{"id":268571,"date":"2026-01-05T15:19:07","date_gmt":"2026-01-05T15:19:07","guid":{"rendered":"https:\/\/www.europesays.com\/ie\/268571\/"},"modified":"2026-01-05T15:19:07","modified_gmt":"2026-01-05T15:19:07","slug":"the-chatbot-will-see-you-now-how-ai-is-being-trained-to-spot-mental-health-issues-in-any-language-global-development","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ie\/268571\/","title":{"rendered":"The chatbot will see you now: how AI is being trained to spot mental health issues in any language | Global development"},"content":{"rendered":"

When patients telephone Butabika hospital in Kampala, Uganda<\/a>, seeking help with mental health problems, they are themselves assisting future patients by helping to create a therapy chatbot.<\/p>\n

Calls to the clinic helpline are being used to train an AI algorithm that researchers hope will eventually power a chatbot offering therapy in local African languages.<\/p>\n

One person in 10<\/a> in Africa struggles with mental health issues, but the continent has a severe shortage of mental health workers<\/a>, and stigma is a huge barrier to care in many places. AI could help solve those problems wherever resources are scarce, experts believe.<\/p>\n

Prof Joyce Nakatumba-Nabende, scientific head of the AI Lab at Makerere University. Photograph: Courtesy Kampala Geopolitics Conference<\/p>\n

Prof Joyce Nakatumba-Nabende is scientific head of the Makerere AI Lab at Makerere University. Her team is working with Butabika hospital and Mirembe hospital, in Dodoma in neighbouring Tanzania.<\/p>\n

Some callers just need factual information on opening times or staff availability, but others talk about feeling suicidal or reveal other red flags about their mental state.<\/p>\n

\u201cSomeone probably won\u2019t say \u2018suicidal\u2019 as a word, or they will not say \u2018depression\u2019 as a word, because some of these words don\u2019t even exist in our local languages,\u201d says Nakatumba-Nabende.<\/p>\n

After removing patient-identifying information from call recordings, Nakatumba-Nabende\u2019s team uses AI to comb through them and determine how people speaking in Swahili or Luganda \u2013 or another of Uganda\u2019s dozens of languages \u2013 might describe particular mental health disorders such as depression or psychosis.<\/p>\n

In time, recorded calls could be run through the AI model, which would establish that \u201cbased on this conversation and the keywords, maybe there\u2019s a tendency for depression, there\u2019s a tendency for suicide [and so] can we escalate the call or call back the patient for follow up\u201d, Nakatumba-Nabende says.<\/p>\n

Current chatbots tend not to understand the context of how care is delivered or what is available in Uganda, and are available only in English, she says. The end goal is to \u201cprovide mental health care and services down to the patient\u201d, and identify early when people need the more specialised care offered by psychiatrists.<\/p>\n

The service could even be delivered over SMS messaging for people who don\u2019t have a smartphone or internet access, Nakatumba-Nabende says.<\/p>\n

The advantages of a chatbot are numerous, she says. \u201cWhen you automate, it\u2019s faster. You can easily provide more services to people, and you can get a result faster than if you were to train someone to do a medicine degree and then specialise in psychiatry and then do the internship and the training.\u201d<\/p>\n

Promoting World Mental Health Day in Kampala, Uganda, in 2020. Photograph: Xinhua\/Alamy<\/p>\n

Scale and scope are also important: an AI tool is easily accessible any time. And, Nakatumba-Nabende says, people are reluctant to be seen seeking mental health care in clinics because of stigma. A digital intervention bypasses that.<\/p>\n

She hopes the project will mean the existing workforce can \u201cprovide care to more people\u201d and \u201creduce the burden of mental health disease in the country\u201d.<\/p>\n

\u2018Does this thing operate well in Zulu?\u2019 … is not a question that the FDA, I think, has ever considered<\/p><\/blockquote>\n

