Enhancing emerging technology discovery in nanomedicine by integrating innovative sentences using BERT and NLDA

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Regional distribution of innovation indicators_

Region	Average count	Percentage (%)
USA	91.0	0.35
Australia	89.5	0.40
Poland	87.5	0.33
France	86.5	0.44
Greece	85.5	0.42
Iraq	83.5	0.42
Denmark	83.0	0.38
Jordan	82.0	0.35
Kenya	81.0	0.34
Hungary	81.0	0.38
Malaysia	79.0	0.38
India	75.5	0.39
Mexico	75.5	0.47
Thailand	75.5	0.25
China	74.5	0.40
Germany	74.0	0.41
Nepal	73.5	0.44
Brazil	73.0	0.40
Italy	71.0	0.37
Netherlands	71.0	0.45

Criteria for distinguishing sentences_

Sentences with academic innovation	Sentences that lack innovation
Introduce new ideas, unique approaches, or novel methods.	Furnish common background information or definitions.
Display original discoveries, experimental results, or undocumented data.	Elucidate routine procedures and methods that are commonly used in this field.
Propose unique applications, materials, or techniques.	Provide a summary of well-established information or results available in the literature.

BERT model hyperparameterization_

Hyperparameter	Values	Description
batch_size	32	Number of samples per batch during training
max_seq_length	500	Maximum length of input sequences
learning_rate	2e-5	Learning rate, subject to tuning
train_epochs	20	Number of training epochs
warmup_proportion	0.1	Proportion of total training steps for learning rate warm-up
adam_epsilon	1e-8	Epsilon value for the Adam optimizer
dropout_prob	0.1	Dropout probability in dropout layers

NLDA Topic-Word Distribution_

Topic 1: Nanostructures and Polymer Chemistry		Topic 2: Graphene and Nanocomposites in Drug Delivery		Topic 3: Nanomaterial Quality and Surface Properties		Topic 4: Nanoparticles in Cancer Research and Therapy
Polymers	Structures	Bacteria	Diffraction	Nanoparticles	Solution	Nanoparticles	Treatment
Nanoparticles	Nanostructures	Graphene	Surface	Nanomedicines	Surface	Transfection	Delivery
Copolymer	Solution	Nanoparticles	Solution	Information	Factors	Migration	Concentration
Treatment	Polymerization	Spectroscopy	Treatment	Product	Quality	Solution	Exosomes
Surface	Polymerization	Nanocomposites	Coating	Treatment	Molecules	Pathway	Surface
Topic 5: Ultrafast Centrifugation and Nanomaterial Preparation		Topic 6: Antitumor Therapy and Tumor Stem Cells		Topic 7: Nanoparticles and Drug Delivery		Topic 8: Photothermal Therapy and Nanomaterials in Cancer
Microscope	Centrifugation	Survival	Metastasis	Nanoparticles	Solubility	Cancer	Treatment
Supernatant	Reagent	Resistance	Cancer	Curcumin	Solution	Nanoparticles	Conversion
Nanoparticles	Solution	Chemotherapy	Treatments	Encapsulation	Content	Nanosheets	Photothermal
Minutes	Transmission	Antitumor	Cancers	Hydrogel	Surface	Solution	Hypoxia
Microplate	Concentration	Nanoparticles	Doxorubicin	Storage	Treatment	Species	Performance
Topic 9: Antidiabetic Nanodrug Carriers and Biomedical Applications		Topic 10: Animal Studies and Biomedical Protocols		Topic 11: Nanoparticle Surface Characterization and Complex Structures		Topic 12: Inflammation and Biomaterial Interactions in Disease Research
Extract	Insulin	Animals	Staining	Adsorption	Solution	Inflammation	Solution
Nanoparticles	Surface	Biodistribution	Committee	Nanoparticles	Treatment	Nanoparticles	Treatment
Dendrimers	Delivery	Nanoparticles	Liver	Surface	Complexes	Macrophage	Responses
Activities	Treatment	Sections	Solution	Nanotubes	Structures	Collagen	Surface
Solution	Concentration	Group	Surface	Results	Material	Cytokines	Inflammatory

Emerging technologies in nanomedicine_

Topic id	Topic meaning
12	Inflammation and Biomaterial Interactions in Disease Research
8	Photothermal Therapy and Nanomaterials in Cancer
6	Antitumor Therapy and Tumor Stem Cells
4	Nanoparticles in Cancer Research and Therapy
2	Graphene and Nanocomposites in Drug Delivery
16	Animal Studies and Biomedical Protocols
9	Antidiabetic Nanodrug Carriers and Biomedical Applications
7	Nanoparticles and Drug Delivery

NLDA Topic -Word Distribution_

Topic 13: Nanotechnology in Vaccine Research and Infectious Diseases		Topic 14: Liposomes and Receptors in Drug Delivery		Topic 15: Nanoparticles in Materials Science		Topic 16: Nanocarriers for Hormone Release and Antitumor Drugs
Nanoparticles	Treatment	Peptides	Affinity	Nanoparticles	Silicon	Nanocarriers	Loading
Authors	Concentration	Antibodies	Solution	Channel	Treatment	Nanoparticles	Micelle
Science	Diseases	Vesicles	Receptor	Solution	Diffusion	Carrier	Circulation
Solution	Results	Nanoparticles	Membranes	Surface	Results	Dialysis	Prodrug
Nanotechnology	Disease	Conjugation	Treatment	Parameters	Frequency	Antitumor	Solution
Topic 17: Luminescence and Spectroscopy in Nanomaterials		Topic 18: Endocytosis and Cell Signaling with Nanoparticles		Topic 19: Methods for Nanoparticle Preparation and Purification		Topic 20: Nanoparticle Permeation Properties in Oncology Treatments
Emission	Wavelength	Internalization	Pathway	Dispersion	Product	Transport	Circulation
Nanoparticles	Spectrum	Endocytosis	Nucleus	Nanoparticles	Solution	Nanoparticles	Solution
Excitation	Signals	Nanoparticles	Surface	Centrifugation	Calibration	Penetration	Spheroids
Resonance	Solution	Mechanisms	Treatment	Ethanol	Treatment	Vessels	Surface
Resolution	Fluorescent	Solution	Pathways	Compound	Surface	Permeability	Treatment

