疾病的種類越來越複雜,相對治療各種疾病、併發症的藥物處方箋亦然,然而醫生面對病人的看診時間並未增加,反而越來越短,從北醫衍生獨立的醫守科技,今年獲選中小企業暨新創署「黑科技」類的潛力新創,結合AI技術針對處方箋的診斷與用藥,透過大數據深度學習分析,獨家開發「臨床診斷推論網路模型」,幫助醫師執行臨床用藥決策,強化病人安全。 開錯藥物的新聞時有所聞,醫守科技創辦人暨執行長龍安靖以退燒止痛的普拿疼ACETAMINOPHEN為例,在台灣一年就有3000次開錯,不小心開成青光眼的用藥ACETAZOLAMIDE,兩種藥名長得很像,導致非常容易開錯處方箋。 醫守科技的臨床推論網路模型將每種藥對應的症狀、疾病連結對應,專司防守用藥錯誤的「RxPrime藥御守」如果發現處方箋裡有不合理的用藥,或少開了藥,系統就會提醒建議,等於是請AI幫忙醫生開處方箋時加一道防線。 醫守科技透過蒐集大量數據加上AI的深度學習分析推論,最早從收集台灣健保資料,後來加上美國的資料,目前累積超過32億筆的病歷數據,且不斷在更新中,幾乎涵蓋各科所有疾病;龍安靖說,醫療團隊與AI團隊密集定期會議討論,打磨更新商品的資訊功能;目前競爭對手有各有不同方法,例如美國是找很多專家從上建立指導策略,人做出的知識,說明描述比較清楚,但很難做到全科系完整的覆蓋。 除了用藥識別,相同技術也多元彈性運用在解決醫療、用藥不同痛點,例如健保申請,經常容易出現的漏帳或超收,透過AI推論網路模型可以更有效率校正;此外藥廠有些新藥推廣不易,將資訊放在平台,可以讓新藥直接與第一線看診醫師接觸。新藥只有十年專利,但前3、4年都在研發、推廣,過了專利期學名藥就出來了,對於藥廠在市場推廣新藥是一大利器。 近幾年智慧醫療研發創新名目眾多,醫守是少數在智慧醫療領域成功出海的新創公司,且團隊第一筆資金就來自美國矽谷,團隊提出的解決方案受到肯定,在台灣醫守的產品已有將近一半醫學中心採用,也成功打入美國市場,龍安靖表示,醫界的改革通常很慢、很謹慎,醫守科技提出的並非顛覆性改革,而是站在幫助醫療人員的立場,解決現有的痛點,醫療的挑戰很多,這也是醫守科技的使命與機會。 Reference:
報導原文
DxPrime 好完診 : 第一時間做好全面診斷 世界衛生組織表示,全世界大多數成年人在一生中都可能至少被誤診一次。實際上在美國,平均每年有80萬人因診斷錯誤而終生失能或死亡,這背後代表著80萬個家庭與整體社會沈重的負擔。 診斷錯誤,包括任何被忽略、延誤或不正確的診斷。一旦診斷錯了,接下來整體治療重點也會跟著走錯。然而診斷決策的過程並不是線性的,每個步驟都充滿不確定性,在醫療人力日漸短缺,能夠分給每個病人的時間變少的趨勢下,診斷錯誤的可能性越來越高。 臨床推論輔助 臨床推理能力是醫療人員必備的能力,醫生根據病人主訴的症狀、表徵等一連串資訊與證據,推論出病人得到什麼疾病。隨著科技、生活環境改變與人口高齡化帶來的多重疾病等問題,加劇了疾病形成原因與表現的複雜程度,使得醫生要分析考量的因素變多。 醫守的臨床深度推論AI模型能夠自動綜合分析診斷、藥物、手術、檢驗檢查及病歷中的自由文字等,直接為醫師完成其原本要做的推論分析,即時呈現運算結果給醫生評估,縮短其自行蒐集與分析數據的時間。 難以跨越的臨床知識高牆 2019年醫守從臺北醫學大學正式分割獨立,在這之前,醫守的核心模型已經發展了長達十年的臨床研究基礎,模型從一開始先單純探索疾病與疾病、藥物與藥物之間的關係,慢慢發展到分析疾病與藥物的交互關係。 近幾年醫守不斷擴充病歷數據庫,收錄了臺灣健保、美國聯邦醫療保險CMS、全球知名醫院 Mayo Clinic,以及DARTNet等資料,累計到 32億筆總量,AI運算模型也淬鍊出五百萬條臨床關聯知識,形成更強大的臨床深度推論網路與醫療情境適應能力。 及早預測併發症 即時介入與管理 醫療照護受限於知識與科學發展,多半以「一體適用(one size fits all)」的治療指引,再加上「包含或排除」、「嘗試錯誤」等方法逐步修正診斷與治療計畫。DxPrime好完診運用科技幫助醫生更有效率地因應病人的個體化差異,針對不同科別與病人性別,即時探索所有診斷、共病與併發症之可能性,藉由及早預測併發症,提醒醫師適時介入與管理,避免後續引發更嚴重的健康問題。 具解釋能力的AI 促進推論思考與鑑別 自從人工智慧開始商業化後,其黑盒子現象經常引起爭議。DxPrime好完診能夠依據所點選的建議項目,直接展示其與臨床證據之間的網路關係,不僅提高醫師對產品的信賴,也幫助醫師確認臨床合理性,提高診斷決策品質。醫師藉由DxPrime分析大量臨床關聯知識的能力,作為鑑別診斷等決策評估工具,減少診斷過程的不確定性與盲點,並據此與病人進一步溝通,更能掌握病情,促進病人安全與治療成效。
