In our previous post we used AI to prioritise research priorities for Parkinson’s Disease. But how do we judge if it’s any good? Well, we went and explored the literature and found this 2024 paper in Nature Reviews Neurology Parkinson disease therapy: current strategies and future research priorities. It is unclear how they arrived at their list, I assume expert opinion.

But the comparison—using ChatGPT—is fascinating. Not just in terms of where they align, but also in their differences. For me, the standout difference is that Nature Reviews Neurology places a strong emphasis on interventions such as pharmaceutical drugs and surgical treatments. This seems intuitively correct, but it also reminds me of Iain Chalmers’ work on research prioritisation.

Iain has done extensive work in this area and was the driving force behind the James Lind Alliance. In his 2015 paper Patients’, clinicians’ and the research communities’ priorities for treatment research: there is an important mismatch highlights a significant divide between research agendas. The study found that patients and clinicians often prioritise non-drug treatments, such as physical or psychological therapies, while researchers tend to focus on drug treatments.

Specifically, only 18% of the treatment priorities identified by patients and clinicians were drug-related, compared to 37% in non-commercial trials and 86% in commercial trials. The authors emphasise the need for the research community to better align with the priorities of patients and healthcare professionals, advocating for increased efforts to address issues most relevant to those directly affected.

Comparison of Research Priorities: Nature Reviews Neurology vs. Trip Database Blog

I’ve compared the research priorities outlined in Nature Reviews Neurology (“Parkinson Disease Therapy: Current Strategies and Future Research Priorities”) with those in the Trip Database Blog (“Identifying Research Gaps in Parkinson’s Disease – Prioritised”). Below is a breakdown of where they align and where they diverge.

---

1. Shared Research Priorities

1.1 Early Detection & Biomarkers

Both sources emphasize the importance of developing reliable biomarkers for early diagnosis and monitoring disease progression.

• Nature Reviews Neurology focuses on integrating sensitive biomarkers (biofluid, imaging, digital) to track disease progression and support early intervention.
• The Trip Database Blog highlights the need for non-invasive biomarkers (e.g., saliva, blood, microbiota) to improve accessibility and reduce inequities in early detection.

1.2 Advancing Symptomatic Treatments

Both sources prioritize improving symptom management, particularly for motor and non-motor complications.

• Nature Reviews Neurology discusses refining deep brain stimulation (DBS), surgical, and infusion therapies to target levodopa-resistant symptoms and delay complications.
• The Trip Database Blog explores optimal exercise regimens and cognitive training interventions to improve motor function and cognitive symptoms.

1.3 Disease Modification Strategies

Both sources recognize the need for treatments that alter the disease course, rather than just alleviating symptoms.

• Nature Reviews Neurology discusses potential disease-modifying therapies, including α-synuclein-targeting treatments, neuroinflammation approaches, and genetic therapies (LRRK2, GBA mutations, GLP-1 receptor agonists like Exenatide).
• The Trip Database Blog specifically calls out GLP-1 receptor agonists (like Exenatide) as a promising intervention and highlights the need to determine which patients will benefit most from disease-modifying therapies.

---

2. Differences Between the Two Sources

2.1 Role of Artificial Intelligence (AI) (Trip Database Blog Only)

• The Trip Database Blog explicitly prioritizes the use of AI in early diagnosis to improve accuracy and reduce misdiagnosis rates.
• Nature Reviews Neurology does not specifically mention AI, though its emphasis on biomarkers could theoretically align with AI-driven diagnostics.

2.2 Personalized vs. Population-Level Approaches

• Nature Reviews Neurology emphasizes a personalized medicine approach, tailoring therapies based on genetic and biomarker profiling.
• The Trip Database Blog is more focused on population-level solutions, such as broad biomarker screening and AI integration to ensure equitable early diagnosis.

2.3 Focus on Exercise & Lifestyle (Trip Database Blog Only)

• The Trip Database Blog highlights the need to identify the most effective exercise regimens for symptom management and potential disease modification.
• Nature Reviews Neurology does not explicitly discuss exercise or lifestyle interventions, although it does acknowledge environmental and genetic risk factors in disease development.

2.4 Deep Dive into Disease Mechanisms (Nature Reviews Neurology Only)

• Nature Reviews Neurology provides a much deeper discussion of underlying disease mechanisms, including α-synuclein aggregation, genetic mutations, and neuroinflammatory pathways.
• The Trip Database Blog focuses more on practical applications (e.g., biomarker accessibility, AI tools, and exercise programs) rather than mechanistic research.

