An artificial intelligence tool has helped to identify a rare neurological condition in a woman from Wales after she spent four years being incorrectly diagnosed by medical professionals. Phoebe Tesoriere, 23, from Cardiff, was initially told by doctors that she was experiencing anxiety, depression and epilepsy, despite presenting with progressively worsening symptoms such as seizures, mobility problems and balance problems. Following a severe seizure that left her in a coma for three days in July 2025, Phoebe consulted ChatGPT to investigate her condition. The AI tool identified multiple possible conditions, among them hereditary spastic paraplegia—a rare genetic disorder that impacts the nervous system. After presenting this finding to her GP, genetic testing confirmed the finding, at last offering clarity after years of frustration and poor management within the NHS.
A Four-Year Passage Across Medical Uncertainty
Phoebe’s medical problems began well before her diagnosis. Throughout her early years, she experienced a ongoing difficulty walking, which she attributed to being born without a hip socket and undergoing surgical correction as an baby. She also struggled with difficulties with balance and was tested for dyspraxia, a disorder of the nervous system impacting physical motor control, though the results proved negative. These preliminary indicators would subsequently become important in establishing her root cause, yet at the time they remained unexplained and frequently disregarded by doctors.
The situation deteriorated markedly when Phoebe was 19 years old. She experienced a seizure whilst at work, a frightening experience that should have prompted comprehensive enquiry. Instead, doctors ascribed the incident to anxiety—a diagnosis that was thereafter recorded in her medical records despite Phoebe having no previous experience with anxiety disorders. She characterised herself as “a really happy, bubbly person” before this incident, making the diagnosis seem notably inconsistent. This incorrect characterisation would set the tone for prolonged stretches of inappropriate treatment and growing exasperation.
- Childhood limp resulting from hip surgery, not primary neurological condition
- Balance problems tested for dyspraxia but results proved negative
- First seizure at 19 incorrectly identified as anxiety episode
- Anxiety diagnosis added to medical records lacking proper investigation
The Game-Changing Breakthrough: ChatGPT’s Surprising Finding
After spending three days in a coma after a severe seizure in July 2025, Phoebe found herself at a critical juncture. Upon recovery, a doctor delivered a bewildering statement: she did not have epilepsy after all, but rather anxiety. This contradicted years of treatment and the earlier epilepsy diagnosis she had been given in 2022. Frustrated by the circular nature of her healthcare experience and struggling to be heard by healthcare professionals, Phoebe made the decision to turn to an alternative approach for answers. She inputted her complete symptom profile into ChatGPT, the AI chatbot that has become more common in healthcare discussions.
The AI tool’s output proved notably thorough. ChatGPT produced a range of potential conditions that might explain Phoebe’s collection of clinical presentations—progressive weakness, balance difficulties, seizures, and paralysis episodes. Among the suggestions was a rare genetic neurological disorder affecting the spinal cord, a uncommon hereditary neurological disorder that impacts the spinal cord and causes advancing rigidity and weakness in the legs. What distinguished this suggestion from earlier clinical assessments was its specificity and the way it cohesively explained multiple symptoms that had earlier remained scattered across various diagnoses. Phoebe recognised immediately that this condition might at last offer the unified explanation she had been seeking.
From Uncertainty to Verification
Armed with the recommendation from ChatGPT, Phoebe approached her GP with details regarding hereditary spastic paraplegia. Rather than dismissing the AI-generated hypothesis outright, her doctor treated the recommendation with seriousness and arranged genetic testing. This pragmatic approach turned out to be transformative. The genetic tests returned positive results, confirming that Phoebe did indeed have hereditary spastic paraplegia—validating both the analysis provided by the AI chatbot and, more importantly, finally delivering a definitive diagnosis after four years of medical misdiagnosis and uncertainty.
The confirmation represented a significant moment for Phoebe, though it also highlighted the constraints of her previous medical care. Her GP, Dr Rebeccah Tomlinson, has since acknowledged the role artificial intelligence can play in healthcare research, whilst stressing the significance of expert validation. She pointed out that when people use artificial intelligence tools to investigate health concerns, these findings should be discussed with qualified medical professionals before drawing conclusions. This measured approach recognises both the potential benefits of artificial intelligence in medicine and the irreplaceable value of professional medical expertise.
