S3.E3. 成為經典 Upgrade for a classic

200多年來，對於醫生來說，聽診器一直是最重要的器材之一，然而，在診斷罕見的肺部疾病方面，它的適用性卻非常有限─電腦程式應該提供緊急的幫助。

Luca Richeldi是一個謙遜的人，他總以一種溫和並謹慎的方式說話，無論是他的語氣還是說話內容，都是經過再三斟酌後才表達的。他從不會聲稱自己是罕見肺疾病領域的專家，即使事實上，他正是這領域數一數二的先驅。他來自義大利，最初在摩德納(Modena)大學，在罕見肺病領域建立了地位，如今，他在羅馬的Gemelli大學醫院擔任肺病和呼吸系統疾病的教授及主任，他的病人無數，連教皇也是他的病人之一。

Richeldi透過聽診器聽取患者肺部和呼吸道來診斷，然而，即使是經驗最豐富的專家也很快就會遇到瓶頸。

「診斷罕見的肺部疾病，如特發性肺纖維化(IPF)，是非常複雜的」，Richeldi解釋說，用聽診器你可以聽到肺部有些不對的地方，「然而缺乏經驗的醫生，特別是認為不一定需要進一步去確診IPF的醫生，往往都會假設是心臟問題、哮喘或其他肺部疾病，這些疾病都因有具體聲音而影響評斷結果。」當初期症狀發作後，平均需要17個月來確診為IPF，對患者來說是漫漫長路，且浪費許多時間，因為嚴重的疾病通常可能已到末期。確診越早，治療結果越好。

為了幫助醫生早期診斷IPF，百靈佳殷格翰正在開發一種人工智慧的「聽診援助」，其運用原理如下：帶有數位介面的聽診器透過手機與雲端的聲音數據庫相連，然後，使用人工智慧將患者的肺部聲音與來自聲音數據庫的參考數據進行比對。該數據庫是根據大型臨床研究中的肺病記錄和確診資料收集創建的。聽診輔助裝置立即以分數的形式向醫生發送可能的病症，如果該分數高於預先值，則工具將建議醫師進行其他診斷步驟，檢查和程序。

「我們堅信聽診輔助將減少誤診的機會，加速診斷像IPF這樣的罕見疾病。」百靈佳殷格翰人類醫藥業務部門的董事會成員Allan Hillgrove說。他補充說，該設備涵蓋了以前尚未研究的領域，因此將為患者創造出真正的附加價值。

(本文單純報導百靈佳殷格翰在國外的科技創新與應用，目前台灣並沒有該應用的導入，同時呼籲：疾病的預防與治療都應與專業醫療人員配合，尊重專業意見，不宜自行判斷。)

For more than 200 years, the stethoscope has been one of the most important devices for physicians. However, when it comes to diagnosing rare pulmonary diseases, it is only of limited suitability. An algorithm should provide urgent assistance.

Luca Richeldi is an unassuming man. He speaks in a quiet and considered way and tends to be reserved – both in his tone and in what he says. He would never claim to be an expert in his field: the diagnosis and treatment of rare pulmonary diseases. Yet, that is exactly what he is. Hailing from Italy, he originally established the chair for rare pulmonary diseases at the University of Modena. Today, he practises at the Gemelli University Hospital in Rome as a professor and director for pulmonary and respiratory diseases – and counts no less a person than the Pope as one of his patients.

His standard diagnostic tool is the stethoscope. Richeldi uses it to listen to his patients’ lungs and airways in order to determine the cause of their complaints. However, even the most experienced specialists quickly come up against their limits.  “Diagnosing rare pulmonary diseases, such as idiopathic pulmonary fibrosis (IPF), is extremely complicated,” he explains. “With the stethoscope, you can hear that something isn’t right with the lungs,” says Richeldi. “However, inexperienced doctors – in particular – do not necessarily go on to identify IPF, but rather assume that cardiac problems, asthma or other pulmonary diseases are the cause of the very specific sound pattern.” It takes an average of 17 months to confirm a diagnosis of IPF after the onset of the initial symptoms. An eternity for patients – and lost time, since the serious disease can often be terminal. The earlier it is identified, the better the treatment outcomes are.

In order to support the identification of IPF at an earlier stage, Boehringer Ingelheim is developing an artificial intelligence-based “Auscultation Aid” which works as follows: a stethoscope with a digital interface is linked via a mobile phone to a cloud-based large sound database. Using artificial intelligence, a patient’s lung sound recordings are then compared with reference data from the sound database. This database was created from recorded and confirmed diagnoses of lung diseases, collected in large clinical studies. The auscultation aid immediately sends the physician a result in the form of a “probability score” for a certain lung disease. If this score is higher than a pre-specified treshold value, the tool will provide suggestions to the examining physician for additional diagnostic steps, examinations and procedures.

“We firmly believe that this auscultation aid will reduce misdiagnoses and identify rare diseases like IPF much faster.”
ALLAN HILLGROVE
Member of the Board of Managing Directors with responsibility for Human Pharma

“We firmly believe that this auscultation aid will enable a reduction in misdiagnoses and identify rare diseases like IPF much faster,” says Allan  Hillgrove, Member of the Board of Managing Directors with responsibility for the Human Pharma Business Unit at Boehringer Ingelheim. He adds that the device covers a previously unresearched area and will therefore create genuine added value for patients.