---

Conclusion

Key Overlaps:

✅ Early Detection & Biomarkers – Both emphasize the importance of finding reliable, accessible biomarkers.
✅ Symptom Management – Both focus on improving treatments for motor and non-motor symptoms.
✅ Disease Modification – Both support research into disease-modifying therapies, particularly GLP-1 receptor agonists (like Exenatide).

Key Differences:

❌ AI in Diagnosis – Only Trip Database Blog prioritizes the role of AI in improving diagnosis.
❌ Exercise & Lifestyle – Only Trip Database Blog emphasizes exercise regimens as a research priority.
❌ Personalized Medicine vs. Population-Level Approaches – Nature Reviews Neurology focuses on tailored treatments based on genetics and biomarkers, while the Trip Database Blog highlights broad interventions for all patients.
❌ Mechanistic Research Focus – Nature Reviews Neurology is heavily focused on underlying disease mechanisms, while the Trip Database Blog is more focused on applied interventions.

UPDATE: Shortly after publishing this blog, I had a thought—does any literature exist on prioritisations? It turns out there is, which inspired a new blog: Identifying Research Gaps in Parkinson’s Disease – Prioritised and Compared.

“All gaps are weighted equally so it would also be interesting to see if it could provide some sort of ranking.” Building on yesterday’s discussion on research priorities, I leveraged AI/LLMs to do the heavy lifting. I asked two separate LLMs (ChatGPT and DeepSeek) to prioritize the original list based on things such as potential impact on disease burden, equity, and feasibility of implementation. I then used the LLMs to reconcile their suggestions, leading to the following final prioritization:

Top Priority (High Impact, Feasible, and Addresses Urgent Needs & Equity)

These research areas have the highest potential to significantly alter disease progression, improve early diagnosis, and enhance patient quality of life, while being feasible for near-term implementation.

1. Lack of Reliable Biomarkers for Early Detection

• Why? Early diagnosis is critical for slowing disease progression and improving quality of life. Biomarkers (e.g., α-synuclein, mitochondrial DNA, blood-based markers) could transform Parkinson’s care by enabling earlier intervention.
• Feasibility: Advances in genetic, imaging, and blood-based biomarkers are progressing rapidly.
• Equity: Biomarkers would increase access to earlier diagnosis, especially if they can be non-invasive and cost-effective.

2. Non-Invasive Biomarkers for Disease Detection & Progression Monitoring

• Why? Saliva, blood, and microbiota-based markers offer less invasive and more accessible alternatives to expensive imaging or invasive procedures.
• Feasibility: These biomarkers are already under active investigation and could be implemented relatively quickly with further validation.
• Equity: Improves accessibility in low-resource settings, benefiting underserved populations.

3. Integration of AI for Early & Accurate Diagnosis

• Why? AI-based tools enhance diagnostic accuracy, potentially reducing misdiagnoses and allowing earlier intervention.
• Feasibility: AI-based algorithms for imaging, digital cognitive assessments, and motor function tracking are already in development and testing.
• Equity: If designed with diverse datasets, AI can expand diagnostic access to regions with limited specialists.

4. Understanding Non-Motor Symptoms as Early Indicators

• Why? Non-motor symptoms (e.g., cognitive decline, gut microbiota changes, depression, psychiatric symptoms) often appear years before motor symptoms, making them valuable for early diagnosis.
• Feasibility: Ongoing research suggests non-motor symptoms could be integrated into diagnostic criteria with further validation.
• Equity: Improves early detection and personalized treatment in diverse populations.

5. Role of GLP-1 Receptor Agonists as Disease-Modifying Treatments

• Why? GLP-1 agonists (e.g., Lixisenatide, Exenatide) have shown promise in slowing disease progression, addressing a major unmet need.
• Feasibility: These drugs are already approved for diabetes and other conditions, making repurposing feasible.
• Equity: If effective, they could be integrated into treatment regimens globally.

6. Best Exercise Type & Intensity for Motor Symptoms

• Why? Exercise is a low-cost, widely accessible intervention with proven benefits for motor symptoms and no significant side effects.
• Feasibility: Exercise is already widely studied, but optimal regimens for symptom management still need refinement.
• Equity: Can be implemented globally at low cost, benefiting all socioeconomic groups.

7. Cognitive Training Interventions for Parkinson’s-Related Dementia & Mild Cognitive Impairment

• Why? Cognitive decline significantly impacts quality of life and caregiver burden, yet current treatments are limited.
• Feasibility: Digital and behavioral cognitive training interventions are emerging and could be scaled up.
• Equity: Can be widely accessible via mobile apps, online programs, and community health initiatives.

