Period                                   March 8-10, 2019
Place                                    Google Japan
                                             (Roppongi Hills, 6-10-1 Roppongi, Minato-ku, Tokyo  106-6108, Japan)  
Representative Organizer       Satoru Hashimoto, MD (Kyoto Prefectural University of Medicine)
*Hands-on Workshop will be also held on March 7, 2019 at the TMDU as the supplemental program.



Japan’s Second Big Data
Machine Learning Event in Healthcare


 It is my great pleasure to announce our second medical big data analytics conference in Japan, which we will host at the Google Japan Tokyo office during March 8 to 10, 2019. Our first conference at Tokyo Medical and Dental University (TMDU) in 2018 was largely successful and ignited great enthusiasm among experts from industry and academia, as well as among students. For our second event, we anticipate many data scientists and critical-care experts to gather in Tokyo and decipher big data extracted from various ICU-derived electronic medical records. We will also host a hands-on workshop on March 7 at TMDU as an introductory session and side event to the conference.
 At our first Datathon at TMDU, it was amazing to see many participants that initially did not know one another instantly connect. By the end of the event, many had become so close, remaining in contact to develop new projects and partake in ongoing collaborative research.
 For our second conference, the steering committee and I will host a full Datathon, inviting experts from the United States, Australia, New Zealand, and Singapore, alongside other newcomers. We hope this event will catalyze the development of an integrated multidisciplinary team of healthcare professionals, data scientists, system engineers, statisticians, industries, venture capitalists, and other professionals. Our ultimate goal is to work as a team to optimize patient care at the bedside by effectively utilizing artificial intelligence and machine learning with big data. We look forward to welcoming you all to Japan.

Satoru Hashimoto, MD
Professor, Director of Intensive Care Division
Department of Anesthesiology and Intensive Care Medicine
Kyoto Prefectural University of Medicine, JAPAN

 2019年3月8日から3日間、東京六本木ヒルズ Google Japan東京オフィスにて第2回のBig Data and Machine Learning in Healthcare in Japanを開催させていただくことになりました。今回は会場が手狭なため60名程度しかDatathon(3月9日10日の2日間)に参加いただけないため、3月7日に東京医科歯科大学構内にて技能別のハンズオンワークショップも企画しております。
 2018年2月24-25日に東京医科歯科大学で開催した第1回のBig Data and Machine Learning in Healthcare in Japanは多くの皆様のご協力により盛会となり成功裏に終会しました。それまで面識のなかった統計学者と臨床医が二日間という短い期間ではありましたがお互いを知ることとなり、多くの方が1年後の再会を約して下さいました。当初は私の本拠地である京都での開催を考えましたが、過去に本イベントを全面的に支えておられるGoogle社のご厚意により東京六本木の本社にて開催することに急遽変更させていただきました。このためご案内や若干募集等の開始が遅れ、また募集総数が少なめになってしまったことはご容赦ください。
 医療において、電子カルテをはじめとしたデジタル化の波は今後も前進しつづけることは間違いありません。そこで蓄積されるbig dataをいかに利活用するかが、これからの医療において重要な意味を持つことは誰の目にも明らかです。一方、医療者だけではこのようなbig dataを処理しそこから意味ある結論を導くことはますます困難になってきているのではないでしょうか? データソンはこのようなbig dataの解析における、AI machine learning活用に長けるdata scientistsと医療従事者との出会いの場です。春間近の六本木にて皆様をお待ち申し上げます。

橋本 悟
集中治療部 部長/病院教授

Screen Shot 2018-07-31 at 21.34.50.png

What is a Datathon?

