Newswire

Medication errors are a critical problem in healthcare, and Look-Alike, Sound-Alike (LASA) medication errors pose a particularly daunting challenge. Studies show that LASA errors account for approximately one in four medication errors, making them a significant threat to patients. AESOP Technology is thus pleased to announce remarkable results from its recent clinical research, demonstrating its exceptional effectiveness in preventing LASA errors.

"Accurately identifying LASA errors can be challenging due to their complex origins. Surprisingly, only about 15% of intercepted wrong drug errors during our study could be clearly categorized as LASA errors, in the sense that the medications had similar names that contributed to the mix-up. The LASA errors also did not follow predictable patterns, with only 9 out of 71 cases repeating. These findings underscore the limitations of conventional human-defined rule systems, even when augmented with reinforcement learning. RxPrime (formerly MedGuard) not only detects errors that were not previously identified but also highlights the essential need for AI with advanced medical knowledge, demonstrating a breakthrough in patient safety in healthcare," said Jim Long, CEO of AESOP Technology, explaining the intricacies of detecting medication errors, specifically LASA errors.

AESOP also leverages its proprietary AI technology to overcome the limitations of traditional clinical decision support systems and address the issue of alert fatigue.

"AESOP has taken additional steps to improve problem list documentation to reduce alert fatigue from LASA error detection. Many alerts contributing to physician fatigue result from poor problem list documentation within electronic health record systems. Thus, AESOP intervened at the source by helping physicians complete clinical diagnoses and documentation more effectively while prescribing," Long added.
​
More than half of all medication errors occur during the prescription phase, making it a critical focus for improving patient safety. AESOP's innovative approach offers a beacon of hope. Applying advanced AI technology to this complex problem has yielded impressive results and holds great promise for the healthcare industry. As we address patient safety challenges, AESOP Technology's contributions stand as a testament to the potential of innovative solutions in ensuring the well-being of patients worldwide.

Reference: yahoo finance

SOAP Health's conversational AI for medical encounters, risk and symptom assessment, and documentation integrates with AESOP Technology's electronic medical record data analysis for clinical decision optimization, coding, and productivity.
​
​
SOAP Health and AESOP Technology are excited to announce a transformative partnership that will push the boundaries of AI-enhanced medical encounters. This collaboration combines AESOP's cutting-edge DxPrime and DeepDRG solutions with SOAP Health's patented and clinically validated Ideal Medical AI Assistant™ to fuse patient-reported data with Electronic Medical Record Systems (EMRs) data to create Precision Patient Profiles™ that give physicians the most comprehensive view and understanding of their patients to improve speed to diagnosis, workflow efficiency, and revenue.

Steven Charlap, MD, MBA, CEO of SOAP Health, believes this alliance marks a milestone in effectively integrating AI into clinical encounters. "By incorporating AESOP's DxPrime into our existing solutions, we are elevating the realm of data-driven clinical decision-making. DxPrime's DeepDRG and Natural Language Processing capabilities are revolutionary, enhancing the quality and efficiency of data analysis and diagnostic decisions," said Dr. Charlap. "Combined with SOAP's patented and clinically validated Ideal Medical AI Assistant™, this partnership promises to enhance medical encounters, providing a robust, integrated solution that is unparalleled in today's market."

Combined with SOAP's integration with Dolbey Fusion Narrate™, a previously announced partnership, the Precision Patient Profile™ will seamlessly integrate into over 100 EMRs, fortifying the power of these applications to deliver value to physicians. "The joint venture between AESOP Technology and SOAP Health promises to radically optimize physician data collection and medical coding," says Jeremiah Scholl, Co-founder and CPO of AESOP Technology. "Our shared mission is to harness the power of AI to improve patient outcomes and clinical efficiency, and this partnership is a giant leap toward fulfilling that commitment."

SOAP Health's vision to reduce diagnostic errors aligns perfectly with AESOP's focus on improving the quality and efficiency of clinical decision-support and medical coding. This partnership is poised to bring significant advancements in physician practice, optimizing patient care and safety.
For more details on how SOAP Health and AESOP Technology are collaborating, please visit the SOAP Health Partner Page at www.soap.health/aesop

About AESOP Technology
AESOP Technology harnesses advanced AI to improve the clinical decision-making process, enhance medical coding quality, and prioritize patient safety. AESOP's flagship products, DxPrime and DxCode, boast 99% accuracy in identifying and analyzing data and integrate directly into physicians' clinical workflows. DeepDRG is the unique AI approach they developed to unlock understanding of how diagnoses are typically associated with structured clinical data like lab results, medications, and procedures. To learn more about AESOP Technology, visit aesoptek.com.