---

Final Adjustments & Notes on Reconciliation

• Both original lists shared the same core priorities, but some terminology and emphasis differed.
• Equity considerations were harmonized—especially in how early detection, AI, and exercise could reach underserved populations.
• Feasibility analysis was refined to ensure short-to-medium-term implementation is realistic.
• The ranking maintains a balance between high-impact, scalable interventions and urgent research gaps.

Final comments: Looks and sounds plausible but we have no way of verifying the ‘accuracy’ of the above. As with yesterday, and interesting experiment none-the-less!

We host one of the largest dedicated collections of systematic reviews on the web, with over 550,000 reviews available. With this vast resource comes a responsibility: ensuring that users critically assess the validity of the systematic reviews they access.

Systematic reviews sit at the top of the evidence pyramid/hierarchy, but their inclusion in this category does not automatically guarantee high-quality evidence. While well-conducted systematic reviews deserve their status, many are poorly executed and risk misleading users.

To address this, we have developed a scoring system designed to help users gauge the reliability of systematic reviews. By identifying markers of both rigorous methodology and potential weaknesses, this system will generate a score displayed alongside each review, providing a quick and informed assessment of its credibility.

These scores may be controversial, and we recognize the limitations of any scoring system. To ensure transparency, we provide an explanation of each scoring element and how it impacts the final score. Ultimately, the primary aim of this system is to encourage healthy scepticism among our users.

Elements

Age of review?: The older the review the more likely new research has been published, meaning the systematic review out of date. Not exact as there might be no new research, but hopefully the sentiment is clear.

• 0-2 years = Good
• 3-5 = OK
• 6+ = Cause for concern

Number of Authors?: Systematic reviews require rigorous methodology, and having a single author raises concerns about bias and robustness. While more isn’t always better, a minimum of three authors is generally seen as best practice.

• 1 author = Red flag
• 2 authors = Cause for concern
• ≥ 3 = No concerns

Databases Searched ?: A systematic review should search multiple databases to minimize bias and ensure comprehensive coverage of relevant literature. A review relying on just one database is highly problematic, and even two may be insufficient.

• 1 database = Bad
• 2 = Cause for concern
• ≥ 3 = No concerns

Mention of registration?: Registering systematic reviews (e.g., in PROSPERO) is considered best practice. Reviews published before PROSPERO’s launch in 2011 won’t have this option, but they may already be affected by the Age of Review criterion.

• Mentions PROSPERO or similar registry = Good
• No mention of registration = Cause for concern

Mention of quality tools ?: Quality assessment frameworks such as GRADE, AMSTAR, and PRISMA enhance systematic review rigor. Their inclusion signals a commitment to high methodological standards.

• Mentions any of these tools = Good
• No mention = Cause for concern

Retraction watch check for the article and referenced work?: We check the Retraction Watch database for articles that are included in systematic reviews. Any retraction gets a Red Flag, regardless of the contribution to the systematic review.

• No retractions = No cause for concern
• Any retractions = Red flag

Each element is given a score and these are combined to assign one of three scores:

Some obvious issues with the score, here are a handful, I’m sure others will highlight other issues:

• Abstract-based assessment – The system evaluates what is explicitly mentioned in the abstract, not the full text.
• Text-matching accuracy – Automated detection of databases, PROSPERO registration, etc., may not be 100% accurate.
• Reliance on DOIs – Missing digital object identifiers (DOIs) can disrupt the scoring process.
• No text – Our system needs text to analyse, so no text = no score. Text might be absent if there are redirects, or other website anomalies.
• Arbitrary thresholds – The cutoffs for each category are subjective and may evolve over time.

Whitelisted sources

For a number of trusted publishers we default to ‘Appears promising’, these are typically national bodies such as IQWiG, CADTH, NICE and Cochrane. We still look for retractions (where the publication has a DOI) and will ‘red flag’ them if there is a retraction.

Summary

So, there you have the scoring system, flaws and all. Despite these imperfections, we are excited to release this scoring system. Its primary purpose is to encourage critical thinking, ensuring that users do not accept systematic reviews at face value but instead engage with them sceptically and thoughtfully.

UPDATE: After a reader’s comment we have now generated a prioritised list.

Following on from last weeks post on research gaps, I took the top 200 articles on Trip for the search Parkinson’s Disease and sent these to ChatGPT and DeepSeek asking them to generate a list of research gaps, based on the 200 articles. I then reconciled them to create a list whereby it was included if both LLMs suggested the research gaps.

