Diabetes Detection Needs Better Tools. They’re on the Way
Diabetes Detection Needs Better Tools. They’re on the Way
糖尿病检测需要更好的工具，它们正在路上
For decades, a diabetes diagnosis has relied largely on measuring blood sugar and seeing whether it crosses a clinical threshold. But researchers increasingly worry that approach misses millions of people already progressing toward disease. 几十年来，糖尿病的诊断主要依赖于测量血糖，观察其是否超过临床阈值。但研究人员越来越担心，这种方法漏掉了数百万已经在向疾病发展的患者。
Globally, diabetes has become one of the defining health crises of the modern era. According to the World Health Organization, 14 percent of adults were living with diabetes in 2022, up from 7 percent in 1990. In the US, more than 40 million people have diabetes, but around 11 million remain undiagnosed. More than 115 million Americans are estimated to have prediabetes, and roughly 80 percent do not know it. In the UK, around 5.8 million people are living with diabetes, with up to 1.3 million thought to be undiagnosed. 在全球范围内，糖尿病已成为现代社会最严峻的健康危机之一。根据世界卫生组织的数据，2022年有14%的成年人患有糖尿病，而1990年这一比例为7%。在美国，超过4000万人患有糖尿病，但约有1100万人尚未被确诊。据估计，超过1.15亿美国人患有糖尿病前期，其中约80%的人并不知情。在英国，约有580万人患有糖尿病，据信有多达130万人未被确诊。
“We’re talking about an epidemic that, in my mind, is way worse than the Covid pandemic,” says Michael Snyder, professor of genetics at Stanford University. “We need new ways of approaching this.” “我们谈论的是一场在我看来比新冠疫情严重得多的流行病，”斯坦福大学遗传学教授迈克尔·斯奈德（Michael Snyder）说，“我们需要应对它的新方法。”
The danger is not just diabetes itself, but the damage that accumulates silently for years before diagnosis. Persistently elevated blood sugar increases the risk of heart disease, stroke, kidney failure, blindness, and nerve damage. The earlier the disease is identified, the greater the chance of preventing those complications—or avoiding diabetes entirely. 危险不仅在于糖尿病本身，还在于诊断前多年悄然积累的损害。持续升高的血糖会增加心脏病、中风、肾衰竭、失明和神经损伤的风险。疾病发现得越早，预防这些并发症——或完全避免患上糖尿病——的机会就越大。
Diagnosis still relies heavily on measuring glucose levels in the blood, most commonly using the HbA1c test, which estimates average blood sugar over the previous few months. While widely used and generally reliable, it is not infallible. Results aren’t able to reflect certain medical conditions or physiological factors that can impact blood sugar levels. 诊断仍然严重依赖于测量血液中的葡萄糖水平，最常用的是糖化血红蛋白（HbA1c）测试，它用于评估过去几个月的平均血糖。虽然该测试应用广泛且总体可靠，但并非万无一失。其结果无法反映某些可能影响血糖水平的医疗状况或生理因素。
Researchers are increasingly concerned that existing diagnostic tools are also less effective in some populations. Recent studies suggest HbA1c can read falsely low in some Black and South Asian people, delaying diagnosis until the disease is more advanced. 研究人员越来越担心，现有的诊断工具在某些人群中的有效性较低。最近的研究表明，HbA1c在一些黑人和南亚人群中可能出现假性偏低，从而延误诊断，直到疾病发展到更严重的阶段。
That disparity has triggered growing interest in more personalized and data-rich approaches to diabetes detection: ones that combine biomarkers, wearable devices, and artificial intelligence to identify risk earlier and understand the disease in greater detail. 这种差异引发了人们对更个性化、数据更丰富的糖尿病检测方法的浓厚兴趣：即结合生物标志物、可穿戴设备和人工智能，以更早地识别风险并更详细地了解疾病。
At Stanford University, Snyder and colleagues have been exploring whether continuous glucose monitors (CGMs)—wearable sensors that track glucose levels in real time—can reveal hidden metabolic patterns long before conventional diagnosis of Type 2 diabetes, which accounts for around 95 percent of cases. While often associated with obesity—which is an important risk factor—slimmer people can also develop Type 2. Snyder himself developed Type 2 diabetes despite not fitting the stereotypical profile for the disease. 在斯坦福大学，斯奈德及其同事一直在探索连续血糖监测仪（CGM，一种实时跟踪血糖水平的可穿戴传感器）是否能在常规诊断出2型糖尿病（约占病例的95%）之前，揭示隐藏的代谢模式。虽然2型糖尿病通常与肥胖（一个重要的风险因素）有关，但体型较瘦的人也可能患病。斯奈德本人虽然不符合该疾病的典型特征，但也患上了2型糖尿病。
“Glucose regulation involves many organ systems: your liver, your muscle, your intestine, your pancreas, even your brain,” Snyder says. “There are lots of biochemical pathways, and it stands to reason that glucose dysregulation may not just be one bucket.” “血糖调节涉及许多器官系统：肝脏、肌肉、肠道、胰腺，甚至大脑，”斯奈德说，“这里面有许多生化途径，因此血糖失调很可能不仅仅是一种单一的病理机制。”