 A Datathon per se is a voluntary, sprint-like event in which data scientists and experts in a certain field gather and work side by side with the aim of tackling major questions in the field through the analysis of big data. It is typically organized in the way of a competition with many concurring teams, and often held on a weekend. ICU Datathons do not differ much from this general model: teams composed by physicians, data scientist, statisticians and engineers are formed and all attempt to solve some of the current issues in the Intensive Care Unit (ICU) using the data from MIMIC Database, ANZICS APS, or JIPAD. The themes (clinical questions) are proposed by physicians, usually members of the national ICU society of the hosting country, before the actual Datathon takes place, while the teams are built just prior or at the event itself.
 Second Datathon in Japan will be held from Friday, 8th of March 2019 to Sunday, 10th of March. The first day will offer hands-on workshops and lectures. Saturday and part of Sunday will be for “hacking”, which in a health Datathon means the application of machine learning on health data. Participants with various backgrounds will work together with the shared goal of addressing a research question. At the end of Sunday, teams present their analyses. A Scientific Committee will select and award the best 3 projects based on clinical relevance, the novelty of the topic, the methodology, and the quality of the presentation.
 The IT infrastructure is managed by the experts from Massachusetts Institute of Technologies and National University of Singapore and other societies. A team coming from various Japanese institutes takes care of setting up the database and the connections to the servers. These facilitators also provide support to the various teams during the competition.
 The event is sponsored by companies and institutions. In past Datathons, companies like Google, Philips, General Electric, Hitachi and others (see past events) were involved with their national and international representatives.

How does it work?

 The opening ceremony is usually held by the members of the MIT Team, who welcome the participants, introduce the rules and the subject of the event, and explain all the tools and databases available during the competition.
 The teams are then formed and assigned a clinical task: the modalities in which this is brought to completion vary. The core of the Datathon is the hacking phase, which takes place from Saturday morning through Sunday afternoon. Teams thus have less than 2 days to tackle the clinical question they were assigned. Afterwards, they are asked to present their results in front of both the public and judges. The board decides and announces the winning team and runner-ups during the closing ceremony where they are presented with their awards. The goal of the Datathon is ultimately to create interdisciplinary collaborations in critical care as well as promoting the use of advancing machine learning techniques in healthcare.
 Before and/or during the competition, MIT experts, invited speakers and exponents from companies and institutions engage in presentations and talks about the subject, making up for the conference part of the event. This is usually held on Friday.


Hands-on Workshop
March 7, 2019 9:00-16:30@TMDU


An introduction to causal inference
Ryo Uchimido/Wei-Hung Weng

Causal inference is an approach to estimate an average causal effect of treatment. Although machine learning/deep learning has developed many predictive algorithms with extraordinal accuracy, those algorithms are not sufficient in clinical decision making. For instance, identifying patients with poor outcomes might be very different from identifying the best treatment in a population. Causal inference could offer theoretical frameworks for the better choices of treatments. In addition, applying machine learning for causal inference has proposed as a next step of machine learning developments.
This course aims to provide a good start of learning causal inference approach. This course is mainly for participants who don’t have previous knowledge of causal inference. We will start from scratch by using a “DoWhy” Python library. This workshop has the following requirements: laptop with Anaconda 5.0.1 (Python 3.6 version) installed, and basic understanding of Python and Jupyter notebook. Required reading;


Matching & Causal Inference: New Directions
Aaron Kaufman/Adrian Velasquez

Matching is an important tool in causal inference, especially in the analysis of patient records, and it is one of the fastest-developing areas of research in statistics. In this workshop, we will discuss the basics of matching, the assumptions under which matching produces causal estimates, some of the classic techniques used to perform matching, and the methods used to measure match quality. We will apply these methods to MIMIC data related to patients with sepsis. Finally, we will introduce matching with text data, a new frontier in matching, and show how text data can improve match quality.
1) Basic experience with causal inference
2) Basic familiarity with the R programming language and R Studio


Data analysis using JIPAD, ANZICS APD, etc.
Shawn Sturland/David Pilcher/Satoru Hashimoto