About SOAP Health
SOAP Health is a trailblazer in medical practice AI. Through patented conversational and generative AI, SOAP's mission is to save lives by reducing diagnostic errors, accounting for over 800,000 preventable deaths and permanent disabilities each year. The company leverages the collective expertise of seasoned medical entrepreneurs, scientists, and technologists to deliver clinically validated solutions. To learn more about SOAP Health, visit soap.health. 

Referred: BENZINGA

從健保資料庫挖礦 終成臨床編碼唯一服務供應商

​「我們始終想要用數據來做應用。」醫守科技執行長暨聯合創辦人龍安靖笑說，雖然曾被說不學無術，但團隊仍默默投入健保資料庫資料研究分析，靠著一股堅持，將數以百計的光碟片，一一讀取。也因為進得夠早、走得夠久、探得夠深，讓醫守得以成為臨床編碼唯一服務供應商，與臺灣的簽約數呈倍數成長，在數位發展部數位產業署的「資料經濟價值躍升計畫」支持下，也於美國傳來好消息，未來全球市場精彩可期。

由世界衛生組織建立的疾病分類系統，目的是把跨國家、地區在一定期間所蒐集的罹病或死亡資料，能夠系統化記錄、分析、解讀與比較，現已成為病歷書寫的重要部分。住院過程中，一位病患的病歷，作者群是經手過該病患治療歷程的所有醫師，他們會記錄病患主觀陳述、客觀檢查結果、曾經進行的手術或處置，最後進行病歷總結，再交給疾病分類人員分別進行疾病分類編碼，用以進行健保給付申報。
​
全球健保制度經過數十年的演進，申報制度大量引進各種編碼系統，為了整合各個複雜的系統，醫院需要耗費大量人力、物力，付出許多額外成本，更造成醫院的損失。臺灣健保疾病分類於2016年起以ICD-10 CM/PCS（International Statistical Classification of Disease and Related Health Problems, Tenth Revision, Clinical Modification / Procedure Coding System，國際疾病分類第十版）申報後，編碼數量大幅增加，也提高了臨床編碼的困難度。尤其，當醫師面對較不熟悉的處置碼和非本身專業科別的疾病，要選擇最正確且合適的編碼，相當挑戰與費時，導致疾病分類師必須花費更多的心力調整和修正醫師所選的編碼，更遑論進行在院編碼和品質稽核。

李宛庭

​「solaxin」與「solian」兩個極其相似的藥名，實際卻是天差地遠的藥品，分別是肌肉鬆弛劑和抗精神病藥。另外，每家藥廠又都有著各自的命名方式，因此即使是聰明又小心的醫生，也可能不小心開錯藥。

開錯藥品可能帶來的風險，不只是患者無法得到妥善的治療，還有可能導致誤食過敏藥物、產生其他副作用等嚴重後果。

2019年，醫守科技看見了醫療產業開錯藥的問題，開發RxPrime藥御守協助解決，現今則推出DxPrime好完診進軍診斷系統服務，今（2022）年8月更完成了295萬美元（約新台幣8,850萬元）的Pre-A輪募資，由台杉資本領投、日本知名上市遊戲公司Colopl Next、美國創投500 Global和比翼生醫創投等跟投。

從原先的「藥物開立服務」跨足「診斷系統服務」，醫守科技究竟看見了哪些產業問題？

從「用藥」到「診斷」，醫守科技如何從知名產品RxPrime藥御守轉型再出發？
​
2019年成立的醫守科技，最先推出的產品是RxPrime藥御守，希望為醫生減少開錯藥的狀況。藥廠出廠藥品時，會為藥品命名，相似的藥名卻可能是天差地遠的藥品，於是醫守科技的RxPrime藥御守，透過機率模型與增強學習雙重人工智慧引擎，打造用藥安全演算法，在偵測到藥品可能開錯時，即時發出系統警告提醒醫生。

儘管推出RxPrime藥御守立意良好，醫守科技卻面臨到了醫院採購的系統性問題。

Digital health startup AESOP Technology has raised a $2.95 million series pre-A round to address the growing medical and billing errors problem. The round was led by Taiwania Capital with participation from Colopl Next, 500 Startups, and BE Capital.

Originally from Taiwan, AESOP started as a university spin-off from Taipei Medical University (TMU). Professor Yu Chuan (Jack) Li, the founder and current president of the International Medical Informatics Association, spent ten years before AESOP working on big data approaches to reduce medication errors. He initially applied the model to launch a product, RxPrime (previously known as MedGuard), that identifies wrong-drug errors.

During the pandemic in 2020, Prof. Li officially established AESOP in the US with his former student, who grew to become CIO of a TMU-affiliated hospital, Dr. Jim Long, and former TMU Visiting Assistant Professor, Dr. Jeremiah Scholl. They worked together to broaden the types of errors the AI could identify and on products they could use to improve the US healthcare system.