The Stanford team developed an AI-powered algorithm that analyzes patterns in CGM data to identify different forms of Type 2 diabetes. In tests, the system identified some of these patterns with around 90 percent accuracy. 斯坦福团队开发了一种人工智能算法，通过分析CGM数据中的模式来识别不同类型的2型糖尿病。在测试中，该系统识别出其中一些模式的准确率约为90%。
The researchers believe that the findings could help identify people who are already developing metabolic problems long before a conventional diabetes diagnosis. “It’s a tool that people can use to take preventative measures,” Snyder says. “If the levels trigger a prediabetes warning, dietary or exercise habits could be adjusted, for example.” 研究人员认为，这些发现有助于在常规糖尿病诊断前很久就识别出已经出现代谢问题的人。“这是一个人们可以用来采取预防措施的工具，”斯奈德说，“例如，如果血糖水平触发了糖尿病前期的预警，就可以调整饮食或运动习惯。”
CGMs are also becoming cheaper and more accessible, with many now available over the counter in the US. Snyder believes they could eventually become part of routine preventative health care. “In an ideal world, people would wear them once a year,” he says. “The goal from our standpoint is to keep people healthy versus try to fix them later.” CGM也变得越来越便宜且易于获取，许多产品现在在美国可以非处方购买。斯奈德认为，它们最终可能成为常规预防性医疗保健的一部分。“在理想的情况下，人们每年会佩戴一次，”他说，“我们的目标是保持人们的健康，而不是等到以后再去补救。”
Researchers are also searching for signals outside the bloodstream entirely. 研究人员也在寻找血液循环系统之外的信号。
At Imperial College London, consultant cardiologist Fu Siong Ng and cardiology specialist registrar Arunashis Sau have developed an AI system that analyzes electrocardiograms—simple heart tracings known as ECGs—to identify people at higher risk of developing Type 2 diabetes years before blood sugar rises. 在伦敦帝国理工学院，心脏病学顾问医生傅雄昂（Fu Siong Ng，音译）和心脏病学专科注册医生阿鲁纳希斯·索（Arunashis Sau）开发了一种人工智能系统，通过分析心电图（ECG，即简单的心脏描记图）来识别那些在血糖升高前几年就处于2型糖尿病高风险的人群。
Using around 1.2 million ECGs from hospital records, alongside UK Biobank data, the researchers trained an AI model called AI-ECG Risk Estimation for Diabetes Mellitus (AIRE-DM) to detect subtle cardiovascular changes linked to future diabetes risk. The tool predicted future risk in diverse populations around 70 percent of the time. 研究人员利用医院记录中的约120万份心电图以及英国生物样本库（UK Biobank）的数据，训练了一个名为“糖尿病人工智能心电图风险评估”（AIRE-DM）的模型，以检测与未来糖尿病风险相关的细微心血管变化。该工具在不同人群中预测未来风险的准确率约为70%。
“It’s not perfect,” Ng says. “But it’s at least as good, if not better, than some of the current tools for diagnosis,” he adds. “它并不完美，”傅医生说，“但它至少和目前的一些诊断工具一样好，甚至更好。”
The potential advantage is scale. ECGs are already widely used in hospitals and clinics around the world. If approved for clinical use, tools like AIRE-DM could flag at-risk patients automatically during routine care. 其潜在优势在于规模化。心电图已经在全球的医院和诊所中广泛使用。如果获得临床使用批准，像AIRE-DM这样的工具可以在常规护理中自动标记出高危患者。
“If someone has diabetes, you want to get the sugars down as soon as possible, because their long-term risk is reduced,” Ng says. “And if you know someone may develop diabetes in the future, you can hopefully take preventative action.” “如果某人患有糖尿病，你需要尽快降低其血糖，因为这样可以降低他们的长期风险，”傅医生说，“如果你知道某人未来可能会患上糖尿病，你就有希望采取预防措施。”
That could include intensive weight-loss programs or newer anti-obesity drugs that are increasingly being explored as diabetes prevention tools. “We would never say this is a replacement” to measuring blood sugar and Hb1Ac, Ng says. “Those are sort of the gold-standard diagnostic tests, but we now have additional things you can flag this early.” 这可能包括强化减肥计划或较新的抗肥胖药物，这些药物正越来越多地被探索作为糖尿病预防工具。“我们绝不会说这是对测量血糖和HbA1c的替代，”傅医生说，“那些是某种意义上的黄金标准诊断测试，但我们现在有了额外的方法可以在早期发出预警。”
Type 1 diabetes poses a different screening challenge. Unlike Type 2, it is an autoimmune disease in which the body attacks insulin-producing beta cells in the pancreas. By the time someone’s blood sugar is high enough for a conventional diagnosis, “the horse has bolted,” says Richard Oram, professor of diabetes and nephrology at the University of Exeter. Many of those beta cells have already been lost. 1型糖尿病带来了不同的筛查挑战。与2型不同，它是一种自身免疫性疾病，身体会攻击胰腺中产生胰岛素的β细胞。埃克塞特大学糖尿病与肾脏病学教授理查德·奥拉姆（Richard Oram）表示，当一个人的血糖高到足以进行常规诊断时，“为时已晚”（马已经跑了）。因为许多β细胞已经丧失了。
Until recently, there was little doctors could… 直到最近，医生们能做的还很少……