Isolated pulmonary nodule puncture sampling device and risk prediction model construction method

Abstract

The invention relates to an isolated pulmonary nodule puncture sampling device and a risk prediction model construction method.The isolated pulmonary nodule puncture sampling device comprises a guide tube and a puncture needle slidably connected into the guide tube, and a suction cup capable of being adsorbed to the skin of a patient is detachably and fixedly connected to the outer wall of the guide tube; a first through hole communicated with an inner cavity of the suction cup is formed in the pipe wall of the guide pipe, the puncture needle is in a hollow pipe shape, the lower end of the puncture needle is closed, a sampling hole is formed in the side wall of the lower end of the puncture needle, and a second through hole communicated with the first through hole is formed in the side wall of the upper end of the puncture needle. The upper end of the puncture needle is communicated with a negative pressure suction assembly. The invention aims to provide the isolated pulmonary nodule puncture sampling device and the risk prediction model construction method so as to solve the problems that in the prior art, a puncture needle mostly depends on manual fixation, stability of the puncture needle is difficult to maintain in the puncture process, and the risk that the puncture needle deviates from a target position is increased.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a solitary pulmonary nodule puncture sampling device and a risk prediction model construction method. Background Art

[0002] Solitary pulmonary nodules (SPNs) are common pulmonary imaging findings, and assessing their malignancy risk is crucial for the diagnosis of early-stage lung cancer. Currently, clinical risk assessment relies primarily on imaging features (such as nodule size, margin characteristics, and density as shown on CT scans) combined with clinical parameters (such as patient age and smoking history) to input into the Brock, PKUPH, Mayo, and VA models. However, single-image assessment has limitations, particularly for atypical nodules, which can make differentiation between benign and malignant.

[0003] To further assess the malignancy risk of a solitary pulmonary nodule, tissue samples must be collected for further analysis. These samples are typically collected by inserting a needle near the target nodule. However, these needles often rely on manual fixation, making it difficult to maintain stability during the procedure and increasing the risk of the needle deviating from its target position. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a solitary pulmonary nodule puncture sampling device and a risk prediction model construction method to solve the problem in the existing technology that the puncture needle mostly relies on manual fixation, making it difficult to maintain the stability of the puncture needle during the puncture process, and increasing the risk of the puncture needle deviating from the target position.

[0005] The present invention is achieved through the following technical solutions:

[0006] A puncture sampling device for an isolated pulmonary nodule comprises a guide tube and a puncture needle slidably connected to the guide tube; a suction cup that can be adsorbed on the patient's skin is detachably fixedly connected to the outer wall of the guide tube; a first through hole communicating with the inner cavity of the suction cup is provided on the tube wall of the guide tube; the puncture needle is hollow tubular and closed at the lower end; a sampling hole is provided on the side wall of the lower end of the puncture needle; a second through hole communicating with the first through hole is provided on the side wall of the upper end of the puncture needle; and the upper end of the puncture needle is connected to a negative pressure suction component.

[0007] Furthermore, a third through hole that matches the outer diameter of the guide tube is provided in the center of the suction cup, and the guide tube passes through the third through hole and slides with the suction cup. A baffle is fixedly connected to the suction cup, and a fourth through hole connected to the first through hole is provided on the baffle. A groove that matches the baffle is provided on the guide tube, and the baffle is slidably connected in the groove. A locking assembly is installed between the suction cup and the guide tube.

[0008] Furthermore, the locking assembly includes a plurality of arc-shaped plates, which are circumferentially distributed around the central axis of the guide tube, the suction cup is provided with a first slide groove adapted to the plurality of arc-shaped plates, and the plurality of arc-shaped plates are respectively slidably connected in the corresponding first slide grooves, and the tops of the plurality of arc-shaped plates are fixedly connected with push rods, the suction cup is provided with a second slide groove adapted to the plurality of push rods, and the plurality of push rods are respectively slidably connected in the corresponding second slide grooves, the second slide grooves are connected to the first slide grooves, and the guide tube is provided with a plurality of arc grooves adapted to the plurality of arc plates, and the plurality of arc grooves are evenly distributed along the length direction of the guide tube.