I asked ChatGPT to explain the inclusion, this is the ‘conversation’:

Trip: In generating this list to what extent what is informed by the initial 200 articles?

ChatGPT: The final list of research gaps was directly informed by the 200 articles, but in a structured and synthesized manner….The research gaps were extracted based on recurring topics, unanswered clinical questions, and areas where further studies were explicitly mentioned in systematic reviews, meta-analyses, and clinical trials.

Trip: But how did you know these were research gaps?

ChatGPT: The research gaps in Parkinson’s disease were identified through:

• Reviewing the 200 articles and extracting recurring themes.
• Extracting explicitly stated research gaps from systematic reviews and meta-analyses.
• Noting controversies and inconsistencies across studies.
• Assessing where the evidence base is weak or inconclusive.
• Identifying new technologies or therapies that require validation.
• Cross-referencing with a second research gap list to confirm priority areas.
• Refining the final list to only include gaps mentioned twice, ensuring strong evidence support.

It all feels a bit like magic. Is it any good, does it work? Here’s the result:

Early Diagnosis & Biomarkers

• Lack of reliable biomarkers for early detection: Current genetic, imaging, and blood-based biomarkers (e.g., α-synuclein, mitochondrial DNA copy number, inflammatory markers) are being studied, but their clinical utility remains uncertain.
• Integration of AI for early and accurate diagnosis: Machine learning and AI-based tools (e.g., imaging analysis, digital cognitive assessments) require validation in diverse populations.
• Non-invasive biomarkers for disease detection and progression monitoring (e.g., blood, saliva, fecal microbiota): These could improve accessibility and patient compliance but need further validation.

Disease Progression & Prognostic Markers

• Understanding non-motor symptoms as early indicators: Cognitive decline, psychiatric symptoms, and gut microbiota changes often precede motor symptoms but are not well integrated into diagnostic criteria.
• Prediction of disease trajectory: Research is needed on fMRI connectivity alterations, functional MRI biomarkers, and gait analysis to predict disease progression.

Novel & Personalized Therapies

• Role of GLP-1 receptor agonists as disease-modifying treatments: Lixisenatide and Exenatide have shown promise in slowing motor disability progression, but their long-term effects need further validation.
• Targeting neuroinflammation and ferroptosis: Drugs like PTC-041 and natural compounds (e.g., Campsis grandiflora, Cissus tuberosa) show neuroprotective effects but lack large-scale clinical trials.
• Microbiome-based therapies: Fecal microbiota transplantation (FMT) is being explored for symptom management, but more research is needed on gut-brain axis mechanisms.
• Efficacy and safety of non-invasive brain stimulation (e.g., transcranial direct current stimulation, vagus nerve stimulation, MRI-guided focused ultrasound) for Parkinson’s symptoms.

Optimizing Exercise & Rehabilitation Strategies

• Best exercise type and intensity for motor symptoms: Tai Chi, aerobic exercise, resistance training, and boxing have been studied, but optimal protocols for symptom management remain unclear.
• Impact of exercise on non-motor symptoms (e.g., cognition, mood, sleep): Most research focuses on motor symptoms, while cognitive and emotional benefits of physical activity are less understood.
• Role of technology in rehabilitation: Augmented reality, gamified virtual reality environments, and sensor-based remote monitoring are promising but lack large-scale trials.

Cognitive Decline & Mental Health

• Cognitive training interventions for Parkinson’s disease-related dementia and mild cognitive impairment.
• Psychosocial impact of Parkinson’s disease: Studies on identity changes, caregiver burden, and quality of life interventions are limited.

Gender & Health Disparities in Parkinson’s Disease

• Underrepresentation of women in clinical trials: Many studies focus predominantly on male participants, potentially overlooking gender-specific disease progression and treatment responses.
• Global variations in Parkinson’s disease prevalence and treatment: Research is needed to understand geographic and socioeconomic disparities in diagnosis and care.

Advanced Disease & Palliative Care

• Management of late-stage complications: More research is needed on dysphagia, psychosis, and palliative care approaches for advanced Parkinson’s patients.
• Integration of digital monitoring for remote care: Devices for remote symptom tracking are emerging but lack validation for real-world clinical decision-making.

Gut-Brain Axis & Parkinson’s Disease

• Role of gut microbiota in disease onset and progression: Changes in the microbiome are linked to Parkinson’s, but causation remains unclear.
• Association between Parkinson’s and inflammatory bowel disease (IBD): A potential link exists, but research on therapeutic implications is lacking.

