Machine Learning 資訊 | 基於深度學習識別姑息治療患者

「Hiring a Machine Learning engineer or Data Scientist in Silicon Valley is becoming like hiring a professional athlete. That’s how demanding it is」 — The New York Times

基於深度學習識別姑息治療患者

Stanford ML Group 創建了一個使用深度學習算法的程序，根據電子健康記錄（Electronic Health Record ，EHR，包括病歷、心電圖、醫療影像等信息）數據肯定在將來3-12個月高風險死亡的住院患者。這些病人的預警信息將發送給姑息治療小組，這有助於姑息護理小組儘早介入、提供服務。

姑息治療（Palliative Care ，在日本、中國臺灣翻譯爲舒緩醫學）起源於 hospice運動，最先起源於公元四世紀。根據世界衛生組織的定義，姑息治療強調控制疼痛及患者有關症狀，並對心理、社會和精神問題予以重視，目的是爲病人和家眷贏得最好的生活質量。

預測模型是一個 18 層的深度神經網絡，輸入參數爲一個病人的 EHR 數據，輸出爲將來 3-12 個月死亡的機率。訓練數據採用斯坦福醫院 EHR 數據庫中的歷史數據，包含超過 200 萬名患者的數據。EHR 數據包括患者過去 12 個月的診斷結論、治療程序、處方和相關細節（通過脫敏和技術處理，以替代碼的形式表示），全部數據被轉換成 13654 維的特徵向量。訓練好的模型 AUROC 評分達到 0.93 ，交叉驗證的平均精度爲0.69 分。

對於機器學習系統來講，使用戶能夠根據預測結果採起行動，須要提供預測結果的詳細解釋，這點對於創建用戶信心相當重要。Stanford 的程序能夠自動生成一個報告，在病人的 EHR 數據中高亮突出對於預測結果具備重要影響因子的條目。

分類

• 圖像處理 Image Manipulation
• 風格轉換 Style Transfer
• 圖像分類 Image Classification
• 臉部識別 Face Recognition
• 視頻穩定化 Video Stabilization
• 目標檢測 Object Detection
• 自動駕駛汽車 Self Driving Car
• 智能推薦 Recommendation Al
• 智能遊戲 Gaming Al
• 智能下棋 Chess Al
• 智能醫學 Medical Al
• 智能演說 Speech Al
• 智能音樂 Music Al
• 天然語言處理 Natural Language Processing
• 智能預測 Prediction

Mybridge AI 在 20000 篇關於建立機器學習應用的文章中挑選了前 50 名。從有實踐經驗的數據科學家那裏學習是一個好方法，咱們能夠的分享中得到構建、運營機器學習應用的經驗教訓。50 篇文章大體能夠分爲 15 個主題，以下所示：

Recommended Learning

• The Beginner’s Guide to Building an Artificial Intelligence in Unity.
• Deep Learning and Computer Vision A-Z™: Learn OpenCV, SSD & GANs and create image recognition apps.

圖像處理 Image Manipulation

• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
• Using Deep Learning to Create Professional-Level Photographs
• High Dynamic Range (HDR) Imaging using OpenCV (Python)

風格轉換 Style Transfer

• Visual Attribute Transfer through Deep Image Analogy
• Deep Photo Style Transfer: A deep-learning approach to photographic style transfer that handles a large variety of image content while faithfully transferring the reference style
• Deep Image Prior

圖像分類 Image Classification

• Feature Visualization: How neural networks build up their understanding of images
• An absolute beginner's guide to Image Classification with Neural Networks
• Background removal with deep learning

人臉識別 Face Recognition

• Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression
• Eye blink detection with OpenCV, Python, and dlib
• DEAL WITH IT in Python with Face Detection

視頻穩定化 Video Stabilization

• Fused Video Stabilization on the Pixel 2 and Pixel 2 XL

目標檢測 Object Detection

• How HBO’s Silicon Valley built 「Not Hotdog」 with mobile TensorFlow, Keras & React Native
• Object detection: an overview in the age of Deep Learning
• How to train your own Object Detector with TensorFlow’s Object Detector API
• Real-time object detection with deep learning and OpenCV

自動駕駛汽車 Self Driving Car

• Self-driving Grand Theft Auto V with Python : Intro [Part I] - Sentdex
• Recognizing Traffic Lights With Deep Learning: How I learned deep learning in 10 weeks and won $5,000

智能推薦 Recommendation AI

• Spotify’s Discover Weekly: How machine learning finds your new music
• Artwork Personalization at Netflix

智能遊戲 Gaming AI

• MariFlow - Self-Driving Mario Kart w/Recurrent Neural Network
• OpenAI Baselines: DQN. Reproduce reinforcement learning algorithms with performance on par with published results.
• Reinforcement Learning on Dota 2 [Part II]
• Creating an AI DOOM bot
• Phase-Functioned Neural Networks for Character Control
• The Game Imitation: Deep Supervised Convolutional Networks for Quick Video Game AI - Stanford University
• Introducing: Unity Machine Learning Agents – Unity Blog

智能下棋 Chess AI

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• AlphaGo Zero: Learning from scratch | DeepMind
• How Does DeepMind's AlphaGo Zero Work?
• A step-by-step guide to building a simple chess AI

智能醫學 Medical AI

• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• Can you improve lung cancer detection? 2nd place solution for the Data Science Bowl 2017.
• Improving Palliative Care with Deep Learning - Andrew Ng
• Heart Disease Diagnosis with Deep Learning

智能演說 Speech AI

• Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model - Data Scientists at Google
• Sequence Modeling with CTC
• Deep Voice: Real-time Neural Text-to-Speech - Baidu Silicon Valley AI Lab
• Deep Learning for Siri’s Voice: On-device Deep Mixture Density Networks for Hybrid Unit Selection Synthesis - Apple

智能音樂 Music AI

• Computer evolves to generate baroque music!
• Make your own music with WaveNets: Making a Neural Synthesizer Instrument

天然語言處理 Natural Language Processing

• Learning to communicate: Agents developing their own language - OpenAI Research
• Big Picture Machine Learning: Classifying Text with Neural Networks and TensorFlow
• A novel approach to neural machine translation - Facebook AI Research
• How to make a racist AI without really trying

預測 Prediction

• Using Machine Learning to Predict Value of Homes On Airbnb
• Engineering Uncertainty Estimation in Neural Networks for Time Series Prediction at Uber
• Using Machine Learning to make parking easier
• How to Predict Stock Prices Easily - Intro to Deep Learning #7

擴展閱讀:《The Machine Learning Master》

• Machine Learning(一):基於 TensorFlow 實現寵物血統智能識別
• Machine Learning (二) : 寵物智能識別之 Using OpenCV with Node.js
• Machine Learning:機器學習項目
• Machine Learning:機器學習算法
• Machine Learning:機器學習書單
• Machine Learning:機器學習參考文集
• Machine Learning:機器學習技術與知識產權法
• Machine Learning:人工智能媒體報道集
• 數據可視化（三）基於 Graphviz 實現程序化繪圖

更多精彩內容掃碼關注公衆號：RiboseYim's Blog