Is AI curing anything? Trials, authorisations and databases on the record.
Medicine · a view of the registers · does not feed the main number
Is AI curing anything? Trial results, approvals and what they show
Breakthrough is a headline word. This page lists the medical results that have a trial, an authorisation list or a database behind them, with what each one does and does not show.
6 entries from the hand-verified registers, checked as of 2026-09-28.
An authorisation is not a measured patient benefit, a Phase 2 result is not an approval, and a structure prediction is not a drug.
in-trialdrug discoverychecked 2026-09-28
What did the AI-designed drug Rentosertib show in Phase 2a?
71patients randomised in Phase 2a (18/18/18 on drug, 17 on placebo)2025-06-03
+98.4 vs -20.3mL mean change in FVC at 12 weeks, 60 mg QD vs placebo2025-06-03
320patients planned in the 52-week Phase 3 (estimated enrolment, recruiting)2026-09-09
What is measured?
A double-blind, placebo-controlled Phase 2a in idiopathic pulmonary fibrosis (NCT05938920) randomised 71 patients to three doses or placebo for 12 weeks (Nature Medicine, online 3 June 2025). The primary endpoint was safety. The share of patients with at least one treatment-emergent adverse event was similar across arms: 72.2 to 83.3% on drug and 70.6% on placebo. At 60 mg once daily, forced vital capacity (a secondary endpoint) changed by a mean of +98.4 mL (95% CI 10.9 to 185.9), against -20.3 mL (95% CI -116.1 to 75.6) on placebo. Insilico announced a 320-patient, 52-week, placebo-controlled Phase 3 (NCT07687459) on 7 July 2026. The registry gives an actual start date of 9 September 2026 and lists 47 sites, all in China; the trial is recruiting.
What gets claimed?
That this is the first drug whose target and molecule were both found by generative AI, and that it can improve lung function in IPF. The efficacy signal came from a secondary endpoint in a small 12-week trial, and the confidence intervals of the 60 mg and placebo arms overlap.
What is the caveat?
The efficacy result is small, short and exploratory, with wide confidence intervals. The most common adverse events leading to discontinuation were liver toxicity and diarrhoea. Insilico sponsored the Phase 2a and employs 11 of its authors. The Phase 3 has produced no results.
How often do AI-discovered molecules pass Phase I and Phase II?
80-90% Phase I success rate for AI-discovered molecules2024-04-30
~40% Phase II success rate (limited sample, comparable to historic industry average)2024-04-30
75AI-derived molecules entered the clinic since 2015 (secondary report of the paper)2024-06-24
67AI-derived molecules in clinical trials in 2023 (secondary report of the paper)undefined
Q1 2027FDA target action date for the zasocitinib NDA (Priority Review accepted)2026-09-14
What is measured?
The first published analysis of the pipelines of AI-native biotech companies appeared in Drug Discovery Today (online 30 April 2024, by BCG authors). It found that AI-discovered molecules succeeded in Phase I 80 to 90% of the time, well above historic industry averages. In Phase II the rate was about 40%, on a limited sample, which is comparable to historic averages. Secondary reports of the paper's body give 75 AI-derived molecules entering the clinic since 2015, and 67 in clinical trials in 2023. Among computationally designed molecules, zasocitinib (TAK-279) is at the application stage. It is a TYK2 inhibitor that Nimbus Therapeutics designed with Schrödinger's physics-based FEP+ simulations. On 14 September 2026 Takeda announced that the FDA had accepted its NDA for plaque psoriasis under Priority Review, with a target action date in the first quarter of 2027.
What gets claimed?
That AI makes drug discovery faster and more successful overall. What has been measured is lower Phase I attrition; no advantage in Phase II efficacy has been shown. Secondary reviews found that the FDA had approved no AI-discovered drug as of July 2026, and no later approval was found.
What is the caveat?