[0009] Furthermore, a protrusion is fixedly connected to one side wall of the plurality of arc-shaped plates, and a limiting groove adapted to the protrusion is provided on the side wall of the plurality of arc-shaped plates away from the protrusion, and the protrusion is embedded in the corresponding limiting groove.

[0010] Furthermore, the first through hole is a strip-shaped hole, and a plurality of support rods are fixedly connected in the first through hole, and the plurality of support rods are distributed along the length direction of the guide tube.

[0011] Furthermore, the lower end of the guide tube is cut with a first bevel, and the lower end of the puncture needle is cut with a second bevel that matches the first bevel, and the second bevel can be in the same inclined plane as the first bevel.

[0012] Furthermore, a blade is fixedly connected to the side wall of the sampling hole, and the blade extends along the length direction of the sampling hole.

[0013] Furthermore, the negative pressure suction component includes a negative pressure pump, and the input end of the negative pressure pump is connected to the upper end of the puncture needle.

[0014] A method for constructing a risk prediction model for solitary pulmonary nodules, comprising a solitary pulmonary nodule puncture sampling device,

[0015] Step 1: First collect the imaging characteristic parameters and clinical parameters of the patient's solitary pulmonary nodule;

[0016] Step 2: Input imaging feature parameters and clinical parameters into the Brock model, PKUPH model, and Mayo model, respectively, and calculate the malignancy risk scores of the Brock model, PKUPH model, and Mayo model;

[0017] Step 3: Determine the prediction errors of the Brock model, PKUPH model, and Mayo model through variance analysis, and assign weight coefficients accordingly;

[0018] Step 4: A weighted average algorithm is used to integrate and optimize to obtain a comprehensive risk score. When the comprehensive risk score is less than the set value, a comprehensive prediction model is directly established. When the comprehensive risk score is greater than the set value, a tissue sample of the patient's solitary pulmonary nodule is collected through the solitary pulmonary nodule puncture sampling device, and a pathological analysis of the tissue sample is performed. A comprehensive prediction model is established based on the pathological analysis results and the average value of the comprehensive risk score.

[0019] Furthermore, the weight coefficients are distributed as follows: 40% for the Brock model, 30% for the Mayo model, and 30% for the PKUPH model.

[0020] The beneficial effects of the present invention are:

[0021] This device and risk prediction model for puncture sampling of solitary pulmonary nodules employs a suction cup attached to the patient's skin to secure the guide tube relative to the skin. This reduces puncture deviation caused by respiratory movement or operator vibration, lowers the risk of the puncture needle straying from the target position, and improves puncture accuracy. The hollow design of the puncture needle, combined with negative pressure suction, ensures smooth entry of tissue samples into the sampling hole, improving sampling success rates, reducing the need for multiple punctures, and lowering the risk of complications such as pneumothorax and bleeding.

[0022] Other advantages, objects, and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art upon examination of the following description or may be learned from practice of the present invention. The objects and other advantages of the present invention may be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A perspective view of a first embodiment of the present invention;

[0024] Figure 2 This is a schematic structural diagram of Embodiment 1 of the present invention;

[0025] Figure 3 For the present invention Figure 2 A partial enlarged view of point A in the middle;

[0026] Figure 4 This is a schematic structural diagram of the guide tube of the present invention;

[0027] Figure 5 Schematic diagram of the structure of the puncture needle of the present invention;

[0028] Figure 6 This is a schematic diagram of the connection between the suction cup and the baffle of the present invention;

[0029] Figure 7 This is a schematic diagram of the connection between the arc plate and the push rod of the present invention;

[0030] Figure 8 The ROC curves of the four classic prediction models of Brock, Mayo, PKUPH and VA for solitary pulmonary nodules in healthy people undergoing physical examinations are shown in the figure.