NLDA model hyperparameterization_

Hyperparameter	Values	Description
num_topicsint	20	Number of topics
Alphaint	50	Alpha parameter of TND
Betafloat	0.01	Beta parameter of TND
Iterationsint	200	Number of training iterations
random_seed	54	Random seed to ensure consistent results

Model evaluation indicators_

Model	Accuracy	Precision	Recall	F1
BERT+ Classifier	0.836	0.864	0.853	0.858
TF-IDF+SVM	0.524	0.537	0.530	0.533
TF-IDF+KNN	0.600	0.617	0.593	0.604
TF-IDF+NB	0.582	0.553	0.569	0.560
Word2Vec+ SVM	0.650	0.658	0.614	0.635
Word2Vec+ KNN	0.696	0.628	0.603	0.615
Word2Vec+ NB	0.623	0.609	0.634	0.621

LDA Topic -Word Distribution_

Topic 1	Topic 2	Topic 3	Topic 4	Topic 5	Topic 6
protein	delivery	nanoparticles	nps	antibacterial	applications
corona	cell	silver	nanoparticles	cells	properties
cell	nanoparticles	agnps	delivery	bacteria	review
proteins	review	activity	brain	activity	materials
bone	drugs	nm	size	vivo	titanium
Topic 7	Topic 8	Topic 9	Topic 10	Topic 11	Topic 12
exosomes	based	tumor	wound	clinical	nanosheets
cells	high	cancer	materials	cancer	surface
tumour	cell	therapy	tissue	therapy	go
nanoparticles	clinical	cells	healing	photothermal	mxenes
drug	detection	pdt	bone	agents	applications

Results of the calculation of thematic indicators_

	Innovation	Originality	Growth	Significance	Topic strength	Emerging degree
Topic 12	0.793	0.446	0.390	0.913	1.000	0.722
Topic 8	1.000	0.489	0.698	0.507	0.567	0.614
Topic 6	0.632	0.591	0.616	0.709	0.375	0.595
Topic 4	0.580	0.296	1.000	0.592	0.499	0.569
Topic 2	0.145	0.566	0.191	0.730	0.777	0.533
Topic 16	0.557	0.769	0.581	0.359	0.426	0.529
Topic 9	0.351	0.342	0.144	0.882	0.376	0.474
Topic 7	0.530	0.315	0.391	0.709	0.284	0.465
Topic 3	0.272	0.000	0.342	1.000	0.256	0.427
Topic 5	0.403	1.000	0.426	0.103	0.180	0.417
Topic 13	0.310	0.217	0.379	0.768	0.046	0.383
Topic 15	0.000	0.124	0.000	0.777	0.609	0.363
Topic 11	0.090	0.213	0.360	0.753	0.044	0.343
Topic 14	0.292	0.238	0.222	0.684	0.071	0.341
Topic 1	0.264	0.263	0.262	0.506	0.268	0.334
Topic 18	0.208	0.479	0.238	0.540	0.000	0.333
Topic 10	0.329	0.758	0.404	0.000	0.246	0.330
Topic 20	0.358	0.089	0.206	0.705	0.117	0.328
Topic 17	0.216	0.332	0.447	0.392	0.156	0.318
Topic 19	0.273	0.544	0.255	0.127	0.007	0.242

Emerging nanomedicine technology keywords classification_

Category	Keywords
Nanomaterial Applications	Nanoparticles; Nanotubes; Nanofibers; Nanocrystals; Nanoshells; Metal nanoparticles (e.g.; Gold; Silver); Carbon nanomaterials (e.g.; Graphene; Fullerenes); Quantum dots; Polymeric nanoparticles; Nucleic acid Nanostructures
Drug Delivery Systems	Drug-loaded nanoparticles; Nanomicelles; Nanoemulsions; Nanocapsules; liposomes; Polymeric drug conjugates; Targeted drug delivery; Controlled release systems; PH-responsive nanocarriers; Temperature-responsive nanocarriers
Diagnostics and Imaging	Molecular imaging; Magnetic resonance imaging (MRI); Positron emission tomography (PET); Single photon emission computed tomography (SPECT); Optical imaging; Fluorescence imaging; Raman spectroscopy imaging; Upconversion nanoparticle imaging; Multimodal imaging
Cancer diagnosis and treatment	Nanoparticles; Hypoxia therapy; Tumor-targeted therapy; Nanoimmunomodulators
Nanotherapy for infectious diseases	Nano-antimicrobials; Inflammation; Antimicrobial peptides; Nano-vaccines; Nano-antibiotics
Rational Design of Antimicrobial Peptides	Antimicrobial peptides (AMPs); Peptide design; Membrane disruption mechanisms; Antibiotic resistance