Pharmacological Treatment Optimization

• Personalized medicine approaches: Biomarker-driven treatment selection for motor and non-motor symptoms needs further development.
• Balancing effectiveness and side effects of levodopa and adjunct therapies: Strategies for reducing dyskinesia and motor fluctuations require further study.

Emerging Technologies in Diagnosis & Treatment

• Wearable and AI-driven diagnostics: Digital monitoring for motor fluctuations, gait disturbances, and cognitive decline needs validation.
• Non-invasive imaging biomarkers: Cross-modality PET image synthesis and novel neuroimaging techniques require clinical standardization.

Long-Term Outcomes and Real-World Data

• Long-term outcomes of Parkinson’s disease treatments (e.g., deep brain stimulation, levodopa, exercise) in real-world settings.

The final bit of experimentation was to explore these research gaps with those identified by the James Lind Alliance Priority Setting Partnerships. The James Lind Alliance (JLA) Priority Setting Partnerships (PSPs) bring together patients, caregivers, and healthcare professionals to identify and prioritize unanswered research questions in specific health conditions. The goal is to ensure that future research aligns with the real-world needs of those affected by the condition.

They have a list of unanswered questions for Parkinson’s Disease and although dated 2014 it was still worth asking the LLM to compare Trip’s generated list of research gaps and the James Lind List. It’s a long list so here is the conclusions of the comparison:

Key Observations

• High Alignment: Most JLA priorities align with existing research gaps, confirming that these areas remain critical and underexplored.
• Three Missing Gaps: Some JLA priorities (urinary problems, pain management, hospital medication training) do not appear in the research gaps. This suggests these may be less studied but still important for patient care.
• Overlapping Themes: Several gaps (e.g., exercise, personalized medicine, digital monitoring, cognitive training) apply to multiple JLA priorities, reinforcing their importance in Parkinson’s research.

So, there you go, a simple experiment. An interesting experiment. A worthwhile experiment? It was simple to do, it was definitely interesting, but worthwhile – I’ve no idea!

It doesn’t have to be Spanish, it could be French, German, Italian etc

In our embrace of LLMs I was wondering about their use in translation. We did this translation:

Spanish original: Tengo osteoporosis. Columna lumbar T-score -3.3. Cadera izda T-score -1.0. Se me ha producido fractura con aplastamiento y edema D11. La reumatóloga me ha mandado Denosumab. He leído efectos secundarios y no se qué hacer. Gracias

English translation: I have osteoporosis. Lumbar spine T-score -3.3. Left hip T-score -1.0. I have experienced a compression fracture with edema at T11. My rheumatologist prescribed Denosumab. I have read about the side effects and I don’t know what to do. Thank you.

Apparently this is very accurate. Could we harness this power into Trip? Allowing such roles as:

• Translate Spanish/German/Italian etc terms into their English equivalent to use within Trip
• Non-native English users being able to check their translated (English) terms
• Allowing free-text questions, in non-English, and searching Trip and getting the results page translated into Spanish etc
• Use any Q&A system we release to allow questions in Spanish/German/French etc and give the reply in the language of choice

In our recent work on automated Q&A we posted an answer to the question What is the Role of H. pylori Eradication in Asymptomatic Individuals? The final recommendation was:

“For asymptomatic individuals, H. pylori eradication should be considered on a case-by-case basis, prioritizing those with gastric cancer risk factors (e.g., family history, high-prevalence areas). Universal eradication is not supported by current guidelines in low-risk populations.“

Spanish translation: Para individuos asintomáticos, se debe considerar la erradicación de H. pylori de forma individualizada, priorizando a aquellos con factores de riesgo de cáncer gástrico (por ejemplo, antecedentes familiares, áreas de alta prevalencia). La erradicación universal no cuenta con el respaldo de las guías actuales en poblaciones de bajo riesgo.

German translation: Für asymptomatische Personen sollte die H. pylori-Eradikation fallweise in Betracht gezogen werden, wobei Personen mit Risikofaktoren für Magenkrebs (z. B. familiäre Vorbelastung, Gebiete mit hoher Prävalenz) priorisiert werden sollten. Eine universelle Eradikation wird von den aktuellen Leitlinien in Bevölkerungsgruppen mit geringem Risiko nicht unterstützt.

Japanese translation: 無症状の個人に対しては、H. pylori の除菌を症例ごとに検討し、胃がんのリスク因子（例：家族歴、高い有病率の地域）を持つ人を優先するべきです。低リスク集団においては、現在のガイドラインでは普遍的な除菌は推奨されていません。

I expect these are all good translations!

