Truace
Subscribe
Good Space a ranking of the record

TheGood surrounding AI

574 documented gains are on the board. 82% rest on at least one peer-reviewed study, and 8% clear the high-evidence bar. Health carries 49% of it. The latest was filed Oct 16, 2026.

Every gain on the board, one square each, shaded by the strength of its evidence. High 45 Moderate 529 Emerging 0
574 results
Show filters and sorting

The board · page 3 of 20

61
Evidence-backed gainPeer-reviewedHealth

Machine learning models trained on routine nursing home assessment data predicted functional decline in residents with type 2 diabetes with high accuracy, pointing to modifiable risk factors for early identification.

Source article: Mental Health and Cognitive Predictors of Functional Decline in Nursing Home Residents with Type 2 Diabetes

Clinical Gerontologist
Reader signal

How should this claim be treated?

62
Evidence-backed gainPeer-reviewedHealth

A neural network built on six predictors including coagulation parameters discriminated difficult from non-difficult single-incision cholecystectomy cases in internal validation, potentially aiding patient selection and surgical planning.

Source article: A Predictive Model Integrating Coagulation Profiles for Preoperative Risk Stratification of Difficult Single-Incision Laparoscopic Cholecystectomy: A Retrospective Cohort Study Based on Explainable Machine Learning

Surgical Laparoscopy, Endoscopy & Percutaneous Techniques
Reader signal

How should this claim be treated?

63
Evidence-backed gainPeer-reviewedEducation

At MTs Diniyyah Putri Lampung, AI chatbots, dhikr and muhasabah apps, and visual learning platforms were reported to increase learning motivation and strengthen students' emotional engagement with Islamic learning.

Source article: The Utilization of Artificial Intelligence (AI) Technology in Islamic Religious Education to Develop Students’ Spiritual Character at MTs Diniyyah Putri Lampung, Gedong Tataan District, Pesawaran Regency, Lampung Province

International Journal of Post Axial: Futuristic Teaching and Learning
Reader signal

How should this claim be treated?

65
Evidence-backed gainPeer-reviewedHealth

A mixture-kernel support vector machine trained on graph-theory features from emotion-regulation brain regions best distinguished 32 fibromyalgia patients from 30 controls on sensitivity and AUC, suggesting a route to less subjective diagnosis.

Source article: Graph theory-based machine learning for automated fibromyalgia diagnosis using fMRI during an emotional task

PLOS One
Reader signal

How should this claim be treated?

66
Evidence-backed gainPeer-reviewedBusiness

Cities that gained ultra-high voltage transmission projects saw listed enterprises advance their AI development more than comparison cities, through stronger innovation, larger resource bases and better regional finance.

Source article: Energy infrastructure construction and enterprises' Artificial Intelligence development: Evidence from China's ultra-high voltage transmission projects

PLOS One
Reader signal

How should this claim be treated?

67
Evidence-backed gainPeer-reviewedScience

Combining linked-segment physics with a BiLSTM network estimated vertical ground reaction forces from seven wearable IMUs with errors below a high-accuracy reference in intra- and inter-subject tests.

Source article: Load-Decomposition Learning Enhances Ground Reaction Force Estimation Using IMUs

IEEE Transactions on Neural Systems and Rehabilitation Engineering
Reader signal

How should this claim be treated?

68
Evidence-backed gainPeer-reviewedEducation

University EFL students taught with a structured ChatGPT protocol showed larger IELTS-style writing score gains than a control class, and the advantage was still present four weeks after the intervention.

Source article: From ChatGPT to Classroom Practice: A Visualized Protocol for Generative AI-Supported Feedback, Critical Thinking, and EFL Writing Instruction

Journal of Visualized Experiments
Reader signal

How should this claim be treated?

69
Evidence-backed gainPeer-reviewedEducation

Dental students randomized to ChatGPT-guided VR skill training scored higher on an immediate operative skills test than students taught by an on-site instructor.

Source article: Effects of Generative AI-Supported Virtual Reality Dental Skill Training on Learning Performance, Visual Behavior, and Cortical Activation Among Dental Students: Stratified Randomized Controlled Trial

Journal of Medical Internet Research
Reader signal

How should this claim be treated?

70
Evidence-backed gainPeer-reviewedHealth

A tongue-image framework that identifies seven tongue attributes and models how they interact reached 0.751 accuracy and 0.767 AUC for liver fibrosis risk screening, with results better than the compared graph and multimodal models.