Bilal Mateen, Path<\/p>\n

Miranda Wolpert, director of mental health for the Wellcome Trust, which is funding a variety of projects looking at AI for mental health globally, says technology offers promise in diagnosis. \u201cWe are very, at the moment, reliant on people filling in, in effect, paper and pencil questionnaires, and it may be that AI can help us think more effectively about how we can identify someone struggling,\u201d she says.<\/p>\n

Technology-facilitated treatments might also look very different to the traditional mental health options of either talking therapy or medication, Wolpert says, citing Swedish research on how playing Tetris could alleviate PTSD symptoms<\/a>.<\/p>\n

Regulators are, however, still grappling with the implications of greater use of AI in healthcare. For example, the South African Health<\/a> Products Regulatory Authority (SAHPRA) and health NGO Path are using funding from Wellcome to develop a regulatory framework.<\/p>\n

Bilal Mateen, chief AI officer at Path, says it is important for countries to develop their own regulation. \u201c\u2018Does this thing operate well in Zulu?\u2019, which is a question that South Africa cares about, is not one that the FDA [US Food and Drug Administration], I think, has ever considered,\u201d he says.<\/p>\n

Christelna Reynecke, chief operations officer at SAHPRA, wants users of an AI algorithm for mental health to have the same assurance as someone taking a medicine that it has been checked and is safe. \u201cIt\u2019s not going to start hallucinating, and giving you strange results, and causing more harm than good,\u201d she says.<\/p>\n

Staff at Uganda\u2019s Butabika hospital, which has launched an AI call centre in collaboration with Makerere University and Mirembe hospital in Tanzania. Photograph: Courtesy of Butabika hospital<\/p>\n

In the background is the spectre of suicides linked to chatbot use, and cases where AI appears to have fuelled psychosis<\/a>.<\/p>\n

Reynecke wants to develop an advanced monitoring system that can identify \u201crisky\u201d outputs from generative AI tools in real time. \u201cIt cannot be something that\u2019s an \u2018after the event\u2019, so far after the event that you may have put other patients at risk, because you didn\u2019t intervene fast enough,\u201d she says.<\/p>\n

The UK regulator the Medicines and Healthcare Products Regulatory Agency (MHRA) has a similar initiative<\/a> and is working with tech companies to understand how best to regulate AI in medical devices.<\/p>\n

Regulators need to decide what risks are important to monitor, says Mateen. Sometimes, the benefits will outweigh the potential harm to the extent that there is \u201can impetus for us to get this into people\u2019s hands because it will help them\u201d.<\/p>\n

It is hoped that the chatbot could help alleviate the mental health workforce gap not just in Africa, but around the world. Illustration: Getty Images<\/p>\n

While much of the conversation around AI revolves around chatbots such as Google Gemini and ChatGPT<\/a>, Mateen suggests \u201cthere is so much more that AI and generative AI … could be used to do\u201d, such as using it to train peer counsellors to provide higher quality care, or finding people the best kind of treatment more quickly.<\/p>\n

\u201cA billion people around the world<\/a> today are experiencing a mental health condition,\u201d he says. \u201cWe don\u2019t just have a workforce gap in sub-Saharan Africa; we have a workforce gap everywhere \u2013 speak to someone in the UK about how long they have to wait for access to talking therapies.<\/p>\n

\u201cThe unmet need everywhere could be met more effectively if we had better access to safe and effective technology.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"When patients telephone Butabika hospital in Kampala, Uganda, seeking help with mental health problems, they are themselves assisting…\n","protected":false},"author":2,"featured_media":268572,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[261],"tags":[291,289,290,18,19,17,82],"class_list":{"0":"post-268571","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-artificial-intelligence","10":"tag-artificialintelligence","11":"tag-eire","12":"tag-ie","13":"tag-ireland","14":"tag-technology"},"share_on_mastodon":{"url":"https:\/\/pubeurope.com\/@ie\/115843167900270479","error":""},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts\/268571","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/comments?post=268571"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/posts\/268571\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/media\/268572"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/media?parent=268571"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/categories?post=268571"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ie\/wp-json\/wp\/v2\/tags?post=268571"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}