[0031] Figure 9 This is a hierarchical analysis diagram of the ROC curves of the four classic prediction models of Brock, Mayo, PKUPH and VA for solitary pulmonary nodules in healthy physical examination population;

[0032] Figure 10 This is a hierarchical analysis diagram of the ROC curves of the four classic prediction models of Brock, Mayo, PKUPH and VA for solitary subsolid pulmonary nodules in healthy physical examination population;

[0033] Figure 11 The ROC curves of the Brock, Mayo, PKUPH and combined prediction models of the present invention for isolated solid pulmonary nodules in healthy people undergoing physical examinations are shown;

[0034] Figure 12 This is a clinical decision curve diagram of the Brock, Mayo, PKUPH and combined prediction models of the present invention for isolated solid pulmonary nodules in healthy physical examination populations;

[0035] Figure 13 This is the precision-recall curve of the Brock, Mayo, PKUPH and combined prediction models of the present invention for isolated solid pulmonary nodules in healthy people undergoing physical examinations;

[0036] Figure 14 This is a risk stratification analysis table for solitary solid pulmonary nodules using the Brock, Mayo, PKUPH and combined models of the present invention.

[0037] In the picture:

[0038] 1. Guide tube; 2. Puncture needle; 3. Suction cup; 4. First through hole; 5. Sampling hole; 6. Second through hole; 7. Negative pressure suction assembly; 8. Third through hole; 9. Baffle; 10. Fourth through hole; 11. Groove; 12. Locking assembly; 13. Arc plate; 14. First slide groove; 15. Push rod; 16. Second slide groove; 17. Arc groove; 18. Bump; 19. Limiting groove; 20. Support rod; 21. First inclined surface; 22. Second inclined surface; 23. Blade; 24. Negative pressure pump; 25. Hose. DETAILED DESCRIPTION

[0039] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0040] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0041] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0042] In the above description of the present invention, it should be noted that the terms "one side," "the other side," and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or the orientations or positional relationships in which the inventive product is typically placed when in use. These terms are intended solely to facilitate the description of the present invention and simplify the description, and are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and the like are used solely for distinction and should not be construed as indicating or implying relative importance.

[0043] Furthermore, the term "identical" and similar terms do not necessarily require that the components be absolutely identical; slight variations are permitted. The term "perpendicular" simply refers to the positional relationship between components being more perpendicular than "parallel," not that the structure must be perfectly vertical; rather, it can be slightly tilted.

[0044] Example 1:

[0045] See also Figure 1-7The present invention provides a technical solution: a solitary pulmonary nodule puncture sampling device, comprising a guide tube 1 and a puncture needle 2 slidably connected to the guide tube 1, wherein the lower end of the guide tube 1 is cut with a first inclined surface 21, and the lower end of the puncture needle 2 is cut with a second inclined surface 22 adapted to the first inclined surface 21, and the second inclined surface 22 can be in the same inclined plane as the first inclined surface 21, and the outer wall of the guide tube 1 is detachably fixedly connected with a suction cup 3 that can be adsorbed on the patient's skin, and the tube wall of the guide tube 1 is provided with a suction cup 3 that is adapted to the inner surface of the suction cup 3. The first through hole 4 connected to the cavity, the puncture needle 2 is hollow tubular and the lower end is closed, a sampling hole 5 is provided on the side wall of the lower end of the puncture needle 2, and a second through hole 6 connected to the first through hole 4 is provided on the side wall of the upper end of the puncture needle 2. The second through hole 6 and the sampling hole 5 are located on the same side of the puncture needle 2. The upper end of the puncture needle 2 is connected to a negative pressure suction component 7, and the negative pressure suction component 7 includes a negative pressure pump 24. The input end of the negative pressure pump 24 is connected to the upper end of the puncture needle 2, and a hose 25 is connected between the negative pressure pump 24 and the puncture needle 2.