"Our solution is revolutionary and generalizable." CEO Jim Long described. "We have developed an AI model with an exceptional understanding of the association between diagnoses and structured clinical data like medications, lab results, and procedures."
One of the first errors RxPrime identified was a 9-year-old girl accidentally prescribed an anti-schizophrenia drug for simple back pain. Another commonly prescribed error was Acetaminophen (pain killer), sometimes mistaken as Acetazolamide (glaucoma and altitude illness). "These mistakes might occur just because the two drugs have look-alike or sound-alike (LASA) names. It is horrible to think about, but errors like LASA happen in hospitals everywhere." Jim explained

AESOP Technology announced that they have been accepted into Mayo Clinic Platform_Accelerate, a 20-week program that helps early-stage health tech AI startups get market-ready.

Participants are selected through a competitive screening process where a panel of Mayo Clinic leaders reviews them from the clinical and operational perspective, led by John Halamka, MD., President of Mayo Clinic Platform.

"It's an excellent opportunity for a medical AI startup like us. Data is the fuel from which everything grows into power, and this program provides de-identified patient datasets and tools to help us validate our solutions," says Jeremiah Scholl, the CPO of AESOP Technology. "This practical experience will help us go even further in developing better products. The fact that we get to be mentored by Mayo Clinic's reputable experts is inspiring."

'AESOP',  which stands for 'AI-Enhanced Safety of Prescription', is working to make physician data entry easier, faster, and less error-prone using machine learning on 3.2 billion data sets. The company has developed products capable of this. One is RxPrime which detects wrong drug errors by checking if medications match patients' diagnoses, age, and gender.

Errors can happen at any stage of the medication-use process, but more than 50% of them occur during the prescribing phase. RxPrime is able to detect potential and unexplained errors in prescriptions and provide optimal recommendations, even for the look-alike-sound-alike medication errors. It offers just-in-time decision support without interfering unnecessarily with the clinical consultation process.

ROCHESTER, Minn. — Mayo Clinic Platform_Accelerate has announced its second cohort of health tech startups, including national and international businesses. The program will help seven companies develop and validate their artificial intelligence-driven health care products or solutions and advance their business plans.

The immersive, 20-week program offers participants access to Mayo Clinic experts in regulatory, clinical, technology and business domains with a focus on AI model validation and clinical readiness. Technology experts from Google and Epic also will provide workshops for the participants.

"The only way we can transform health care is by bringing together clinical experts with technology innovators," says John Halamka, M.D., president of Mayo Clinic Platform, a strategic initiative to improve health care through insights and knowledge derived from data.

"Our Accelerate program combines emerging companies with breakthrough ideas, leaders from Mayo's clinical practice and our unique 'data behind glass' approach to algorithm development," Dr. Halamka says, describing the secure environment that allows companies to build algorithm models they can use for innovation, but the data never leave the Mayo Clinic Platform.
​
The program will help participants explore ways to improve health care in a variety of areas:

• AESOP Technology: Using machine learning on 3.2 billion patient visits, AESOP aims to make physician data entry easier, faster and less error-prone by automating diagnosis input and improving medication-related workflows. AESOP has offices in California, Colorado and Taiwan.
• Biotia: By fighting infectious diseases with AI and genomics, Biota is leveraging new DNA sequencing technology to enable personalized, data-driven discovery of microorganisms that cause illness. The company is based in New York City.
• Delfina: Tackling the maternal health crisis, Delfina’s software is monitoring health data to assess pregnancy risks, coordinate with providers and deliver a personalized care plan to improve pregnancy outcomes. Delfina has offices in San Francisco, New York City and Rochester, Minnesota.
• Dynocardia: Using wearable technology for accurate real-world continuous blood pressure and other advanced heart function measures, Dynocardia is leveraging AI to enable early detection before serious health events. The company is based in Cambridge, Massachusetts.
• ImpriMed: To personalize human and animal cancer treatment, ImpriMed aims to validate an oncology platform to provide patients and clinicians with the best predictive information for individual cancer patients. The company has offices in Palo Alto, California, and Seoul, South Korea.
• Predicta Med: To shorten the diagnostic journey and enable early and effective treatment, Predicta Med is creating an AI-based decision support platform for early detection of autoimmune diseases. The company is based in Tel Aviv, Israel.
• SOAP Health: SOAP (Subjective, Objective, Assessment, Plan) Health seeks to enhance physician productivity and insight to ensure accurate and timely prediagnosis — made before occurrence of symptoms — and diagnosis. The company is based in Boca Raton, Florida.

