WO-2026093175-A1 - SYSTEM AND METHOD FOR PREDICTING SETTINGS FOR TREATMENT OF TISSUE AND TISSUE RESPONSE

Abstract

A system for predicting tissue treatment settings and response of tissue is described. When executed by the processor, instructions cause the processor to: (a) receive measured nitric oxide (NO) tissue data from a personal healthcare device; (b) apply a trained computational model to predict an NO response, and based on the predicted NO response, predict tissue treatment settings; (c) compare the predicted treatment settings to a safety limit; (d) when the comparison of the predicted treatment settings is equal to or below the safety limit, update the predicted treatment settings and carrying out the tissue treatment at the predicted treatment settings; and (e) when the comparison of the prediction is greater than the safety limit, adjust the tissue treatment settings, update weights of the trained computational model, and repeat (c) through (e). A method and a tangible, non-transitory computer readable medium to make the predictions are also disclosed.

Inventors

• VAN DEN DUNGEN, WILHELMUS ANDREAS MARINUS ARNOLDUS MARIA
• STOFFELS, Monique
• PAULUSSEN, ELVIRA JOHANNA MARIA
• KOOIJMAN, GERBEN

Assignees

• KONINKLIJKE PHILIPS N.V.

Dates

Publication Date

20260507

Application Date

20251027

Priority Date

20250127

Claims (15)

1. 1. A system for predicting tissue treatment settings and response of tissue, the system comprising: a personal healthcare device comprising fluorescent dots (Fdots) adapted to detect nitric oxide (NO); a memory adapted to store a trained computational model comprising instructions; and a processor, wherein the instructions, when executed by the processor, cause the processor to: (a) receive measured nitric oxide (NO) tissue data from a personal healthcare device; (b) apply a trained computational model to predict an NO response, and based on the predicted NO response, predict tissue treatment settings; (c) compare the predicted treatment settings to a safety limit; (d) when the comparison of the predicted treatment settings is equal to or below the safety limit, update the predicted treatment settings and carrying out the tissue treatment at the predicted treatment settings; and (e) when the comparison of the prediction is greater than the safety limit, adjust the tissue treatment settings, update weights of the trained computational model, and repeat (c) through (e).
2. 2. The system of claim 1, wherein, based on the measured NO tissue data, the instructions further cause the processor to predict a health status of the tissue.
3. 3. The system of claim 2, wherein the instructions further cause the processor to estimate treatment settings based on the predicted health status of the tissue.
4. 4. The system of claim 1, wherein after the tissue treatment settings are predicted, the instructions further cause the processor to predict an NO tissue response to a treatment at the predicted tissue treatment settings.
5. 5. The system of claim 1, wherein after the carrying out of the tissue treatment, the instructions further cause the processor to measure NO production with the personal healthcare device and compare a tissue response to a predicted response of the tissue. 2024PF00262 35
6. 6. The system of claim 5, wherein when the comparing of the tissue response is not equal to the predicted response, the instructions cause the processor to repeat (c) through (e).
7. 7. The system of claim 1, wherein the trained computational model is a deployed computational model, and when updating the weights of the trained computational model, the instructions further cause the processor to adjust parameters of the trained computational model.
8. 8. The system of claim 1, wherein the trained computational model is a deployed computational model, and the instructions further cause the processor to: adjust parameters of the trained computational model based on a real-time response of the tissue.
9. 9. The system of claim 8, wherein the real-time response is based on a treatment of the tissue with a particular NO level.
10. 10. The system of claim 1, wherein the instructions further cause the processor to apply the trained computational model to a particular location at a particular time; and repeat (c) through (e).
11. 11. The system of claim 10, wherein the instructions further cause the processor to apply the trained computational model at the particular location at another particular time; repeating (c) through (e); and generate a health map.
12. 12. The system of claim 11, wherein the instructions further cause the processor to use an area in the health map that is related to the particular location to update the weights of the model at the particular location.
13. 13. The system of claim 1, wherein the trained computational model is a deployed computational model, and the instructions further cause the processor to: share weights and parameters based on received federated learning rates.
14. 14. A tangible, non-transitory computer readable medium that stores instructions, which when executed by a processor, cause the processor to: (a) receive measured nitric oxide (NO) tissue data from a personal healthcare device; (b) apply a trained computational model to the NO tissue data to predict an NO response, and based on the predicted NO response, predict tissue treatment settings; (c) compare the predicted treatment settings to a safety limit; 2024PF00262 36 (d) when the comparison of the predicted treatment settings is equal to or below the safety limit, update the predicted treatment settings and carrying out the tissue treatment at the predicted treatment settings; and (e) when the comparison of the prediction is greater than the safety limit, adjust the tissue treatment settings, update weights of the trained computational model, and repeat (c) through (e).
15. 15. A method of predicting tissue treatment settings and nitric oxide (NO) response of tissue, the method comprising: (a) measuring nitric oxide (NO) tissue data from a personal healthcare device comprising fluorescent dots (Fdots); (b) applying a trained computational model to the NO tissue data to predict an NO response, and based on the predicted NO response, predicting tissue treatment settings; (c) comparing the predicted treatment settings to a safety limit; (d) when the comparing of the predicted treatment settings is equal to or below the safety limit, updating the predicted treatment settings and carrying out tissue treatment at the predicted treatment settings; and (e) when the comparing of the prediction is greater than the safety limit, adjusting the tissue treatment settings, updating weights of the trained computational model, and repeating (c) through (e).