Source article: An expert routing-driven graph framework from tongue multi-task features to liver fibrosis prediction

Engineering Applications of Artificial Intelligence
Reader signal

How should this claim be treated?

71
Evidence-backed gainPeer-reviewedHealth

In Markov models for Costa Rica, using AI as a first reader in breast screening and lung cancer diagnosis was projected to lower costs while increasing quality-adjusted life-years over 10 years.

Source article: Cost-Effectiveness of AI in Breast Cancer Screening and Lung Cancer Diagnostics: A Case Study From Costa Rica

Value in Health Regional Issues
Reader signal

How should this claim be treated?

72
Evidence-backed gainPeer-reviewedClimate

A machine learning classifier applied to multi-sensor satellite and terrain data produced a consistent circumpolar wetland baseline that can improve methane flux models and conservation planning.

Source article: PAWI: The first high-resolution, multi-class, Pan-Arctic Wetland Inventory

Journal of Environmental Management
Reader signal

How should this claim be treated?

73
Evidence-backed gainPeer-reviewedHealth

AI can pull latent diagnostic information from routinely acquired cardiac signals, which could improve ischemia detection where noise, operator dependence and incomplete signal capture limit accuracy.

Source article: Artificial Intelligence for Cardiac Ischemia Detection: A Review of Biosensor, Biomarker, and Imaging Applications

Sensors
Reader signal

How should this claim be treated?

74
Evidence-backed gainPeer-reviewedHealth

An agentic generative AI framework produced disease concept and model structure diagrams for breast cancer and a rare disease that were checked against literature and by modelers and clinicians.

Source article: Conceptualising Health Economic Models Using a Graph Retrieval-Augmented, Agentic AI Framework with Human-in-the-Loop Validation: Proof-of-Concept Study

PharmacoEconomics - Open
Reader signal

How should this claim be treated?

75
Evidence-backed gainPeer-reviewedHealth

An automated PET-CT algorithm can measure body composition changes in advanced prostate cancer patients and identify those on systemic therapy who are at risk for muscle wasting.

Source article: An artificial intelligence algorithm characterizes the deterioration of body composition from systemic therapy for patients with advanced prostate cancer

JNCI: Journal of the National Cancer Institute
Reader signal

How should this claim be treated?

76
Evidence-backed gainPeer-reviewedEducation

Among 64 Economics Education students, greater use of AI-based learning applications was significantly associated with stronger critical thinking skills, explaining about 26% of the variation.

Source article: Analysis of the Influence of the Use of Artificial Intelligence (AI) on Students' Critical Thinking Abilities in Learning

Educational Journal of Learning Technology
Reader signal

How should this claim be treated?

77
Evidence-backed gainPeer-reviewedHealth

Gastroenterologists rated ChatGPT-4's Turkish-language answers to common colonoscopy questions highly, with over 70% of ratings at 4 or above in every domain, outperforming Google Bard.

Source article: Large language models' performance in answering common patient questions about colonoscopy: an expert-based evaluation

BMC Gastroenterology
Reader signal

How should this claim be treated?

78
Evidence-backed gainPeer-reviewedScience

Adding an Inspector agent that checks each proposal against nine physical constraints increased the share of generated constitutive models passing all checks, from 90% to 95% for Opus and from 47% to 60% for Kimi.

Source article: LLM-driven design of physics-constrained constitutive models: Two agents are better than one

Machine Learning for Computational Science and Engineering
Reader signal

How should this claim be treated?

79
Evidence-backed gainPeer-reviewedHealth

The AWMP deep learning model predicted cervical cancer survival 4.74% better than the mean of four comparator methods and helped identify four prognosis-linked genes and a B-cell subset tied to immune response.

Source article: Cervical cancer survival analysis by integrating multi-omics data through an adaptive weighted deep neural network

Computational Biology and Chemistry
Reader signal

How should this claim be treated?

80
Evidence-backed gainPeer-reviewedPolicy

On the DeepAccident benchmark, grounding crash analysis in predefined legal rules cut object hallucination to 2.8% and reached 94.0% legal accuracy, giving reviewers traceable evidence-to-rule chains.

Source article: Toward explainable traffic crash liability analysis via neural-symbolic multimodal reasoning: Integrating visual perception with legal knowledge graphs

Accident Analysis & Prevention
Reader signal

How should this claim be treated?