​California-based medical AI startup Aesop Technology, which has an R&D office in Taiwan, has recently unveiled its latest clinical documentation improvement tool that helps coders spot incorrectly coded diagnoses or procedures.

DxPrime provides suggestions to support medical data entry. The CDI tool is based on a machine learning model that has been trained based on a data set of some 3.2 billion patient visits. According to Aesop Technology, their latest solution for medical coding harnesses AI to "efficiently compensate for traditional CDSS and NLP weaknesses to find correct or missed diagnoses".

WHY IT MATTERS

Now available on digital health marketplace Olive Library, DxPrime provides information on missing and wrongly coded diagnoses or procedures to easily correct patients' charts. 

With incorrect patient records, Aesop claims, patients could be given improper discharge instructions, thus receiving poor after-discharge care. For providers, this could lead to a wrong estimate of their patients' length of stay and wrong code insurance claims, which could ultimately result in denials and revenue losses.

Aesop emphasized that errors in diagnosis input are difficult for physicians to avoid due to the gap in their knowledge of coding systems. Currently, the 10th revision of the International Statistical Classification of Diseases and Related Health Problems (ICD-10) has 14,400 diseases included in its base classification, 68,000 diagnosis codes under ICD-10-CM and 87,000 procedural codes under ICD-10-PCS.

PRNewswire

Medical AI start-up Aesop Technology announced a new partnership that made their new product, DxPrime, available in the Olive Library. DxPrime provides physicians and clinical documentation improvement (CDI) teams with information about missing and wrongly coded diagnoses and procedures to correct the patient's chart in just a few clicks. It makes completing discharge summaries, prioritizing work for CDI teams, and medical coding much easier, faster, and less error-prone.
​
If the patient record is incorrect, you cannot code correctly.

Completeness, precision, and validity of medical documentation are critical for all healthcare stakeholders. Without correct patient records, patients could receive improper discharge instructions and a sub-optimal continuum of care. Providers also can struggle to estimate the length of stay and code insurance claims correctly, resulting in denials and loss of revenue.

Approximately 10% of inpatient claims are denied, of which more than 85% (or about $35 billion) result in unnecessary losses. Many of these denials occur because of errors in the patient record that occur upstream from the claims process. Diagnosis input errors are difficult for physicians to avoid because the knowledge of coding systems is different from what they need to learn to provide great patient care. Modern medicine's complexity has caused 14,400 diseases to be included in ICD-10, further classified into 68,000 ICD-10-CM and 87,000 ICD-10-PCS codes.

"Physicians, CDI team, and coders have to spend a lot of time poring through medical records to find the key clinical diagnoses among the vast amount of information available," said Jim Long, CEO of AESOP. "After that, they have to follow a series of inefficient steps on the computer to complete the input process, and search functionality for ICD codes often is not helpful. The whole process is complex, time-consuming, and error-prone.

When the physicians input the improper diagnosis, it also has downstream implications. "When using DxPrime, we have helped physicians often notice they did not correctly code complications such as urinary tract infections and respiratory failure. By assisting them in inputting the proper diagnoses, our partners have seen an increase in revenue of 5-10% per inpatient."

State-of-the-art machine learning assisted physician data entry.

DxPrime provides high-quality suggestions to support physician data entry based on a machine learning model (published in the Healthcare journal) that has been run on top of data from 3.2 Billion patient visits, including vast amounts of structured information. It allows DxPrime to use items from the patient record like lab test results and medications ordered when predicting a diagnosis.
​
This comprehensive model utilizes artificial intelligence to efficiently compensate for traditional CDSS and NLP weaknesses to find correct or missed diagnoses.

Referred from: yahoo finance

U.S.A., Jan. 31, 2022 - Olive, the automation company creating the Internet of Healthcare, today announced the winners of the first-ever Hack for Health contest. In partnership with Rotera, Olive held the contest to encourage developers to build Loops (think apps in an app store) that will change the way healthcare employees work by improving efficiency, reducing the scope for errors and burnout, and enhancing productivity — all to optimize the patient experience.

Olive designed its Hack for Health contest to solve healthcare’s biggest problems through collaboration with the developer community. Participation is open to any individual developer, startup, health system, or enterprise technology company. Winning Loop submissions are published on Olive’s platform, giving developers full access to Olive’s growing payer-provider network.

While any developer who publishes a loop on Olive’s platform receives 85% of the revenue generated from their Loop(s) once published, Hack for Health grand prize winners also receive tiered cash prizes up to $10,000, industry speaking engagement opportunities, a 60-minute pitch meeting with the Olive Ventures team, an Oculus Quest 2, YubiKey, and a 30” curved monitor. Olive also provides opportunities for its employees to develop Loops as part of an internal contest with its own set of prizes.