醫守科技是一家以AI人工智慧進行「醫療防錯」的公司,致力於協助醫師避免醫療疏失、守護病人安全。歷經十年研發的「DxPrime 好完診」AI模型,不僅能輔助臨床診斷,還能預測並處理潛在併發症;它不僅提供診斷結果,還會展示推論過程,減少診斷過程中的不確定性,最重要的是,能夠即時提醒醫師「開錯診斷」。 醫守科技創業五年來,守護了一百多萬的病人、申請二十一項發明專利、通過五個醫院人體試驗委員會(IRB)臨床試驗,發表十多篇論文。這些創舉不僅在臺灣,全球也沒幾家公司能做到。醫守科技執行長龍安靖擁有醫療和科技雙重背景,早在十幾年前,他的博士論文便聚焦「用藥安全」,也從那時起他立下志業,確保每位患者都能享有安全且精準的醫療照護。 目前全臺已有30多家醫療院所與醫守科技簽約,使用「DxPrime 好完診」系統來輔助診療工作。不少醫師對這套系統讚譽有加,感謝醫守科技團隊研發出如此實用的醫療輔助工具,顯著提升了臨床診斷的準確性與效率,世界知名醫院美國梅奧診所也是醫守科技的重要投資者。 全球布局與精準化募資策略 傲人成績背後,除了仰賴全球頂尖的醫療機構與32億筆病歷大數據的支持,還有創辦人暨執行長龍安靖率領團隊逐步拓展,現在臺灣和美國兩地都有據點。儘管數位醫療需求龐大,但醫療院所的財務預算週轉緩慢,營業收入至少都要一年到一年半才能看到成果,因此必須不斷地尋找投資人。 然而初期的投資者選擇並不理想,合作過程中常發現彼此目標不符,讓團隊疲於奔命、陷入困境。特別是兩年前的募資階段,那段時間為了要同時處理臺灣和美國的工作,幾乎是進入「無時差狀態」,每天都睡不到三小時。經歷了這些挑戰,龍安靖逐漸摸索出更精準的募資策略:他開始慎選合作對象,為公司設立極高的篩選標準,專注於找到合適的領投機構合作,才讓公司進入穩定發展的軌道。 步步為營:醫守科技的長跑精神 「無論順境或逆境,都要把該做的事情做好!」這是醫守科技創辦人龍安靖的經營信念。喜歡跑步的他,也常以跑馬拉松來比喻創業之路:「一開始跑得快,未必能最後奪冠;用自己熟悉的步調,努力不懈地堅持到底才是關鍵。」堅持初心、履行企業責任,醫守科技在醫療創新中不斷突破,將使命感化為行動力。這股信念推動著「DxPrime 好完診」AI模型,成為醫生不可或缺的臨床輔助工具,顯著提升患者安全與醫療品質,為精準醫療領域帶來全新高度。 Reference:
第23屆新創事業獎得獎專輯, 經濟部, 2024 醫守科技「DxPrime好完診」,獨家臨床深度推論AI模型,協助醫師在第一時間完成全面診斷,降低診斷錯誤的風險,獲選經濟部中小及新創企業署「潛力新創選拔」績優廠商。 臨床推理能力是醫療人員必備的核心技能,然而隨著科技進步、生活環境改變以及高齡化現象,讓疾病的成因與表現變得複雜,也讓醫生面臨更為複雜的診斷挑戰。世界衛生組織曾公布,大多數人一生中都可能至少被誤診一次!以美國來說,每年約有80萬人因診斷錯誤而終生失能或死亡,造成許多家庭和社會沈重的負擔。 醫守科技執行長龍安靖表示,診斷錯誤通常包括不正確、忽略或延誤的診斷。一旦診斷有誤,隨之而來的治療也將偏離正軌。在醫療人力不足和每個病人看診時間縮短的趨勢下,診斷錯誤的風險也相應而升。 醫守獨家的臨床深度推論AI模型,大幅縮短了醫生自行搜集與分析資料的時間,直接將AI推論的結果呈現在醫生面前,提供給醫師作為鑑別診斷的評估參考。DxPrime好完診可解釋各項診斷建議與臨床證據之間的關係,幫助醫生理解AI的推論邏輯,減少診斷過程中的不確定性,醫生亦能藉此與病人進一步溝通,避免未知的盲點。同時,DxPrime好完診也能提前預測病人可能出現的併發症,及時提醒醫師介入與管理,避免後續衍生更嚴重的健康問題。 執行長龍安靖指出,醫守運用32億筆的國際電子病歷發展出臨床推論網路運算模型,淬煉出具有五百萬條臨床知識的關聯網,能夠在診斷、藥物、手術、檢驗檢查及病歷中的自由文字之間來回推論,除了用於提升診斷精準度,也能應用於用藥、手術、醫療編碼等決策流程,不僅預防錯誤,更進一步促進醫療決策的全面思考,提升治療成效。目前醫守科技正積極拓展臺灣、美國與中國的市場,持續開發更多元的臨床應用產品。 A Safer Tomorrow: AESOP Technology's Battle Against Look-Alike, Sound-Alike Medication Errors10/24/2023
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: PR Newswire
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
|
全部
|