Resource is a potential issue, these translations are not free and if it proves popular it might be too heavy a burden (anyone know of any funding opportunities?). However, the benefits are huge. It would immediately open up the English-language evidence-base to people who can’t speak English. In addition it could support non-native English speakers to get the most out of Trip.

Déjame saber qué piensas. (Spanish)
Fais-moi savoir ce que tu penses. (French)
Lass mich wissen, was du denkst. (German)
Fammi sapere cosa ne pensi. (Italian)
Me diz o que você acha. (Portuguese)
Дай мне знать, что ты думаешь. (Russian)
让我知道你的想法。 (Chinese – Simplified)
讓我知道你的想法。 (Chinese – Traditional)
あなたの考えを教えてください。 (Japanese)
네 생각을 알려줘. (Korean)
دعني أعرف ما هو رأيك. (Arabic)
Laat me weten wat je denkt. (Dutch)
मुझे बताएं कि आप क्या सोचते हैं। (Hindi)
Ne düşündüğünü bana söyle. (Turkish)
Låt mig veta vad du tycker. (Swedish)
Daj mi znać, co myślisz. (Polish)
Cho tôi biết bạn nghĩ gì. (Vietnamese)
บอกให้ฉันรู้ว่าคุณคิดอย่างไร (Thai)
Πες μου τη γνώμη σου. (Greek)

We continue our work exploring LLMs and we’ve done more work based on last week’s question What is the Role of H. pylori Eradication in Asymptomatic Individuals?. We have asked the LLM to identify, from the question and answer, any research gaps. The response is below. It looks comprehensive, but is it any good?

---

1. Data on Low-Risk Populations

• Gap: Limited evidence on the role of H. pylori eradication in asymptomatic individuals from low-risk populations (e.g., North America, Western Europe), where gastric cancer incidence is lower.
• Rationale: Most studies focus on high-risk regions, leaving uncertainty about the cost-effectiveness and clinical impact of eradication in low-risk settings.

---

2. Adverse Effects and Risks of Eradication Therapy

• Gap: Insufficient discussion of the adverse effects and risks associated with eradication therapy, including:
  • Antibiotic resistance and its impact on treatment efficacy.
  • Side effects of eradication regimens (e.g., gastrointestinal discomfort, allergic reactions).
  • Potential disruption of the gut microbiome and long-term consequences.
• Rationale: A balanced assessment of risks versus benefits is crucial, especially for asymptomatic individuals who may not immediately benefit from treatment.

---

3. Impact on Non-Gastric Conditions

• Gap: Limited exploration of the systemic effects of H. pylori eradication on non-gastric conditions, such as:
  • Potential protective effects against asthma, inflammatory bowel disease, or other immune-modulated conditions.
  • Potential risks, such as increased incidence of GERD or esophageal adenocarcinoma.
• Rationale: Understanding the broader health implications of eradication is essential for informed decision-making.

---

4. Cost-Effectiveness in Diverse Healthcare Systems

• Gap: Lack of detailed cost-effectiveness analyses across different healthcare systems and economic settings, including:
  • Comparison of eradication programs with other preventive strategies (e.g., endoscopic screening).
  • Economic barriers to implementation in low- and middle-income countries.
• Rationale: Cost-effectiveness is critical for policy-making and resource allocation, especially in diverse global contexts.

---

5. Long-Term Follow-Up Data

• Gap: Insufficient long-term data on the durability of benefits and potential late adverse effects of eradication, particularly in:
  • Low-risk populations.
  • Subgroups with specific genetic or comorbid conditions.
• Rationale: Long-term studies are needed to assess the sustainability of eradication benefits and identify any delayed risks.

---

6. Optimal Screening Strategies

• Gap: Limited evidence on the most effective and cost-efficient screening protocols for asymptomatic individuals, including:
  • Tailored strategies for different demographic groups (e.g., age, genetic risk factors).
  • Integration of screening with other preventive health measures.
• Rationale: Effective screening strategies are essential for identifying individuals who would benefit most from eradication.

---

7. Role of Probiotics and Adjunct Therapies

• Gap: Lack of detailed discussion on the role of probiotics and adjunct therapies in improving eradication outcomes, including:
  • Effectiveness of specific probiotic strains or formulations.
  • Potential for adjunct therapies to reduce side effects or enhance eradication rates.
• Rationale: Adjunct therapies could optimise eradication protocols, but more evidence is needed to guide their use.