[0046] A third through hole 8 is provided at the center of the suction cup 3 that is adapted to the outer diameter of the guide tube 1. The guide tube 1 passes through the third through hole 8 and slides with the suction cup 3. A baffle 9 is fixedly connected to the suction cup 3. The baffle 9 is provided with a fourth through hole 10 that is connected to the first through hole 4. A groove 11 that is adapted to the baffle 9 is provided on the guide tube 1. The baffle 9 is slidably connected in the groove 11. A locking assembly 12 is installed between the suction cup 3 and the guide tube 1. The locking assembly 12 includes a plurality of arc plates 13. The plurality of arc plates 13 are circumferentially distributed around the central axis of the guide tube 1. There is a first slide groove 14 adapted to the multiple curved plates 13, and the multiple curved plates 13 are respectively slidably connected in the corresponding first slide groove 14. The tops of the multiple curved plates 13 are fixedly connected with push rods 15. The suction cup 3 is provided with a second slide groove 16 adapted to the multiple push rods 15. The multiple push rods 15 are respectively slidably connected in the corresponding second slide groove 16. The second slide groove 16 is connected to the first slide groove 14. The guide tube 1 is provided with a plurality of curved grooves 17 adapted to the multiple curved plates 13, and the plurality of curved grooves 17 are evenly distributed along the length direction of the guide tube 1.

[0047] In this solution: by cutting the first bevel 21 and the second bevel 22 at the lower ends of the guide tube 1 and the puncture needle 2 respectively, the second bevel 22 can be in the same inclined plane as the first bevel 21. During the puncture process, the first bevel 21 and the second bevel 22 are aligned to form a continuous inclined puncture surface, reducing tissue resistance during puncture and achieving smooth penetration.

[0048] Because the puncture needle 2 is hollow and tubular with a closed lower end, a sampling hole 5 is defined on the sidewall of the lower end of the puncture needle 2. Once the first bevel 21 and the second bevel 22 are aligned, the sampling hole 5 aligns with the sidewall of the guide tube 1. With the lower end of the puncture needle 2 sealed, the risk of front-end blockage and pneumothorax during puncture is reduced. Rotating the puncture needle 2 180 degrees exposes the sampling hole 5, and the negative pressure generated by the negative pressure pump 24 directly acts on the sampling hole 5, enabling efficient extraction of tissue samples.

[0049] A bowl-shaped suction cup 3, capable of adsorbing onto the patient's skin, is removably fixedly attached to the outer wall of the guide tube 1. A first through-hole 4 is defined in the wall of the guide tube 1, communicating with the inner cavity of the suction cup 3. A second through-hole 6 is defined on the upper sidewall of the puncture needle 2, communicating with the first through-hole 4. A baffle 9 is fixedly attached to the suction cup 3, defining a fourth through-hole 10 communicating with the first through-hole 4. The suction cup 3 is secured to a suitable position within the guide tube 1. A negative pressure pump 24 generates negative pressure, directing air between the suction cup 3 and the patient's skin through the fourth through-hole 10, the second through-hole 6, the first through-hole 4, and the puncture needle 2, thereby adhering the suction cup 3 to the patient's skin, securing the guide tube 1 and reducing the risk of displacement during puncture. The second through-hole 6 and the sampling hole 5 are located on the same side of the puncture needle 2, allowing the second through-hole 6 to communicate with the first through-hole 4 after the sampling hole 5 is exposed, thereby enabling the negative pressure pump 24 to switch between the suction cup 3 and the sampling hole 5.

