Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands." Front Neurorobot.10.

Chen H, E. O., Wang Y, Olivecrona M, Blaschke T (2018). "The rise of deep learning in drug discovery." Drug Discov Today.17: S1359-6446.

Cleophas, T. J., Zwinderman, Aeilko H. (2015). Machine Learning in Medicine. Cookbook.

Columbus, L. (2018). "10 Ways Machine Learning Is Revolutionizing Manufacturing In 2018." from https://www.forbes.com/sites/louiscolumbus/2018/03/11/10-ways-machine-learning-is-revolutionizing-manufacturing-in-2018/#5a95ee6623ac.

Dürr O, S. B. (2016). "Single-Cell Phenotype Classification Using Deep Convolutional Neural Networks." J Biomol Screen.21(9): 998-1003.

Edelman RR, W. S. (1993). "Magnetic resonance imaging " N Engl J Med.328(10): 708-716.

El Naqa, I., Li, Ruijiang, Murphy, Martin J (2015). Machine learning in radiation oncology.

EvaluatePharma (2017). World Preview 2017, Outlook to 2022.

Ferrucci D, B. E., Chu-Carroll J (2010). "Building Watson: an overview of the DeepQA project." AI Magazine31(3): 59-79.

Flaumenhaft Y, B.-A. O. (2018). "Personal health records, global policy and regulation review." Health Policy.: pii: S0168-8510(0118)30132-30135.

Han H, J. X. (2014). "Overcome support vector machine diagnosis overfitting." 13(Suppl 1): 145-158.

Hassanien, A.-E., Grosan, Crina, Tolba, Mohamed F (2016). Applications of Intelligent Optimization in Biology and Medicine.

Havaei M, D. A., Warde-Farley D (2015). "Brain tumor segmentation with deep neural networks." arXiv Preprint1505(03540).

Hay M., T. D., John L, Craighead J.L., Economides C., Rosenthal, J. (2014). "Clinical development success rates for investigational drugs." Nature Biotechnology32: 40-51.

Heikamp K, B. J. (2014). "Support vector machines for drug discovery." Expert Opin Drug Discov.9(1): 93-104.

Hochreiter S, H. M., Obermayer K. (2007). "Fast model-based protein homology detection without alignment." Bioinformatics.23(14): 1728-1736.

Holger R. Roth, L. L., Senior Member, Jiamin Liu, Jianhua Yao, Ari Seff, Kevin Cherry, Lauren Kim, Ronald M. Summers (2015). "Improving computer-aided detection using convolutional neural networks and random view aggregation." arXiv Preprint arXiv1505(03046).

Holzinger, A. (2016). Machine Learning for Health Informatics.

Hsieh J (2009). Computed tomography: principles, design, artifacts, and recent advances. . SPIE Bellingham, WA, 2009.

Huang S, C. N., Pacheco PP, Narrandes S, Wang Y, Xu W (2018). "Applications of Support Vector Machine (SVM) Learning in Cancer Genomics." Cancer Genomics Proteomics15(1): 41-51.

Ishita Bhakta, A. S. (2016). "Prediction of Depression among Senior Citizens using Machine Learning Classifiers." International Journal of Computer Applications144(7): 11-16.

Kumar, N. (2017). "How AI Will Invade Every Corner of Wall Street." from https://www.bloomberg.com/news/features/2017-12-05/how-ai-will-invade-every-corner-of-wall-street.

Kurenkov, A. (2016). "A brief history of game AI." from http://www.andreykurenkov.com/writing/ai/a-brief-history-of-game-ai/.

Lee B, L. T., Na B, Yoon S. (2016). "DNA-Level Splice Junction Prediction using Deep Recurrent Neural Networks." arXiv Preprint1603: 09123.

Lee JG, J. S., Cho YW, Lee H, Kim GB, Seo JB, Kim N (2017). "Deep Learning in Medical Imaging: General Overview " Korean J Radiol.18(4): 570-584.