Description

2024PF00262 1 SYSTEM AND METHOD FOR PREDICTING SETTINGS FOR TREATMENT OF TISSUE AND TISSUE RESPONSE BACKGROUND Light therapy is being investigated to treat oral tissue. For example, certain wavelengths of light have been found to inhibit the growth of oral biofdms, thereby reducing dental plaque in a subject. Additionally, certain wavelengths of light have been found to reduce the inflammation response of human gingival cells. Accordingly, application of such light can reduce gingival inflammation (periodontitis). While light treatment therapy shows promise for reducing inflammation of a variety of tissues, using certain known devices, the time required to gather data related to the inflammation can be quite long. Moreover, after data are gathered, it may be difficult to determine the correct treatment, and particularly, the correct settings of the device used to provide the treatment. As a result, known methods of diagnosing and effectively treating inflamed tissue are rather inefficient. What is needed, therefore, is a method and system adapted to treat tissue that overcomes at least the known shortcomings of the known methods described above. SUMMARY In accordance with a representative embodiment, method of predicting tissue treatment settings and (NO) response of tissue is disclosed. The method comprises: (a) measuring nitric oxide (NO) tissue data from a personal healthcare device comprising fluorescent dots (Fdots); (b) applying a trained computational model to the NO tissue data to predict an NO response, and based on the predicted NO response, predicting tissue treatment settings; (c) comparing the predicted treatment settings to a safety limit; (d) when the comparing of the predicted treatment settings is equal to or below the safety limit, updating the predicted treatment settings and carrying out tissue treatment at the predicted treatment settings; and (e) when the comparing of the prediction is greater than the safety limit, adjusting the tissue treatment settings, updating weights of the trained computational model, and repeating (c) through (e). In accordance with another representative embodiment, a system for predicting tissue treatment settings and response of tissue is disclosed. The system comprises: a personal healthcare device comprising fluorescent dots (Fdots) adapted to detect nitric oxide (NO); a memory adapted to store a trained computational model comprising instructions; and a processor, wherein the instructions, when executed by the processor, cause the processor to: (a) receive measured nitric oxide (NO) tissue data from a personal healthcare device; (b) apply a trained computational model to predict an NO response, and based on the predicted NO response, predict tissue 2024PF00262 2 treatment settings; (c) compare the predicted treatment settings to a safety limit; (d) when the comparison of the predicted treatment settings is equal to or below the safety limit, update the predicted treatment settings and carrying out the tissue treatment at the predicted treatment settings; and (e) when the comparison of the prediction is greater than the safety limit, adjust the tissue treatment settings, update weights of the trained computational model, and repeat (c) through (e). In accordance with another representative embodiment, a tangible, non-transitory computer readable medium stores instructions, which when executed by a processor, cause the processor to: (a) receive measured nitric oxide (NO) tissue data from a personal healthcare device; (b) apply a trained computational model to the NO tissue data to predict an NO response, and based on the predicted NO response, predict tissue treatment settings; (c) compare the predicted treatment settings to a safety limit; (d) when the comparison of the predicted treatment settings is equal to or below the safety limit, update the predicted treatment settings and carrying out the tissue treatment at the predicted treatment settings; and (e) when the comparison of the prediction is greater than the safety limit, adjust the tissue treatment settings, update weights of the trained computational model, and repeat (c) through (e). BRIEF DESCRIPTION OF THE DRAWINGS The example embodiments are best understood from the following detailed description when read with the accompanying drawing figures. It is emphasized that the various features are not necessarily drawn to scale. In fact, the dimensions may be arbitrarily increased or decreased for clarity of discussion. Wherever applicable and practical, like reference numerals refer to like elements. Fig. 1 is a conceptual view showing sources of inflammation, resulting in production of NO, and resulting adverse effects. Fig. 2A is a perspective view of a mouthpiece comprising a material comprising fluorescing dots (Fdots) in accordance with a representative embodiment. Fig. 2B is a graph showing Fdot size versus emission wavelength. Fig. 3 is a graph showing onset of NO production in the presence