Deep learning for medical imaging
Mengling (Mornin) Feng

Artificial intelligence (AI) is the buzzword for all things relating to technology these days. In particular, healthcare is seen as an area in which AI may be gainfully deployed to improve medical care, especially with big data, exponential computing power and a burgeoning demand on healthcare systems due to aging populations. In this talk, I will share one use case that my group has engaged recently.
Our use case focuses on the analysis of medical images, in particular, the mammogram images. My team recently participated the DREAM digital Mammogram challenged funded by the US white house fund and FDA. The aim was to improve the predictive accuracy of digital mammography for the early detection of breast cancer. The challenge was constructed around 640,000 mammogram images for over 80,000 patients. We developed a patch-based deep neural network structure to extract abnormal lesions and patterns from mammograms so to detect breast cancer. After months of training, the proposed AI model managed to achieve detection performance close to human experts. We are now working with the Breast Cancer Screening Center at National University Hospital aiming to develop and deploy an AI-aided tool to assist radiologists to achieve more accurate, consistent and faster breast cancer screening. Our workshop will share the fundamentals on how deep neural networks can be applied on medical image analysis, and I will also share the lessons learned via our mammogram project. Only pen and paper will be required.


Tree-based approaches for prediction, with applications to healthcare data
Matthieu Komorowski


Natural language processing
Christina Chen/Euma Ishii/Naoaki Ichihara


Leo Anthony Celi/Dan Ebner/Marta Fernandes/Louis Agha-Mir-Salim


Software and tools for data analytics - GitHub, Jupyter notebook, Google Colabs, Slack
Kenneth Paik/Stephanie Ko

March 8, 2019 9:00-16:30@Google Japan

Datathon Worksop
March 9 &10, 2019 9:00-16:30@Google Japan



We still have the availability for the Course-1, 2 and 5.
Application form for foreign applicants > click here
Application form for Japanese applicans > click here

Those who would like to join the 2nd Big Data Machine Learning in Healthcare in Japan are requested to apply in advance before completing the registration by paying the registration fee.

※The pre-Datathon event, that is the trial seminar for training for the 2nd Datathon, is planned to have on January 12, 2019 at the TMDU. The registrants can join this pre-event for free (Pre-registration is required.).

Registration Category

◆Course 1: Lectures (March 8, 2019@Google Japan)

Registration fee
<Physician>5,000 JPY
<Other professionals & student>2,000 JPY
<Industry staff>5,000 JPY

◆Course 2: Hands-on Workshop (March 7, 2019@TMDU/Portable WiFi required) + Lectures (March 8, 2019 @Google Japan)

Registration fee
<Physician>15,000 JPY
<Other professionals & student>5,000 JPY
<Industry staff>15,000 JPY

Course 3: Lectures (March 8, 2019@Google Japan) + Datathon Workshop (March 9 & 10, 2019 @Google Japan)→Full booked

Registration fee
<Physician>30,000 JPY
<Other professionals & student>10,000 JPY
<Industry staff>50,000 JPY

*Those who would like to attend the Hand-on workshop on March 7, please ask the availability.

Course 4:  Hands-on Workshop (March 7, 2019@TMDU/ Portable WiFi required) + Lectures (March 8, 2019@Google Japan) + Datathon Workshop (March 9 & 10, 2019 @Google Japan)→Full booked

Registration fee
<Physician>35,000 JPY
<Other professionals & student>11,500 JPY
<Industry staff>55,000 JPY

◆Course 5:  Hands-on Workshop (March 7, 2019@TMDU/ Portable WiFi required)

Registration fee
<Physician>12,000 JPY
<Other professionals & student>3,500 JPY
<Industry staff>12,000 JPY

How to register

  1. Application:
    Click the ‘APPLY’ and complete the Application Form before December 15, 2018.
  2. Selection:
    In case of oversubscription, we will select participants in the capacity according to the occupation, affiliation and/or other backgrounds.
  3. Notification:
    Result of selection will be announced with the URL for the Registration Form by email before December 31, 2018.
  4. Registration:
    Fill in the Registration Form.
    Complete the registration by remitting the registration fee by credit card.
    Completion notice will be received with the information of MY PAGE. In MY PAGE, you will find the QR code and the tentative receipt. Your personal data and log-in password can be changed.

How to participate

  1. Print out and show your QR code at the Reception Desk and receive the name card.
  2. Be sure to wear your name card during the event.
    *Please bring your own PC.