“Olive created healthcare’s first true platform. We wanted to create an event that encouraged a wide range of developers to come build on it to grow our ecosystem of people working together to transform healthcare,” said Patrick Jones, Executive Vice President, Partnerships at Olive. “Our first-ever Hack for Health contest, in partnership with Rotera, was the perfect way to introduce developers of all sizes to Olive and create new solutions that will help change the way healthcare workers work.”

Olive selected the following five Loops as the grand prize winners based on their functionality, innovation, outcome improvement, and bettering of diversity, equity, and inclusion among underrepresented healthcare workers and patients:

• AESOP Technologies with the RxPrime Loop and DxPrime Loop: These Loops identify potential wrong-drug errors like “look alike/sound alike” errors and “wrong click” errors, as well as missing and incorrect diagnoses codes. They also provide suggestions of diagnoses and medications based on comparing the patient's chart to information mined from more than 3 billion patient visits.

左起為臺北醫學大學生醫加速器執行長-陳兆煒、科技部人工智慧生技醫療創新研究中心副執行長-張丹菁、食藥署品質監督管理組副組長-陳映樺、主持人未來城市頻道總監-陳芳毓、台灣醫材新創醫守科技創辦人-龍安靖進行精采的分享。圖片來源：食藥署

​智慧醫材論壇最終場「產業與智慧醫材菁英跨域對談」，27日在書香花園圓滿落幕，從8月底開始，五場智慧醫材論壇，一路從學界觀點談到政策發展，最終場來到「醫材創業」的主題。
​
本次論壇榮幸邀請到台灣學研界的專家——臺北醫學大學生醫加速器執行長陳兆煒，科技部人工智慧生技醫療創新研究中心副執行長張丹菁，以及成功打入美國市場的台灣醫材新創醫守科技創辦人龍安靖，在短短三小時內分享交流研發醫材創業的心路歷程。

針對市場需求，陳兆煒執行長指出，首要任務是瞭解使用者的需要，定義出需解決的問題，藉此幫助團隊找出創業初期市場中尚未滿足的需求（Unmet Need），「經過十年後，就要致力於找到高價值需求True need，才能幫助台灣的生醫市場發展起來。」同時，北醫加速器在做的，就是協助新創團隊在複雜的利害關係中，調整出最合適的經營模式。
​
成功進軍美國市場的醫守科技是少數經歷各種加速器培育成長的智慧醫材新創，且團隊第一筆資金即來自美國矽谷。龍安靖創辦人分享，現在醫守科技試圖建立一個小規模發展模式，以爭取美國市場投資或商業機構合作為主，「先在美國吸取經驗、習慣美國客戶需求，待熟悉美國的環境、條件、限制後，再進一步去找國際化資金。」

龍安靖也分享，在美國市場尋找立足點，要注意三點，一是缺乏美國醫療數據，須加入美國大數據平台，才能有效率的開發產品。二是落地深耕有難度，如何證明自身實力，才能吸引大規模的病例公司合作，醫守科技過往發表的論壇期刊即是證明。第三點品牌識別度，在國外市場要建立品牌鑑別度頗具難度，因此對於品牌服務的定位，比起找出競爭者，更應著重在找到合作對象，藉此發揮合作效益的最大化。

醫守科技正是成功發現新問題，在醫院工作大量電子化的情形下，有新問題產生——系統使用不便導致醫師開藥錯誤、帳務計算錯誤等，龍安靖說：「我們透過期刊論文證明我們的方法有效，利用大數據解決電子化趨勢下產生的新問題。」

Ten startups from the Taiwan Tech Arena (TTA) will participate in the program's first Global Innovation Pitch Showcase, produced in partnership with Berkeley SkyDeck, UC Berkeley's highly competitive global startup accelerator. Silicon Valley VCs, angel investors and industry professionals will attend the virtual event. Interested investors may register to join the pitch Showcase here.

TTA, funded by Taiwan's Ministry of Science and Technology, is focused on building a vibrant tech ecosystem of Asian startups. Each year, they select a cohort of up to 30 startups to participate in the TTA Silicon Valley accelerator, with eight of the startups participating with SkyDeck as part of its Global Innovation Partners program. This event marks the first time TTA is producing a pitch showcase with SkyDeck.

"We are proud to connect the outstanding Taiwanese tech talent with the impressive entrepreneurial community of Berkeley SkyDeck," said the TTA Silicon Valley office. "Since 2016, we have brought more than 150 innovators from Taiwan to the U.S. to build strong international relationships and connections and attract investment. And it's noteworthy that most of the startups' businesses stem from academia. To date more than half of these Taiwanese startups have raised money. With the new Showcase, we're thrilled we can share their talents, ideas and innovations on a global stage."