Comprehending Hereditary Spastic Paraplegia
Hereditary spastic paraplegia (HSP) is a uncommon hereditary neurological condition marked by progressive weakness and stiffness in the legs. The condition affects the spinal cord, particularly the nerve pathways controlling leg movement. HSP comes in various types, with more than 80 genetic variations identified, complicating diagnosis for medical professionals. Symptoms usually appear gradually and can encompass difficulty walking, balance difficulties, muscular weakness, and in some cases, seizures. The disease’s uncommon nature means most clinicians have little experience recognising it, which partly explains why Phoebe’s condition remained undiagnosed for so long despite displaying classic indicators of the disorder.
| Aspect | Details |
|---|---|
| Primary Affected Area | Spinal cord and nerve fibres controlling leg movement |
| Genetic Variants | Over 80 known genetic forms of the condition |
| Common Symptoms | Progressive leg weakness, stiffness, balance difficulties, and occasionally seizures |
| Inheritance Pattern | Can be inherited in autosomal dominant, autosomal recessive, or X-linked patterns depending on genetic variant |
The intricacy of HSP’s genetic diversity presents significant diagnostic challenges. With various modes of inheritance and variable symptom presentations across different forms, even seasoned neurological specialists can find it difficult to recognise the condition without genetic testing. Phoebe’s case highlights how uncommon hereditary conditions can be overlooked when symptoms overlap with more common conditions like epilepsy or anxiety disorders, underscoring the critical importance of thorough genetic investigation when standard diagnoses do not adequately account for a patient’s presenting symptoms.
The Expanding Debate Surrounding AI in Medical Care
Phoebe’s experience has revived debate about the place of AI in diagnostic processes and healthcare delivery. Whilst her case demonstrates AI’s potential to uncover overlooked conditions, medical professionals and scientists advise against treating chatbots as diagnostic tools. A latest University of Oxford investigation found that individuals pursuing healthcare advice through AI were given varied guidance, spanning from helpful information to risky suggestions. This variation creates significant challenges for patients attempting to differentiate trustworthy advice from unreliable recommendations, especially when managing complex or rare conditions that necessitate expert expertise and thorough medical assessment.
The incident also raises important questions about patient autonomy and the healthcare system’s responsiveness to people who feel their voices aren’t being heard. Many patients resort to AI tools out of frustration when conventional medical routes don’t work, highlighting potential gaps in diagnostic processes. Phoebe’s willingness to use ChatGPT came from experiencing profound loneliness during her medical journey and the exhaustion of fighting to be believed. This reflects a broader concern that patients increasingly seek alternative resources when conventional healthcare systems fail to deliver solutions, indicating that improvements in diagnostic protocols and communication with patients may be equally important as setting out clear rules for AI tool usage in healthcare settings.
Specialist Views on AI-Powered Medical Devices
Dr Rebeccah Tomlinson, a general practitioner, recognises that patients may reasonably employ AI chatbots to research medical issues but emphasises the critical importance of discussing findings with registered healthcare practitioners. This balanced perspective acknowledges people’s right to obtain knowledge whilst preserving clinical supervision. The British Medical Association and other healthcare bodies have similarly advocated for artificial intelligence incorporation within formal clinical systems rather than as a substitute for professional diagnosis. Experts stress that AI tools should complement rather than circumvent medical knowledge, especially considering the complexity of uncommon hereditary disorders demanding expert understanding and genetic testing confirmation.
Cardiff and Vale University Health Board’s response to Phoebe’s case acknowledged her difficult experience whilst tacitly supporting the challenges doctors face when diagnosing rare conditions affecting relatively few patients. Medical professionals contend that hereditary spastic paraplegia’s scarcity and numerous genetic variations make it inherently difficult to identify without specific genetic testing. However, the case has prompted reflection within the medical sector about improving diagnostic pathways for patients with atypical presentations. Healthcare leaders are increasingly acknowledging that developing improved communication frameworks and reduced barriers for referrals for genetic testing could prevent similar diagnostic delays whilst maintaining rigorous clinical standards.
- AI should support professional medical judgment, not substitute for medical expertise and diagnostic assessment
- Patients working with AI systems must discuss findings with certified medical practitioners before acting
- Healthcare systems must enhance diagnostic frameworks for uncommon disorders and atypical symptom presentations
Moving Ahead: Life After Diagnosis
Since receiving her verified diagnosis of hereditary spastic paraplegia in 2025, Phoebe Tesoriere has started adjusting to life with a good grasp of her condition. The genetic confirmation has given her answers after prolonged periods of uncertainty and misdiagnosis, allowing her healthcare team to create a more focused treatment approach. Phoebe has become an advocate for improved diagnostic pathways, sharing her story publicly to raise awareness of hereditary spastic paraplegia amongst patients and medical professionals alike. Her experience has highlighted the importance of listening to patients who persistently report symptoms that don’t match conventional diagnoses, and she remains engaged with medical professionals to manage her condition effectively.
Phoebe’s path has also sparked broader dialogue within the NHS about diagnostic protocols for rare neurological conditions. Whilst she recognises the legitimate obstacles doctors face when diagnosing uncommon genetic disorders, she continues to preventing others from experiencing the prolonged four-year diagnostic process she endured. Her case has sparked consideration amongst medical professionals about reducing barriers for referrals for genetic testing and strengthening communication with individuals with atypical symptom patterns. Moving forward, Phoebe believes her story will motivate both healthcare professionals and patients to persist in seeking answers, demonstrating that rare disorders, though difficult to diagnose, should never be written off as psychological in nature.