[0050] A third through hole 8 is provided in the center of the suction cup 3 to match the outer diameter of the guide tube 1. The guide tube 1 passes through the third through hole 8 and slides with the suction cup 3. A groove 11 is provided on the guide tube 1 to match the baffle 9. The baffle 9 is slidably connected in the groove 11. A plurality of arc-shaped plates 13 are installed between the suction cup 3 and the guide tube 1. The plurality of arc-shaped plates 13 are circumferentially distributed around the central axis of the guide tube 1. A first chute 14 is provided on the suction cup 3 to match the plurality of arc-shaped plates 13. 13 are respectively slidably connected to the corresponding first chute 14, and the tops of the plurality of curved plates 13 are fixedly connected to push rods 15. The suction cup 3 is provided with second chute 16 adapted to the plurality of push rods 15, and the plurality of push rods 15 are respectively slidably connected to the corresponding second chute 16. The second chute 16 is communicated with the first chute 14. The guide tube 1 is provided with a plurality of arc grooves 17 adapted to the plurality of curved plates 13, and the plurality of arc grooves 17 are evenly distributed along the length direction of the guide tube 1. After the suction cup 3 is slid to the appropriate position on the guide tube 1, the plurality of push rods 15 are pushed to drive the corresponding curved plates 13 to slide along the length direction of the first chute 14 and snap into the locking position in the arc grooves 17 of the guide tube 1, thereby achieving rapid locking / unlocking of the guide tube 1 and the suction cup 3. The circumferentially distributed curved plates 13 are evenly stressed, providing stable support and enhancing the sealing of the connection between the guide tube 1 and the suction cup 3, so that the guide tube 1 and the suction cup 3 are sealed.

[0051] Directions:

[0052] Step 1: Locate the target solitary pulmonary nodule through imaging (such as CT), mark the puncture point and determine the puncture path.

[0053] Step 2: Disinfect the puncture site and inject anesthetic to give the patient local anesthesia.

[0054] Step 3: Align the first bevel 21 and the second bevel 22, puncture the patient's puncture point through the guide tube 1 and the puncture needle 2, and slowly advance them to the vicinity of the target nodule.

[0055] Step 4: Move the suction cup 3 to a suitable position on the guide tube 1 so that the suction cup 3 fits on the patient's skin.

[0056] Step 5: Press the suction cup 3 onto the patient's skin and start the negative pressure pump 24 to allow the suction cup 3 to be adsorbed and fixed on the patient's skin.

[0057] Step 6: Push the multiple push rods 15 to insert the multiple arc-shaped plates 13 into the corresponding arc-shaped grooves 17 respectively, so that the suction cup 3 is fixed on the side wall of the guide tube 1 and sealed.

[0058] Step 7: Rotate the puncture needle 2 180 degrees to expose the sampling hole 5, and fit the second through hole 6 with the side wall of the guide tube 1, staggering the first through hole 4, and continue to advance the puncture needle 2 so that the sampling hole 5 is aligned with the target nodule.

[0059] Step 8: Start the negative pressure pump 24 again. Under the action of negative pressure, the tissue sample is sucked into the inner cavity of the puncture needle 2, completing the sampling.

[0060] Step 9: Slowly retract the puncture needle 2 so that the puncture needle 2 is located in the guide tube, push the push rod 15, and make the arc plate 13 withdraw from the corresponding arc groove 17, so that the suction cup 3 is not sealed with the guide tube, and the external air enters the suction cup 3 cavity through the gap between the suction cup 3 and the guide tube. Remove the suction cup 3, puncture needle 2 and guide tube, and press the puncture point to stop bleeding.

[0061] Step 10: Pull out the puncture needle 2 from the guide tube and take out the tissue sample for examination.

[0062] By attaching the suction cup 3 to the patient's skin, the guide tube is fixed relative to the patient's skin, reducing puncture deviation caused by respiratory movement or operator vibration, lowering the risk of the puncture needle 2 deviating from the target position, and improving puncture accuracy. The hollow design of the puncture needle 2, combined with negative pressure suction, ensures that the tissue sample enters the sampling hole 5 smoothly, improving the sampling success rate, reducing the need for multiple punctures, and reducing the risk of complications such as pneumothorax and bleeding.

[0063] In this embodiment, a protrusion 18 is fixedly connected to one side wall of the plurality of arc-shaped plates 13 , and a limiting groove 19 adapted to the protrusion 18 is provided on the side wall of the plurality of arc-shaped plates 13 away from the protrusion 18 , and the protrusion 18 is embedded in the corresponding limiting groove 19 .

