Artificial intelligence is progressively entering pharmaceutical formulation workflows, particularly in areas such as compatibility screening, dissolution profile prediction, formulation optimization and process modelling. These applications are promising, but their value depends strongly on the quality, consistency and traceability of the data used to train and validate the models [1-3].
For oral solid dosage forms, excipient data can be particularly important. A model may use information on particle size distribution, crystallinity, residual moisture, density or surface area to predict formulation behaviour.
This article focuses on one practical question for formulation teams: as artificial intelligence and machine learning become more common in pharmaceutical development. For pharmaceutical lactose suppliers, this question has implications that extend beyond digital tools. AI use emphasizes the need for consistency in both intra-batch and batch-to-batch production, as well as for analytical rigor and quality documentation.
AI in pharmaceutical formulation:
a developing but data-dependent field
Recent publications describe several applications of artificial intelligence in pharmaceutical technology and drug delivery design, including formulation screening, compatibility assessment and prediction of product performance [1,7]. Web-based tools such as FormulationAI have also been presented as examples of AI-supported formulation design platforms [2].
In practice, these tools are most relevant when the formulation space is well defined and when the training data are sufficiently robust. Artificial intelligence can help identify correlations, prioritize experiments and support Design of Experiments analysis. However, it does not remove the need for formulation expertise, experimental validation or regulatory justification.
Machine learning (ML) models are therefore best understood as decision-support tools. They may accelerate development work, but their predictions remain dependent on the quality and comparability of the input data. This is particularly relevant for excipients, because their material attributes can influence processing, tablet behaviour and dissolution-related parameters.
What AI can currently support in formulation development
Current documented uses of AI in formulation development are generally concentrated in specific tasks rather than in full autonomous formulation design. The most relevant areas include:
- API-excipient compatibility screening, using historical stability or compatibility data to identify combinations that may require further assessment [1,3].
- Dissolution profile prediction, where excipient attributes, API properties and process parameters may be correlated with measured dissolution behaviour [3].
- Formulation ratio optimization, often as an extension of classical Design of Experiments, regression modelling or machine learning approaches [2,3].
- Process outcome prediction, where formulation composition is linked to granulation, blending, flow or compression behaviour [3].
These applications can be useful, but they are generally limited to the design space and data quality available to the development team. A model trained on one set of excipient data may not automatically transfer to another supplier or another grade, even when the nominal specification appears similar. In this context, batch consistency within one batch and between delivered batches becomes an important condition for reliable modelling.
Why excipient data consistency matters
In formulation modelling, inconsistent input data can significantly limit the relevance of predictions. This is not specific to lactose, but it is particularly important for excipients used at relatively high levels in oral solid dosage forms, where material attributes may influence blend behaviour, compaction, disintegration and dissolution.
Several situations can reduce the value of an excipient dataset for modelling purposes:
- particle size data generated with different analytical methods, such as laser diffraction and sieve analysis, which are not comparable;
- crystallinity values measured under different humidity or sample preparation conditions;
- Brunauer-Emmett-Teller (BET) surface area data generated with different instruments or protocols;
- residual moisture values reported without sufficient information on method and conditions;
- limited historical data across production batches, which may make it difficult to distinguish normal variation from meaningful change.
When such differences are not enough monitored, the model may compensate by producing wider confidence intervals or less stable predictions. In practical terms, this can reduce the usefulness of AI-supported tools for formulation decision-making.
Pharmaceutical lactose: which parameters may be relevant for AI-supported models?
For pharmaceutical lactose used in oral solid dosage forms, several material attributes may be relevant to formulation models. Their importance depends on the dosage form, the process route, the API and the modelling objective.
| Parameter | Why it may matter | Model relevance |
| Particle size distribution (D10, D50, D90) | May influence flow, blend homogeneity, compaction behaviour and exposure of the API after disintegration. | Can support dissolution, blend uniformity and process behaviour models. |
| Crystallinity / amorphous content | May influence physical stability and compatibility considerations, depending on the API and storage conditions. | Can support stability and compatibility risk assessment. |
| Residual moisture | May influence stability, flow behaviour and interaction with moisture-sensitive APIs. | Can support stability and degradation-related models. |
| Bulk and tapped density | Can influence flowability, die filling and compression behaviour. | Can support compression and manufacturability models. |
| BET surface area | May influence wetting and liquid-solid interactions. | Can support wetting and dissolution-related modelling. |
These parameters are not automatically useful simply because they are measured. For modelling purposes, their value increases when they are measured with consistent analytical methods, documented across production batches and monitored within an appropriate specification framework.
From supplier comparison to batch consistency
For formulation teams using AI-supported models, data from one supplier or one grade should not be assumed to be interchangeable with data from another supplier or another grade. Two lactose grades may comply with the same pharmacopoeial monograph while still can differ in particle size distribution, morphology, density, crystallinity or residual moisture.