SkyDeck's Global Innovation Partner Program serves as a bridge for global startup teams as they participate in the SkyDeck entrepreneurial ecosystem and bring their ideas to the U.S. market. A limited number of startups from outside the U.S. are selected to participate in the partner program alongside the SkyDeck Batch (cohort) and Pad-13 (incubator) teams.

"Working closely with TTA has been a wonderful experience for all of us," said Caroline Winnett, Executive Director, Berkeley SkyDeck "Not only are the teams from Taiwan getting an immersive learning and networking experience at SkyDeck, they will return home ready to launch and create economic opportunities in their communities. We look forward to helping jumpstart these startups here in the U.S. and then seeing how they grow."
The Aug. 19 Showcase will feature the following startups:
​​

• AESOP: AESOP aims to reduce medication errors and billing errors, thus enhancing patient safety and optimizing revenue with AI-powered technologies.

The study also found that applying a federated learning approach can further improve accuracy of the model.​

A study has demonstrated the international transferability of a Taiwanese artificial intelligence model for detecting medication errors in EHR systems in the United States.

The study was jointly conducted by Taiwan-based medical AI startup Aesop Technology, Taipei Medical University, Harvard Medical School and Brigham and Women's Hospital. Its results were announced last week in a press release.

WHY IT MATTERS

The "biggest challenge" in data-driven medicine is the successful implementation of data-driven applications in clinical practice from local to global settings without compromising patient safety and privacy, according to Dr Yu-Chuan Jack Li, a professor at Taipei Medical University.

The study, whose findings were published in the Journal of Medical Internet Research - Medical Informatics in January, found "good" transferability of Aesop's machine learning model in the EHR systems of two training schools under Harvard Medical School – Brigham and Women’s Hospital and Massachusetts General Hospital.

A federated learning (FL) approach was applied to the model which enhanced its performance. The said approach is an emerging technique that addresses the issues of isolated data islands and privacy. 

"FL provides the solution by training algorithms collaboratively without exchanging the data itself," Dr Yu-Chuan said. 

"The study has shown that the model trained by federated learning achieves remarkable performance comparable to the other two models trained by individual data sets," Aesop Technology co-founder and CEO Jim Long also said.

Incorporated in Aesop's MedGuard system, the AI medication safety model was trained using the 1.3 billion prescription data set from the National Health Insurance Administration in Taiwan.

In the statement, Aesop said its system can "immediately" provide adaptive suggestions to help doctors better complete their prescriptions. The AI model has since been expanded to eastern and western hospitals in the US.

THE LARGER TREND

Despite the wide adoption and optimisation of EHR systems in US hospitals, those systems still pose risks given varying safety performance, according to a 2020 study by researchers from the University of Utah and the Brigham and Women’s Hospital.

Medical errors are costing the US around $20 billion each year, leading to over 250,000 deaths. These can occur at any stage of the medication process with errors in prescribing happening half of the time.

The use of an AI system in preventing medication errors was already validated as early as 2017 by researchers at Harvard Medical School. In the same year, MedAware, the Israel-based startup which developed the algorithmic system, raised $8 million to scale its AI-powered solutions.

ON THE RECORD

"Reducing medication errors at the source is crucial. However, to help physicians be better informed and make better decisions, they need more accurate suggestions and alerts. This is where machine learning can help to make better decisions and improve patient safety and quality of care," said Dr David W. Bates, Chief of General Internal Medicine and Primary Care at Brigham and Women's Hospital and Professor of Medicine at Harvard Medical School.

​New study paves the way for collaboration on artificial intelligence modelling and medication error reduction globally

Researchers at Harvard Medical School, Brigham and Women's Hospital, Taipei Medical University, and Aesop Technology, a Taiwan-based startup, announced today the results of a new joint study into the international transferability of machine learning (ML) models to detect medication errors. The results were recently published in the Journal of Medical Internet Research - Medical Informatics.

Working to Reduce Medication Errors

Medication errors are a growing financial and healthcare burden that results in economic costs of around US$ 20 billion and more than 250,000 deaths annually in the U.S. alone.

Medication errors can occur during any stage of the medication process, including prescribing, dispensing, administration, and monitoring, with errors in prescribing accounting for 50% of the total.

When medicating patients, physicians go through complex decision-making processes to accurately write a prescription. First, they must clearly define the patient's problem and list the therapeutic objective before selecting an appropriate drug therapy based on age, gender, and possible allergies. They must also consider dosing, drug-drug interaction, potential discontinuation of the drug, drug cost, and other therapies — and all of these need to be done instantly and simultaneously.