[0064] In this solution, by fixing connecting protrusions 18 on one side wall of the plurality of curved plates 13, and providing limiting grooves 19 on the side wall of the plurality of curved plates 13 facing away from the protrusions 18, the protrusions 18 are fitted into the corresponding limiting grooves 19. This can further improve the sealing performance of the connection between the guide tube 1 and the suction cup 3, ensuring a tight fit between the guide tube 1 and the suction cup 3.

[0065] In this embodiment, the first through hole 4 is a strip-shaped hole, and a plurality of support rods 20 are fixedly connected in the first through hole 4 . The plurality of support rods 20 are evenly distributed along the length direction of the guide tube 1 .

[0066] In this solution, the first through hole 4 is designed as a strip-shaped hole, and multiple support rods 20 are fixedly connected to the first through hole 4. The multiple support rods 20 are evenly distributed along the length of the guide tube 1. Negative pressure is transmitted to the suction cup 3 through the first through hole 4. The support rods 20 maintain the stability of the through hole structure, reducing the probability of the first through hole 4 collapsing under the action of negative pressure.

[0067] In this embodiment, a blade 23 is fixedly connected to the side wall of the sampling hole 5 , and the blade 23 extends along the length direction of the sampling hole 5 .

[0068] In this solution, a blade 23 is fixedly connected to the side wall of the sampling hole 5, and the blade 23 extends along the length direction of the sampling hole 5. When the puncture needle 2 rotates, the sharp edge of the blade 23 assists in cutting the fibrous tissue.

[0069] Example 2:

[0070] See also Figure 8-14 The present invention provides a technical solution: a method for constructing a risk prediction model for solitary pulmonary nodules, comprising a solitary pulmonary nodule puncture sampling device,

[0071] Step 1: First collect the imaging characteristic parameters and clinical parameters of the patient's solitary pulmonary nodule;

[0072] Step 2: Input imaging feature parameters and clinical parameters into the Brock model, PKUPH model, and Mayo model, respectively, and calculate the malignancy risk scores of the Brock model, PKUPH model, and Mayo model;

[0073] Step 3: Determine the prediction errors of the Brock model, PKUPH model, and Mayo model through variance analysis, and assign weight coefficients accordingly; the weight coefficients are assigned as follows: 40% for the Brock model, 30% for the Mayo model, and 30% for the PKUPH model.

[0074] Step 4: A weighted average algorithm is used to integrate and optimize to obtain a comprehensive risk score. When the comprehensive risk score is less than the set value, a comprehensive prediction model is directly established. When the comprehensive risk score is greater than the set value, a tissue sample of the patient's solitary pulmonary nodule is collected through the solitary pulmonary nodule puncture sampling device, and a pathological analysis of the tissue sample is performed. A comprehensive prediction model is established based on the pathological analysis results and the average value of the comprehensive risk score.

[0075] This study included 668 patients with solitary pulmonary nodules (SPNs), including 82 (12.28%) with malignant tumors, including 51 (62.20%) with invasive adenocarcinomas, 4 (4.88%) with minimally invasive adenocarcinomas, 13 (15.85%) with adenocarcinoma in situ, and 14 (17.07%) with squamous cell carcinomas. All patients were diagnosed at early stages. Of these, 436 (65.24%) were male, with a mean age of 56.44 ± 12.24 years.

[0076] Externally validate the applicability of four classic prediction models, Mayo, Brock, PKUPH and VA, in risk assessment of small lung nodules in healthy people undergoing physical examinations.

[0077] according to Figure 8 The results showed that the Brock model had the best predictive efficiency, with an area under the curve (AUC) of 0.86; followed by the Mayo and PKUPH models, with AUCs of 0.83 and 0.82 respectively; the VA model had the worst predictive efficiency, with AUC = 0.71.