The percentages come from the PubMed abstract. The paper is open access (CC BY-NC-ND), but ScienceDirect blocked automated reads, so the 75 and 67 counts rest on secondary reports. The authors define which molecules count as 'AI-discovered', and the set is not audited. Zasocitinib came from physics-based free-energy simulation against a target already validated by an approved drug (deucravacitinib), not from generative AI, and Takeda's releases do not call it AI-discovered. The claim that no AI drug is approved depends on how 'AI-discovered' is defined.
76% of listed devices in the radiology panel (1,230)2026-09-04
335devices authorised in calendar 2025 (highest year)2026-09-04
What is measured?
The FDA's AI-Enabled Medical Device List (content current as of 4 September 2026) has 1,614 authorised devices, the most recent decided on 29 June 2026. Radiology accounts for 1,230 (76%) and cardiovascular for 154. The highest yearly total was 335 in 2025, and 181 more are listed for January to June 2026. Of the 1,614, 1,553 were cleared via 510(k), 40 via De Novo and 21 via PMA, counted from the table on the FDA page today.
What gets claimed?
That AI is transforming clinical care. The list shows marketing authorisation, not measured patient benefit. Most clearances rest on substantial equivalence to an existing device, not on outcome trials.
What is the caveat?
The FDA says the list is not comprehensive. It is built mainly from AI-related terms in summaries, and devices whose decision summaries were not yet published are added in a later update, so the 2026 count is incomplete.
1.55 vs 1.76interval cancers per 1,000 women, AI vs standard (ratio 0.88, 95% CI 0.65-1.18)2026-01-29
80.5 vs 73.8% sensitivity, AI vs standard2026-01-29
44.2% reduction in screen-reading workload (61,248 vs 109,692 readings)2025-02-03
What is measured?
MASAI randomised 105,934 women in Sweden between 12 April 2021 and 7 December 2022. One arm had AI-supported screening, in which AI sent each exam to single or double reading and supported detection; the other had standard double reading (The Lancet, 29 January 2026; 105,915 analysed). Interval cancers were 1.55 per 1,000 in the AI arm (82 of 53,043) and 1.76 per 1,000 in the control arm (93 of 52,872). The proportion ratio was 0.88 (95% CI 0.65 to 1.18), which met the 20% non-inferiority margin. Sensitivity was 80.5% vs 73.8%, and specificity was 98.5% in both arms. An earlier report from the same trial found 29% more cancers detected (6.4 vs 5.0 per 1,000) and 44.2% fewer screen readings, with no significant rise in false positives.
What gets claimed?
That AI makes breast screening both better and cheaper everywhere. The 12% lower interval-cancer rate was not statistically significant, and the trial was designed to show non-inferiority. It tested one AI system in one national programme and has not reported mortality.
What is the caveat?
The Lancet page returned 403, so the figures were checked against the PubMed abstracts and The Lancet's press release. The press release rounds sensitivity to 81% vs 74% and gives false-positive rates of 1.5% vs 1.4%. Results from one Swedish double-reading programme may not transfer to single-reader systems such as the US.
How many open structure predictions has AlphaFold published?
>260 millionprotein and complex structure predictions in AlphaFold DB2026-09-24
>2 millionAlphaFold2 users in 190 countries2024-10-09
What is measured?
EMBL reported on 24 September 2026 that the AlphaFold Protein Structure Database holds more than 260 million protein and protein-complex predictions, after adding complexes for more than 2,800 viruses. Half of the 2024 Nobel Prize in Chemistry went jointly to Demis Hassabis and John Jumper 'for protein structure prediction', and the other half to David Baker 'for computational protein design'. The Royal Swedish Academy of Sciences' press release says AlphaFold2 has been used by more than two million people from 190 countries.
What gets claimed?
That protein folding is 'solved'. These are predictions with per-residue confidence scores, not experimental structures. Accuracy varies, especially in disordered regions and complexes, and a prediction does not by itself produce a drug.
What is the caveat?
The EBI site gives two figures. Its headline says 'over 260 million' predictions, while the release note says the latest release has 'over 200 million entries' covering UniProt.
Which Co-Scientist hypotheses were confirmed in the lab?
91% reduction in TGF-beta-induced chromatin changes by vorinostat in liver organoids2025-09-14
25drugs tested in human hepatic organoids (peer-reviewed version; the preprint tested 14)2025-09-14
What is measured?