81
Evidence-backed gainPeer-reviewedClimate

A machine learning model using sensor, soil, nitrogen and free climate data predicted wheat yield before nitrogen application with R² of 0.81, versus 0.12 for the INSEY benchmark.

Source article: Wheat yield prediction using machine learning, proximal sensing, nitrogen and climate data for Oklahoma

Precision agriculture
Reader signal

How should this claim be treated?

82
Evidence-backed gainPeer-reviewedHealth

AI-generated synthetic patients reproduced treatment-effect estimates for escalation versus early intensive therapy in MS while preserving privacy, suggesting a way to extend real-world evidence.

Source article: Validation of generative artificial intelligence techniques for synthetic data generation in multiple sclerosis research: A comparison with real-world evidence from the Italian multiple sclerosis registry

Multiple Sclerosis Journal
Reader signal

How should this claim be treated?

83
Evidence-backed gainPeer-reviewedLifestyle

On real corn storage data, a spatiotemporal self-attention model forecast granary temperature with lower error than LSTM, GRU and other self-attention models, supporting earlier risk warning in grain storage.

Source article: Spatiotemporal self‐attention network ST‐GranNet for granary temperature prediction

Journal of the Science of Food and Agriculture
Reader signal

How should this claim be treated?

84
Evidence-backed gainPeer-reviewedEducation

In a survey of 533 Indonesian students, ChatGPT-enabled personalized learning strengthened both lower- and higher-order cognitive skills, with analyzing and creating most strongly tied to creative thinking.

Source article: Redefining creativity in AI era: Bloom's taxonomy framework and peer interaction elevate higher-order thinking skills

PLOS One
Reader signal

How should this claim be treated?

85
Evidence-backed gainPeer-reviewedHealth

In a decision-tree model of 100,000 preterm infants, community-based AI-assisted ROP screening had lower lifetime societal costs and more QALYs than telemedicine or bedside screening in both urban and rural China.

Source article: Cost-effectiveness of community-based artificial intelligence screening for retinopathy of prematurity

Journal of Global Health
Reader signal

How should this claim be treated?

86
Evidence-backed gainPeer-reviewedEducation

In a pilot with 33 fifth- and sixth-grade students, a prompting chatbot drew out higher-order thinking talk about ratio strategies, and students' talk rose with the chatbot's own.

Source article: Developing a generative AI chatbot to support students' higher-order thinking in STEM education

Journal of Microbiology & Biology Education
Reader signal

How should this claim be treated?

87
Evidence-backed gainPeer-reviewedScience

Pairing amino acid and 3Di structural alignments in generative landscapes recovered known subfamilies and revealed evolutionary relationships in viral glycoproteins that sequence alone did not show.

Source article: A structure-aware generative AI framework for revealing functional relationships in protein families

Proceedings of the National Academy of Sciences
Reader signal

How should this claim be treated?

88
Evidence-backed gainPeer-reviewedHealth

A causal machine learning model on 155 reconstruction patients pointed to lower preoperative hemoglobin and albumin as potential causal predictors of complications, which may help risk assessment.

Source article: A Machine Learning Model to Predict Complications Following Head and Neck Microvascular Surgery

Laryngoscope Investigative Otolaryngology
Reader signal

How should this claim be treated?

89
Evidence-backed gainPeer-reviewedHealth

In a small pilot, an LLM-driven voice simulator produced virtual patients whose MADRS scores from experienced raters landed close to their preset profiles, suggesting a scalable practice tool.

Source article: Voice-Enabled Virtual Patients for Interactive Training in Standardized Clinical Assessment: Mixed Methods Pilot Study

Journal of Medical Internet Research
Reader signal

How should this claim be treated?

90
Evidence-backed gainPeer-reviewedHealth

In a partitioned survival model, the AI-supported AIDPATH platform came out dominant over both cilta-cel and standard of care for triple-class refractory multiple myeloma from the German hospital perspective.

Source article: Cost-Effectiveness of AI-Powered Decentralized Production for Advanced Therapies in the Hospital-Generated Chimeric Antigen Receptor T-Cell Therapy for Multiple Myeloma From a German Hospital Perspective: Early Health Technology Assessment Study

JMIR Cancer
Reader signal

How should this claim be treated?