応募フォーム > こちら

2nd Big Data Machine Learning in Healthcare in Japanは定員制です。参加していただくには、参加費お支払いの前に、まずご応募ください。

※Datathonに向けて予習していただく目的で、2019年1月12日(土)に東京医科歯科大学において2nd Datathonのプレイベントを開催する予定です。2nd Datathon参加者は無料でご参加いただけます(事前申込制)。


◆コース1:講演(3月8日(金)/Google Japan)

<医師> 5,000円
<その他(学生を含む)> 2,000円
<企業関係者> 5,000円

◆コース2:ハンズオンワークショップ(3月7日(木) /東京医科歯科大学/ポケットWiFi持参要)+講演(3月8日(金)/Google Japan)

<医師> 15,000円
<その他(学生を含む)> 5,000円
<企業関係者> 15,000円

◆コース3:講演(3月8日(金)/Google Japan)+ Datathonワークショップ(3月9日(土)・10日(日)/Google Japan) → 定員満了

<医師> 30,000円
<その他(学生を含む)> 10,000円
<企業関係者> 50,000円

◆コース4: ハンズオンワークショップ(3月7日(木) /東京医科歯科大学/ポケットWiFi持参要)+講演(3月8日(金)/Google Japan)+ Datathonワークショップ(3月9日(土)・10日(日)/Google Japan)  → 定員満了


◆コース5: ハンズオンワークショップ(3月7日(木) /東京医科歯科大学/ポケットWiFi持参要)




  1. 下記「APPLY」ボタンをクリックし、応募フォームに必要事項をご入力ください。
    応募期限: 2018年12月15日(土) 終了いたしました。


  2. 定員を超えた場合、職種やご所属、ご活躍分野等を考慮して選抜させていただきます。
  3. ご参加いただけるかどうかを2018年12月末日までにお知らせします。
  4. 参加登録URLをお知らせしますので、必要事項をご入力いただき、参加費をお支払いください(クレジット決済のみ)。


  1. マイページに表示されているQRコードを印刷し、参加受付でご提示ください。名札をお渡しします。
  2. 会議中は必ず名札をご着用ください。


Google Cloud Platform(GCP)を使用します。アクセスのためには各自のG-mailアカウントの登録が必要となります。


Speakers & Facilitators

Coming soon


Prospectus for sponsorship: here


Coming soon

Past Datathons



December 1-3, 2017

The event was held in a coworking space (the Impact Hub Madrid) where every team had its own area to develop their projects. The event began on Friday with a series of talks from MIT experts, European researchers and clinician as well as institution representatives. On Saturday, there were talks from companies such as Philips followed by a team-building phase. The Spanish national ICU society and the MIT committee selected the projects, emphasizing topics that reflected the actual needs in the European landscape. The rest of Saturday and the whole of Sunday were reserved to the actual “hacking” phase. The event ended with final presentations from the various teams, judgement from the board and an awards ceremony.



January 20-21, 2018

Unlike Madrid, the project proposals and team-building phase started twenty days before with groups from Google and completed a week before the Datathon. On Saturday morning clinicians from the MIT-LCP, the APHP and the French ICU society opened the event and introduced the tools that were available for project development. Also, it was at this event that the APHP database was unveiled: the first European online database that resembles MIMIC and currently the biggest medical aggregation. The Datathon ended on Sunday with a talk from Hitachi followed by an awards ceremony. Of note, Google was involved in the MIMIC – OMOP development and was also represented as a team in the competition.

Video review of the event:



February 24-25, 2018

The 1st Big Data Machine Learning in Healthcare Datathon in Japan was held at the Tokyo Dental and Medical University following the Japanese Society of Intensive Care Medicine's Annual Congress. This two day conference first held in Japan was comprised of seven lectures, 11 hands-on workshops, and a mini-Datathon (half day version of the Datathon style workshop). Participants from various sectors, from students and professionals in healthcare related fields to programmers, gathered to analyze data from MIMIC, the ANZICS APD (adult patients database), and JIPAD (Japanese ICU patients database) to answer six prefixed clinical questions, with one winning team selected at the end of the event. Collaborative efforts for publications have continued beyond the Datathon and we look forward to seeing more during our second year.