Google's Co-Scientist is a multi-agent system built on Gemini (Nature, online 19 May 2026). It proposed drug-repurposing candidates and synergistic combinations for acute myeloid leukaemia that were validated in vitro. In a peer-reviewed study (Advanced Science, online 14 September 2025), 25 drugs were tested in human hepatic organoids. Two epigenetic drugs that Co-Scientist recommended showed anti-fibrotic activity, and one of them, vorinostat, reduced TGF-beta-induced chromatin changes by 91%. Separately, Imperial College researchers reported in Cell (online 9 September 2025; 13 November 2025 issue) that its top-ranked hypothesis matched a mechanism of bacterial gene transfer. The mechanism, cf-PICIs hijacking diverse phage tails, was one they had confirmed experimentally but not yet published.
What gets claimed?
That AI is now an independent scientist. Every validation so far is in cell lines or organoids. The bacterial result reproduced something the authors already knew, in a test run by the same team and Google that was not blinded.
What is the caveat?
No patient data exists. The organoid study has Alphabet co-authors, and the Nature paper was funded by Alphabet.
10 of 800 headlines in the newsroom window mention drugs, patients, trials or medicine, as of 2026-10-15 05:24:30 UTC.
Matched by word, so read them before trusting the count.
Is AI curing anything? Trial results, approvals and what they show
This page does not claim a cure. It lists medical results that have a trial, an authorisation list, or a database behind them, each with what was measured and the caveat.
Does an FDA authorisation mean a measured patient benefit?
No. An authorisation is not a measured patient benefit, a Phase 2 result is not an approval, and a structure prediction is not a drug. Each entry states that distinction in its own caveat.
Which headlines mention this in the newsroom now?
10 of 800 headlines in the newsroom window mention drugs, patients, trials or medicine, as of 2026-10-15 05:24:30 UTC. Matched by word, so read them before trusting the count.
What is measured?
Each register entry states what is counted for drugs, patients, trials or medicine: the figure, its unit and the source date — not a forecast.
What gets claimed?
Each entry states what the source claims about drugs, patients, trials or medicine. Claims are not the same as verified outcomes.
What is the caveat?
Each entry states the caveat that keeps the figure from being read as a SIREN forecast or doom probability.
What did the AI-designed drug Rentosertib show in Phase 2a?
A double-blind, placebo-controlled Phase 2a in idiopathic pulmonary fibrosis (NCT05938920) randomised 71 patients to three doses or placebo for 12 weeks (Nature Medicine, online 3 June 2025). The primary endpoint was safety. The share of patients with at least one treatment-emergent adverse event was similar across arms: 72.2 to 83.3% on drug and 70.6% on placebo. At 60 mg once daily, forced vital capacity (a secondary endpoint) changed by a mean of +98.4 mL (95% CI 10.9 to 185.9), against -20.3 mL (95% CI -116.1 to 75.6) on placebo. Insilico announced a 320-patient, 52-week, placebo-controlled Phase 3 (NCT07687459) on 7 July 2026. The registry gives an actual start date of 9 September 2026 and lists 47 sites, all in China; the trial is recruiting. The efficacy result is small, short and exploratory, with wide confidence intervals. The most common adverse events leading to discontinuation were liver toxicity and diarrhoea. Insilico sponsored the Phase 2a and employs 11 of its authors. The Phase 3 has produced no results.
How often do AI-discovered molecules pass Phase I and Phase II?