"Reducing medication errors at the source is crucial. However, to help physicians be better informed and make better decisions, they need more accurate suggestions and alerts. This is where machine learning can help to make better decisions and improve patient safety and quality of care," said Dr. David W. Bates, Chief of General Internal Medicine and Primary Care at Brigham & Women's Hospital and Professor of Medicine at Harvard Medical School.

For technology to assist in solving these problems, it is critical that machine learning understands these variables. For this to be successful, data must be properly collected, organized, and maintained.

「Acetazolamide」與「Acetaminophen」是兩種完全不同的藥品，連要念出來都會讓人舌頭打結，前者是青光眼用藥，後者則是日常常見的止痛藥。
以止痛、解熱的Acetaminophen（乙醯胺酚）來說，在台灣健保用藥中，就有超過50家藥廠製造，普拿疼只是其中一種，每家藥廠的命名方式又不一樣，合計產品數量多達上百種。
​
由於可選擇的產品過多，就算醫師記憶力再怎麼好，也不見得能記住所屬醫院裡全部合作的藥廠產品。因此，有醫師或許會選擇用學名搜尋，卻可能一不留心就選成學名類似的Acetazolamide（乙醯偶氮胺）。
​
「 台灣每年光是把止痛藥開錯，開成青光眼用藥的案例，就多達3,000多次。 」醫守科技共同創辦人暨執行長龍安靖說，「止痛藥通常又會吃好幾顆，對老人、小孩來說，吃錯是非常危險的。」

台北醫學大學（以下簡稱北醫）對創新的積極追求，讓他們在白色巨塔中獨樹一格。

自2014年開始參與科技部各項補助計畫，至今北醫已積累18項自有核心技術，並衍生出多家新創公司，包括提供子宮內膜癌篩檢輔助的「酷式基因」，以及獲得科技廠力晶投資3.5億元、目標研發癌症疫苗及抗體藥物的「智合生醫」。

為發掘更多的創新和創業機會，北醫還與美國史丹佛大學簽約合作，挑選3位醫師接受Stanford Biodesign「醫材創新訓練」課程訓練，並於今年6月將這套課程引進體系內。

萬芳醫院（北醫體系）神經內科醫師陳兆煒，用自己專長的神經內科專長比喻，醫師在診間經常拿著一根小鎚子，用來確認神經傳導狀況。「舉例來說，醫材業者開發診斷類敲擊反射錘時，如果只專注在材質、規格是否更好，沒有重新檢視臨床使用的痛點和需求，很難取得真正的成功。」

解決兩大痛點，開通新創成長之路
​
今年7月，北醫正式開幕生醫加速器。這個台灣首家醫療大學國際級加速器，聚焦「 數位醫療 」、「 人工智慧 」與「 醫療器材 」3大主題，除導入Biodesign訓練課程、從需求找商機外，更運用1校7院的臨床資源，提供試驗規畫、降低開發風險，輔導團隊研究成果商品化與鏈結國際。

第一階段，北醫已和比翼資本共同輔導10家新創公司，並分別投資10萬美元給較成熟的復健醫學智慧軟體開發公司龍骨王、醫療新創醫守科技、美國健康監測解方公司Rhythm Diagnostic System（RDS）等3團隊。

其中的醫守科技，由前萬芳醫院資訊室主任龍安靖與台北醫學大學醫學資訊研究所特聘教授李友專共同創辦，分析13億筆健保處方資料，打造出智慧型藥物安全系統「藥御守」（MedGuard），已成功導入北醫體系與多家國內醫院。

​藥御守這套系統可在醫師開立處方時提供AI建議，把關超過120萬張處方；而醫師對於藥御守的建議接受度，也高達7成。

Digging for data

Any AI system needs to learn from data – the more the better. Taiwan has a trove of data to feed on thanks to its National Health Insurance (NHI)system, which was launched in 1995 and covers more than 99% of the population. In recent years, the government has allowed access to this extensive data for research and development.

One startup to take advantage of this opportunity is AESOP Technology, which has offices in Taipei, Berkeley, California, and Cambridge, Massachusetts. AESOP is trying to reduce a major risk to patients’ health globally: medical errors, specifically prescription errors. In Taiwan, they analyzed NHI data and found at least 3 million incorrect prescriptions each year, from incorrectly filled out forms to prescribing the wrong drugs or dosages.

“Everyone thinks hospitals are high-tech, but in hospitals, the staff records patients’ status on white boards,” said Jim Long, CEO of AESOP. “Doctors spell drug names wrong – even common drug names that sound like and look like other drug names.”