The gap between in silico prediction and industrial reality
Many AI-supported formulation models are initially developed with laboratory-scale data. Transfer to manufacturing scale can introduce additional variability, including blending time, granulation endpoint, compression force, equipment configuration and environmental conditions. These factors are not yet be fully represented in early datasets used by IA [3].
Regulatory agencies are also still building their frameworks for the use of AI and machine learning in drug development. The FDA published a discussion paper on AI and ML in drug and biological product development in 2023, and later publications describe continued cross-center work on AI and medical products [4,5]. In Europe, the HMA-EMA multi-annual AI workplan 2023-2028 sets out actions to guide the use of AI in medicines regulation [6].
This evolving framework reinforces the need for explainable, traceable and well-documented data. For formulation applications, black-box outputs may be difficult to justify if the underlying material data are incomplete or not comparable.
Excipient supplier documentation in an AI-supported formulation context
As AI-supported tools develop, formulation teams will increasingly request more comprehensive data and analyses from excipient suppliers to feed into their predictive models. However, Pharmacopoeia compliance alone will not be sufficient for modelling purposes.
That is why, future expectations may include more detailed characterization data, documented analytical methods, batch history, consistency over time and traceability of critical material attributes.
For producers of pharmaceutical excipients, the challenge is therefore to combine industrial reliability with data reliability. Homogeneous characteristics within a batch and consistent characteristics between delivered batches can help formulation teams build and maintain more reliable predictive models once development moves toward industrialization.
Conclusion
Artificial intelligence is likely to play a growing role in pharmaceutical formulation, but its impact will depend on the reliability of the data used to support it. Algorithms can help accelerate analysis, identify correlations and support formulation decisions, but they cannot compensate for poorly comparable or insufficiently documented material data.
For oral solid dosage forms, excipient characterization may therefore become increasingly important in AI-supported development workflows. Pharmaceutical lactose, when well characterized and supplied with consistent material attributes, can contribute to more reliable formulation datasets, particularly for models involving dissolution, process behaviour and scale-up.
For excipient producers, this context reinforces the relevance of supplying pharmaceutical-grade ingredients whose characteristics are homogeneous within each batch and consistent between batches. In an AI-augmented formulation environment, this consistency may become one of the foundations of reliable prediction and industrial transfer.
FAQ: AI and pharmaceutical formulation
Can AI replace the formulation scientist?
AI is not expected to replace formulation scientists. Its role is more likely to support hypothesis generation, data analysis and decision-making within a defined development framework. Human expertise remains central for defining the design space, interpreting results and validating the final formulation.
What excipient data can be useful for AI-supported formulation?
Useful excipient data may include particle size distribution, crystallinity, residual moisture, bulk and tapped density, and BET surface area. The relevance of each parameter depends on the dosage form, API properties and modelling objective.
Why does batch consistency matter for AI models?
Batch consistency helps ensure that the data used by the model remain comparable over time. If excipient characteristics vary significantly or are measured inconsistently, model predictions may become less reliable for formulation decisions.
How can pharmaceutical lactose support AI-driven formulation work?
Pharmaceutical lactose can support AI-driven formulation work when its material attributes are well characterized, traceable and consistent across batches. This can help formulation teams generate more stable datasets for models related to dissolution, manufacturability and scale-up.
What are the current limitations of AI in drug formulation?
Current limitations include the need for high-quality training data, limited transferability between different suppliers or grades, scale-up variability and evolving regulatory expectations. AI-supported outputs should therefore be interpreted within a validated and documented development framework [4-6].
Sources
1. Vora LK et al. Artificial intelligence in pharmaceutical technology and drug delivery design. Pharmaceutics. 2023;15(7):1916. DOI: 10.3390/pharmaceutics15071916.
2. Dong J, Wu Z, Xu H, Ouyang D. FormulationAI: a novel web-based platform for drug formulation design driven by artificial intelligence. Briefings in Bioinformatics. 2024;25(1):bbad419. DOI: 10.1093/bib/bbad419.
3. Murray JD et al. Advancing algorithmic drug product development: Recommendations for machine learning approaches in drug formulation. European Journal of Pharmaceutical Sciences. 2023;189:106562. DOI: 10.1016/j.ejps.2023.106562.
4. FDA. Using Artificial Intelligence and Machine Learning in the Development of Drug and Biological Products: Discussion Paper. 2023.
5. FDA. Artificial Intelligence and Medical Products: How CBER, CDER, CDRH, and OCP are Working Together. March 2024.
6. EMA/HMA. Multi-annual Artificial Intelligence Workplan 2023-2028. December 2023.
7. Serrano DR et al. Artificial Intelligence Applications in Drug Discovery and Drug Delivery: Revolutionizing Personalized Medicine. Pharmaceutics. 2024;16(10):1328. DOI: 10.3390/pharmaceutics16101328.
8. ICH Q8(R2): Pharmaceutical Development. ICH, 2009.
9. ICH Q10: Pharmaceutical Quality System. ICH, 2008.