The first published analysis of the pipelines of AI-native biotech companies appeared in Drug Discovery Today (online 30 April 2024, by BCG authors). It found that AI-discovered molecules succeeded in Phase I 80 to 90% of the time, well above historic industry averages. In Phase II the rate was about 40%, on a limited sample, which is comparable to historic averages. Secondary reports of the paper's body give 75 AI-derived molecules entering the clinic since 2015, and 67 in clinical trials in 2023. Among computationally designed molecules, zasocitinib (TAK-279) is at the application stage. It is a TYK2 inhibitor that Nimbus Therapeutics designed with Schrödinger's physics-based FEP+ simulations. On 14 September 2026 Takeda announced that the FDA had accepted its NDA for plaque psoriasis under Priority Review, with a target action date in the first quarter of 2027. The percentages come from the PubMed abstract. The paper is open access (CC BY-NC-ND), but ScienceDirect blocked automated reads, so the 75 and 67 counts rest on secondary reports. The authors define which molecules count as 'AI-discovered', and the set is not audited. Zasocitinib came from physics-based free-energy simulation against a target already validated by an approved drug (deucravacitinib), not from generative AI, and Takeda's releases do not call it AI-discovered. The claim that no AI drug is approved depends on how 'AI-discovered' is defined.
How many AI medical devices has the FDA authorised?
The FDA's AI-Enabled Medical Device List (content current as of 4 September 2026) has 1,614 authorised devices, the most recent decided on 29 June 2026. Radiology accounts for 1,230 (76%) and cardiovascular for 154. The highest yearly total was 335 in 2025, and 181 more are listed for January to June 2026. Of the 1,614, 1,553 were cleared via 510(k), 40 via De Novo and 21 via PMA, counted from the table on the FDA page today. The FDA says the list is not comprehensive. It is built mainly from AI-related terms in summaries, and devices whose decision summaries were not yet published are added in a later update, so the 2026 count is incomplete.
Was AI-supported mammography non-inferior to double reading?
MASAI randomised 105,934 women in Sweden between 12 April 2021 and 7 December 2022. One arm had AI-supported screening, in which AI sent each exam to single or double reading and supported detection; the other had standard double reading (The Lancet, 29 January 2026; 105,915 analysed). Interval cancers were 1.55 per 1,000 in the AI arm (82 of 53,043) and 1.76 per 1,000 in the control arm (93 of 52,872). The proportion ratio was 0.88 (95% CI 0.65 to 1.18), which met the 20% non-inferiority margin. Sensitivity was 80.5% vs 73.8%, and specificity was 98.5% in both arms. An earlier report from the same trial found 29% more cancers detected (6.4 vs 5.0 per 1,000) and 44.2% fewer screen readings, with no significant rise in false positives. The Lancet page returned 403, so the figures were checked against the PubMed abstracts and The Lancet's press release. The press release rounds sensitivity to 81% vs 74% and gives false-positive rates of 1.5% vs 1.4%. Results from one Swedish double-reading programme may not transfer to single-reader systems such as the US.
How many open structure predictions has AlphaFold published?
EMBL reported on 24 September 2026 that the AlphaFold Protein Structure Database holds more than 260 million protein and protein-complex predictions, after adding complexes for more than 2,800 viruses. Half of the 2024 Nobel Prize in Chemistry went jointly to Demis Hassabis and John Jumper 'for protein structure prediction', and the other half to David Baker 'for computational protein design'. The Royal Swedish Academy of Sciences' press release says AlphaFold2 has been used by more than two million people from 190 countries. The EBI site gives two figures. Its headline says 'over 260 million' predictions, while the release note says the latest release has 'over 200 million entries' covering UniProt.
Which Co-Scientist hypotheses were confirmed in the lab?
Google's Co-Scientist is a multi-agent system built on Gemini (Nature, online 19 May 2026). It proposed drug-repurposing candidates and synergistic combinations for acute myeloid leukaemia that were validated in vitro. In a peer-reviewed study (Advanced Science, online 14 September 2025), 25 drugs were tested in human hepatic organoids. Two epigenetic drugs that Co-Scientist recommended showed anti-fibrotic activity, and one of them, vorinostat, reduced TGF-beta-induced chromatin changes by 91%. Separately, Imperial College researchers reported in Cell (online 9 September 2025; 13 November 2025 issue) that its top-ranked hypothesis matched a mechanism of bacterial gene transfer. The mechanism, cf-PICIs hijacking diverse phage tails, was one they had confirmed experimentally but not yet published. No patient data exists. The organoid study has Alphabet co-authors, and the Nature paper was funded by Alphabet.