你的用藥觀念正確嗎？響應9月17日「世界病人安全日」，台北醫學大學李友專教授與醫守科技共同發表全台灣用藥安全分析，呼籲民眾重視自己與家人的用藥安全，尤其是長輩以及常見的降血壓藥和降血糖藥。

醫療人工智慧專家、台北醫學大學醫學資訊研究所李友專教授與其創設的醫守科技，根據健保資料庫近期釋出2017年度資料，分析當年度全台灣醫院門診總共開出3億6千萬張處方箋，其中約有60萬張是用藥不恰當的處方；換句話說，平均每600張處方箋中，就有1張用藥有問題，預估影響多達42萬病人，且近6成為超過60歲的老病號。

這些不恰當的一般用藥中，以腸胃藥、過敏藥及安眠藥最常見。至於在特殊高警訊藥類中*，則以降血壓藥、抗生素及降血糖藥最常被不恰當使用，特別需要留意。

今(11)日，由臺北市政府產業發展局主辦「2020臺北生技小聚」系列論壇，第二場次熱烈展開，以「步向2020數位醫療新十年」為主題，下半場邀請到神經元科技執行長楊鈞程以及醫守科技執行長龍安靖數位醫療新銳，與大家分享臺灣數位醫療於臨床上如何落地運用。 

醫守科技執行長龍安靖則分享「AI輔助用藥安全新契機」，他表示即使醫療現在發展已經相對過去進步，但醫院中的資訊仍存在片段化的問題，在醫療資訊不完整情況下，容易造成醫療錯誤、用藥錯誤。

臺灣每年平均開立3.6億張處方量，開錯處方藥約300萬張，明確開錯藥也有10萬張，不洽當劑量、不適當處方開立也占3-5%。根據統計2000年開始，美國因醫療錯誤使患者死亡躍上第三死因，至2016年狀況仍未改善，這是大家都想解決但不易解決的問題。 

開錯處方藥的問題全球都在發生，這不只是藥物管控問題，其衍生的額外人力、物力耗費、訴訟成本等造成龐大社會問題。 

處方藥開錯主要是因為藥名易混淆、看診時間短、多重疾病、多重藥物而造成。目前雖然有很多相關的警示系統開發，除了警示正確率不夠，系統開發、管理者往往不是醫生，因此開發的系統往往無法滿足醫事人員使用需求。 

醫守也進一步將處方開立系統圖像化，該系統在開立的一百張處方箋中約3%的處方會跳出警示，醫生接受率達70%、正確率達85%。他也強調醫守開發的系統不只加強用藥安全，還進一步改善用藥知識。

報導節錄於環球生技月刊

​生病就醫原本是為了獲得治療，但如果醫師開錯藥，不僅無助病症，更可能造成嚴重後果！根據統計發現，美國醫院因醫療錯誤的死亡數，僅次於心臟病、癌症，尤其有 51% 的用藥錯誤，來自醫生一開始就開錯處方。過去曾任萬芳醫院資訊室主任，在醫療與製造業累積達 20 年經驗的龍安靖， 2019 年與醫療人工智慧權威李友專教授共同創立醫守科技，打造智慧型藥物安全系統「藥御守」（ MedGuard ），透過醫療大數據以及 AI 機器學習的人工智慧科技，改善用藥安全，降低醫師開錯藥物的機率。

善用健保資料庫大數據，有效解決醫師開立處方的系統性問題

事實上，台灣非常適合發展醫療 AI 技術，因為台灣健保制度上線多年，病歷電子化程度高，而且資料結構完整，加上臺灣人愛看醫生，進而累積全世界少有的高品質醫療大數據。醫守科技蒐集最近五年高達 13 億筆的處方資料，運用人工智慧從中探索複雜的診斷與用藥關聯以建立模型，並且每年持續更新模型。

龍安靖說，大多數醫師看診時，病患身上 80% 的問題，醫師可透過長年累積的醫學知識開立正確的藥物，但有 20% 的病患由於病因複雜或其他特殊狀況，可能會不當地導致醫師開錯藥。龍安靖長期待在醫療產業，他說開錯藥多半來自系統性問題(註1)，但過去缺乏有效的解決方案。

他舉例，某家教學醫院導入用藥錯誤的預防安全系統高達 40 多個，但是傳統的警示系統只能從大原則提醒，無法針對患者個人實際狀況，從上億種藥物與病因之間的組合給予精確建議，導致大約僅有 5% 的第一線醫師會參考這類只能警示大原則的傳統系統。

7月23日，比翼資本與北醫攜手在2020-Bio Asia亞洲生技大會期間，舉辦新一期輔導新創成果展「TMU X BE Demo Day」，展示來自美國、加拿大國內外10家獨具潛力的新創公司，同時，比翼與北醫選出3家最具海外市場擴展的新創公司分別注入10萬美金的投資，包含龍骨王(LongGood)、醫守科技(AESOP)與美國健康監測解方公司Rhythm Diagnostic System(RDS)。