[0078] Stratified analysis of solitary solid and subsolid pulmonary nodules

[0079] according to Figure 9 and Figure 10 The results of the study showed that the prediction efficiency of the four prediction models of Brock, Mayo, PKUPH and VA for solitary solid pulmonary nodules was significantly better than that for solitary subsolid pulmonary nodules. The prediction efficiency of the four prediction models for solitary solid pulmonary nodules was 0.92, 0.92, 0.87 and 0.80 respectively. Figure 9 ; The AUCs for solitary subsolid pulmonary nodules were 0.83, 0.78, 0.77, and 0.65, respectively. Figure 10In summary, the Brock, Mayo, PKUPH, and VA prediction models are more suitable for risk prediction of solitary solid pulmonary nodules. The reason for this is that solitary solid pulmonary nodules are mainly composed of tumor types such as squamous cell carcinoma and lung adenocarcinoma, while solitary subsolid pulmonary nodules are mainly composed of tumor types such as carcinoma in situ and microinvasive adenocarcinoma. There are differences in the risk factors of solitary solid and solitary subsolid pulmonary nodules. Therefore, the Brock, Mayo, PKUPH, and VA traditional lung cancer prediction models are more suitable for risk prediction of solitary solid pulmonary nodules. In addition, the VA model's predictive efficacy for both solitary solid and solitary subsolid pulmonary nodules is significantly lower than that of the Brock, Mayo, and PKUPH models.

[0080] Construction of Mayo+Brock+PKUPH joint prediction model

[0081] Because the three classic prediction models, Brock, PKUPH, and Mayo, are independent models with comparable predictive performance (AUCs of 0.92, 0.92, and 0.87, respectively), the combined prediction model employed an average weighting approach. This approach was accomplished through three steps: ① Calculating the risk scores of each independent prediction model based on the original model parameters; ② Evaluating the variance of the prediction errors of each prediction model to determine the weight coefficient for each independent model; and ③ Re-adjusting the intercept term of the risk score to match the characteristics of the target population, fully accounting for undercalibration due to certain factors. The adjusted composite risk score was then combined using a simple weighted average method. Weights were assigned as follows: the Brock model was assigned a 40% weight, while the Mayo and PKUPH models were each assigned a 30% weight.

[0082] Evaluation of the predictive performance of the Mayo+Brock+PKUPH combined model for solitary solid pulmonary nodules

[0083] ① Prediction performance evaluation (ROC curve analysis)

[0084] according to Figure 11 The research results show that the predictive performance of the combined model is better than that of any single model, and the predictive performance AUC of the combined model reaches 0.95.

[0085] ②Clinical utility evaluation (decision curve analysis)

[0086] according to Figure 12 The results of the study showed that the combined model had better clinical net benefits than any single model.

[0087] ③Classification performance evaluation (precision-recall curve, PR curve analysis)

[0088] according to Figure 13The research results show that the precision and recall rate of the joint model is better than that of any single model, and the area under the precision and recall curve (AUC) is 0.65, 0.65, 0.51, and 0.70 respectively.

[0089] In summary, although the Brock and Mayo prediction models each exhibit superior predictive efficacy, clinical utility, and classification performance for solitary pulmonary nodules, both Brock and Mayo are based on data from Western populations. The combined prediction model, combining the Brock, Mayo, and PKUPH models, outperforms any of the individual models in terms of predictive efficacy, clinical utility, and classification performance. Therefore, the combined prediction model improves the overall risk prediction performance of the prediction model and provides a more reliable theoretical basis for the practical application of risk prediction for solitary pulmonary nodules in healthy populations undergoing physical examinations.

[0090] Risk stratification using Mayo, Brock, KUPH, and combined prediction models

[0091] ① By calculating the risk score of the joint model, the joint prediction model is divided into three risk levels, namely low risk, medium risk and high risk. The risk stratification of each risk prediction model is detailed in Figure 14 .