---

8. Ethical Considerations

• Gap: Absence of discussion on ethical considerations related to treating asymptomatic individuals, such as:
  • Balancing the benefits of prevention against the risks of unnecessary treatment.
  • Ensuring informed consent in population-based eradication programs.
• Rationale: Ethical considerations are critical for public health interventions, particularly when treating individuals who may never develop complications.

---

9. Impact of Vaccination (Future Directions)

• Gap: Limited exploration of vaccination as an alternative or complementary strategy to eradication therapy, including:
  • Current progress in H. pylori vaccine development.
  • Potential impact of vaccination on the need for eradication in asymptomatic individuals.
• Rationale: Vaccination could revolutionise H. pylori management, but its role remains underexplored.

---

10. Subgroup and Population-Specific Data

• Gap: Insufficient data on how subpopulations (e.g., by age, genetic factors, or comorbid conditions) respond to eradication therapy.
• Rationale: Tailored interventions based on subgroup-specific data could improve the efficacy and safety of eradication programs.

---

11. Long-Term Impact Beyond Cancer Prevention

• Gap: Limited understanding of the long-term impact of eradication on gastric physiology and overall health, including:
  • Potential benefits (e.g., reduced inflammation, improved nutrient absorption).
  • Unintended consequences (e.g., changes in gastric acid secretion, microbiome alterations).
• Rationale: A comprehensive understanding of long-term effects is necessary to weigh the risks and benefits of eradication.

---

Summary of Rationalised Knowledge Gaps

Gap	Details
Low-risk populations	Limited data on benefits in regions with low gastric cancer incidence.
Adverse effects of eradication	Risks and side effects of eradication therapy in asymptomatic individuals.
Non-gastric conditions	Impact of eradication on immune modulation and other diseases.
Cost-effectiveness	Economic analyses in diverse healthcare systems.
Long-term follow-up data	Durability of benefits and late adverse effects.
Optimal screening strategies	Effective and cost-efficient screening protocols for diverse populations.
Role of probiotics and adjuncts	Effectiveness of probiotics and adjunct therapies in eradication regimens.
Ethical considerations	Ethical implications of treating asymptomatic individuals.
Vaccination	Potential role of vaccination as an alternative strategy.
Subgroup-specific data	Response to eradication in subpopulations (e.g., age, genetics, comorbidities).
Long-term impact beyond cancer	Broader effects of eradication on gastric physiology and overall health.

---

Addressing the Gaps

To address these gaps, future research and reviews should:

1. Include studies from low-risk populations to assess the universal applicability of eradication programs.
2. Evaluate the risks and side effects of eradication therapy in asymptomatic individuals.
3. Investigate the systemic effects of H. pylori eradication on non-gastric conditions.
4. Conduct cost-effectiveness analyses in diverse economic settings.
5. Extend long-term follow-up studies to assess the durability of benefits and late adverse effects.
6. Develop and evaluate optimal screening strategies for diverse populations.
7. Explore the role of probiotics and adjunct therapies in improving eradication outcomes.
8. Discuss ethical considerations in population-based eradication programs.
9. Investigate the potential of vaccination as a preventive strategy.
10. Generate subgroup-specific data to tailor eradication interventions.
11. Study the long-term impact of eradication on gastric physiology and overall health.

By addressing these gaps, the evidence base can be strengthened, leading to more informed and balanced recommendations for H. pylori eradication in asymptomatic individuals.

We’ve been really busy of late! The Mind Maps have just been released, the systematic review scoring system is nearly finished and we’ve been having lots of fun with automated clinical question answering. Next up, we’re tackling mobile optimisation, as we know the current experience isn’t where it should be.

Now, we’re planning the next round of improvements – and we need your input. Over the past 25 years, Trip has grown by listening to our users, and we’re continuing that tradition. Your feedback has shaped Trip, and now it’s time for more of it.

We’ve put together a short survey to explore different aspects of your search experience. It covers six key themes, with just a few questions in each, taking no more than 15 minutes to complete. Your insights will directly help us make Trip better for you and for other users.

We’d love for you to take part every response counts!

Click here to take part in the survey 🙂

We host one of the largest dedicated collections of systematic reviews on the web, with over 550,000 reviews available. With this vast resource comes a responsibility: ensuring that users critically assess the validity of the systematic reviews they access.

Systematic reviews sit at the top of the evidence pyramid/hierarchy, but their inclusion in this category does not automatically guarantee high-quality evidence. While well-conducted systematic reviews deserve their status, many are poorly executed and risk misleading users.