Lenselink EB, T. D. N., Bongers B, Papadatos G, van Vlijmen HWT, Kowalczyk W, IJzerman AP, van Westen GJP (2017). "Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set." J Cheminform.9(1).

Lohr, S. (2017). "A.I. Is Doing Legal Work. But It Won’t Replace Lawyers, Yet." from https://www.nytimes.com/2017/03/19/technology/lawyers-artificial-intelligence.html.

Min S, L. B., Yoon S (2017). "Deep learning in bioinformatics." Brief Bioinform.18(5): 851-869.

Miyoshi F, H. K., Minota S, Okada M, Ogawa N, Mimura T (2016). "A novel method predicting clinical response using only background clinical data in RA patients before treatment with infliximab." Mod Rheumatol.26(6): 813-816.

Murnane, K. (2016). "Thirteen companies that use deep learning to produce actionable results.". from https://www.forbes.com/sites/kevinmurnane/2016/04/01/thirteen-companies-that-use-deep-learning-to-produce-actionable-results/#4214de8633b8.

NIH. "The Cost of Sequencing a Human Genome." from https://www.genome.gov/27565109/the-cost-of-sequencing-a-human-genome.

Ning F, D. D., LeCun Y (2005). "Toward automatic phenotyping of developing embryos from videos. ." IEEE Trans Image Process14(9): 1360-1371.

Nvidia. "Long Short-Term Memory (LSTM)." from https://developer.nvidia.com/discover/lstm.

Olivecrona M, B. T., Engkvist O, Chen H. (2017). "Molecular de-novo design through deep reinforcement learning." J Cheminform.9(1).

Ortiz-Catalan M, G. R., Kristoffersen MB, Zepeda-Echavarria A, Caine-Winterberger K, Kulbacka-Ortiz K, Widehammar C, Eriksson K, Stockselius A, Ragnö C, Pihlar Z, Burger H, Hermansson L (2016). "Phantom motor execution facilitated by machine learning and augmented reality as treatment for phantom limb pain: a single group, clinical trial in patients with chronic intractable phantom limb pain." Lancet.388(10062): 2885-2894.

Plis SM, H. D., Salakhutdinov R, Allen EA, Bockholt HJ, Long JD, Johnson HJ, Paulsen JS, Turner JA, Calhoun VD (2014). "Deep learning for neuroimaging: a validation study." Front Neurosci.8.

Sønderby SK, S. C., Nielsen H (2015). "Convolutional LSTM networks for subcellular localization of proteins." arXiv Preprint1503(01919).

Sau A, B. I. (2014). "Artificial Neural Network (ANN) Model to Predict Depression among Geriatric Population at a Slum in Kolkata, India." J Clin Diagn Res.11(5): VC01-VC04.

Siegismund D, T. V., Heyse S1, Sick B, Duerr O, Steigele S. (2018). "Developing Deep Learning Applications for Life Science and Pharma Industry." Drug Res (Stuttg).68(6): 305-310.

Tortajada S, G.-G. J., Vicente J, Sanjuán J, de Frutos R, Martín-Santos R, García-Esteve L, Gornemann I, Gutiérrez-Zotes A, Canellas F, Carracedo A, Gratacos M, Guillamat R, Baca-García E, Robles M. (2009). "Prediction of postpartum depression using multilayer perceptrons and pruning." Methods Inf Med.48(3): 291-298.

Touchman, J. (2010). "Comparison of whole genome sequences provides a highly detailed view of how organisms are related to each other at the genetic level. How are genomes compared and what can these findings tell us about how the overall structure of genes and genomes have evolved?". from https://www.nature.com/scitable/knowledge/library/comparative-genomics-13239404.

Ypsilantis PP, S. M., Sohn HM, Davies A, Cook G, Goh V, Montana G. (2015). "Predicting Response to Neoadjuvant Chemotherapy with PET Imaging Using Convolutional Neural Networks." PLoS One.10(9).

Zhou J, T. O. (2015). "Predicting effects of noncoding variants with deep learning-based sequence model." Nat Methods.12(10): 931-934.