To address this, we are developing a scoring system designed to help users gauge the reliability of systematic reviews. By identifying markers of both rigorous methodology and potential weaknesses, this system will generate a score displayed alongside each review, providing a quick and informed assessment of its credibility. Below is a mock-up of how each score will look:

There are 4 graphics of which 3 are actual, meaningful, scores:

• Appears promising
• Potential concerns
• Bad

We’re working through a few issues but everything is looking promising for a release in the near future (famous last words).

We’ve been having a lot of fun working hard on an automated Q&A system – we’ve been working on and off for over 12 months. Recently we’ve made some big strides and below is an example Q&A. It’s impressive (although I could easily be accused of being biased)!

What is the Role of H. pylori Eradication in Asymptomatic Individuals?

Helicobacter pylori (H. pylori) is a bacterium that infects the stomach lining and is a leading cause of peptic ulcer disease, gastritis, and gastric cancer. While many infected individuals remain asymptomatic, H. pylori is classified as a Group 1 carcinogen by the World Health Organization (WHO) due to its association with gastric cancer. The question of whether to treat asymptomatic individuals is debated, with considerations including the potential to reduce gastric cancer risk and the risks of antibiotic resistance and microbiome disruption.

---

1. Does Eradication of H. pylori Reduce Gastric Cancer Risk?

Evidence from Meta-Analyses and Clinical Trials:

• A meta-analysis of randomized controlled trials found that H. pylori eradication reduced the incidence of gastric cancer by approximately 34% (Ford et al., 2014).
• Another systematic review and meta-analysis concluded that individuals who received eradication therapy had a 38% reduction in gastric cancer incidence (Lee et al., 2016).
• A cost-effectiveness study using a Markov model showed that a screen-and-treat approach was both effective in preventing gastric cancer and cost-saving in the long term, particularly in high-risk populations (Areia et al., 2013).

Applicability to Western Populations:

• Most studies demonstrating the benefits of eradication are from Asian populations, where the background incidence of gastric cancer is high. The applicability to Western populations, where gastric cancer incidence is lower, remains uncertain (Sugano et al., 2015).

---

2. Are There Official Guidelines Supporting Eradication in Asymptomatic Individuals?

Evidence from Guidelines:

• 2022 Chinese National Clinical Guideline: Recommends screening and treatment for H. pylori in high-risk populations but does not advocate for universal eradication in asymptomatic individuals (Liu et al., 2022).
• Saudi H. pylori Working Group: Provides management recommendations but does not support mass eradication in asymptomatic individuals (Alrashed et al., 2021).
• ESPGHAN/NASPGHAN Guidelines: Focus on treatment for children and adolescents with symptoms rather than asymptomatic individuals (Jones et al., 2017).

Targeted “Screen-and-Treat” Strategy:

• A study in the U.S. population found that targeted eradication for individuals with a family history of gastric cancer was beneficial (Choi et al., 2018).

---

3. Are There Risks Associated with Eradication?

Evidence-Based Risks:

• Antibiotic Resistance: Rising resistance rates to common H. pylori treatments (e.g., clarithromycin, metronidazole) are a significant concern, particularly in regions with high antibiotic use (Savoldi et al., 2018).
• Gastrointestinal Microbiome Disruption: Eradication therapy can alter the gut microbiome, potentially leading to dysbiosis and other gut-related symptoms (Ianiro et al., 2016).

Theoretical Risks:

• In low-risk individuals, the benefits of treatment may not outweigh the risks, particularly given the potential for antibiotic resistance and microbiome disruption.

---

4. Summary and Recommendations

Evidence-Based Recommendations:

• H. pylori eradication reduces gastric cancer risk, particularly in high-risk groups (e.g., those with a family history of gastric cancer or living in high-prevalence regions) (Ford et al., 2014).
• Screen-and-treat strategies are cost-effective in high-risk populations (Areia et al., 2013).

Guideline Recommendations:

• Current guidelines recommend a selective approach rather than mass eradication, particularly in low-risk Western populations (Sugano et al., 2015).

Risks to Consider:

• The risks of antibiotic resistance and microbiome disruption must be weighed against the potential benefits of eradication (Savoldi et al., 2018).

---

Final Recommendation

For asymptomatic individuals, H. pylori eradication should be considered on a case-by-case basis, prioritizing those with gastric cancer risk factors (e.g., family history, high-prevalence areas). Universal eradication is not supported by current guidelines in low-risk populations.

---

Key References:

1. Ford et al., 2014
2. Lee et al., 2016
3. Areia et al., 2013
4. Sugano et al., 2015
5. Savoldi et al., 2018