[0092] according to Figure 14 The results of the study showed that the combined prediction model was divided into three risk levels, with the malignancy probabilities of low, medium, and high risk levels being 0.95%, 15.38%, and 76.67%, respectively. The risk assessment of solitary pulmonary nodules by the risk prediction model was limited to baseline risk assessment, and follow-up observation of the changing trend of nodules was still required. This is of great significance for the prediction of benign and malignant solitary pulmonary nodules. Therefore, compared with the three single prediction models, the risk stratification of the combined prediction model is more suitable for risk stratification of solitary pulmonary nodules and health management decisions in healthy people undergoing physical examinations. However, the calculation of the risk score of the combined prediction model requires certain calculations and has a high demand for health management information. To facilitate the promotion and application of the combined prediction model in primary medical institutions, the risk stratification of the combined prediction model was simplified. Solitary pulmonary nodules can be divided into four risk levels by simple weighted average, namely risk level 0, risk level 1, risk level 2, and risk level 3. The malignancy probability of each risk level is 0% (0 / 166), 7.81% (5 / 64), 18.75% (6 / 32), and 64.86% (24 / 37), respectively.

[0093] When the probability of malignancy is greater than 64.86%, the solitary pulmonary nodule puncture sampling device is used to collect tissue samples of the patient's solitary pulmonary nodules, and the tissue samples are pathologically analyzed. A comprehensive prediction model is established based on the pathological analysis results and the average value of the comprehensive risk score, which can more accurately determine the probability of malignancy.

[0094] Establishment of the optimal threshold of the model

[0095] The optimal threshold of the model needs to be localized. In the analysis of solitary pulmonary nodules in this healthy population, the optimal thresholds of the joint model were 0.056 and 0.165, respectively; the optimal thresholds of the Brock model were 0.076, respectively; the optimal thresholds of the Mayo model were 0.158, respectively; and the optimal thresholds of the PKUPH model were 0.376, respectively.

[0096] This approach can more accurately stratify the risk of small pulmonary nodules detected by LDCT lung cancer screening in healthy individuals undergoing physical examinations, providing a theoretical basis for health management strategies. Furthermore, accurate risk stratification can reduce the missed diagnosis rate of high-risk nodules, improve early diagnosis rates, and optimize treatment opportunities. It can also prevent low-risk nodules from entering clinical diagnosis and treatment, reducing overdiagnosis and treatment of low-risk nodules. Furthermore, it can help healthy individuals undergoing physical examinations better understand the risks of isolated small pulmonary nodules, reduce excessive fear and anxiety about small pulmonary nodules, and rationally standardize the follow-up intervals and procedures for small pulmonary nodules.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the purpose and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A puncture sampling device for solitary pulmonary nodules, comprising a guide tube (1) and a puncture needle (2) slidably connected to the guide tube (1), characterized in that: A suction cup (3) capable of being adsorbed on the patient's skin is detachably fixedly connected to the outer wall of the guide tube (1), a first through hole (4) communicating with the inner cavity of the suction cup (3) is provided on the tube wall of the guide tube (1), the puncture needle (2) is hollow and tubular and has a closed lower end, a sampling hole (5) is provided on the side wall of the lower end of the puncture needle (2), a second through hole (6) communicating with the first through hole (4) is provided on the side wall of the upper end of the puncture needle (2), and the upper end of the puncture needle (2) is connected to a negative pressure suction component (7).

2. The solitary pulmonary nodule puncture sampling device according to claim 1, characterized in that: The suction cup (3) is provided with a third through hole (8) adapted to the outer diameter of the guide tube (1) at the center thereof, the guide tube (1) passes through the third through hole (8) and slides with the suction cup (3), a baffle (9) is fixedly connected to the suction cup (3), a fourth through hole (10) connected to the first through hole (4) is provided on the baffle (9), a groove (11) adapted to the baffle (9) is provided on the guide tube (1), the baffle (9) is slidably connected in the groove (11), and a locking assembly (12) is installed between the suction cup (3) and the guide tube (1).

3. The solitary pulmonary nodule puncture sampling device according to claim 2, characterized in that: The locking assembly (12) includes a plurality of arc-shaped plates (13), which are circumferentially distributed around the central axis of the guide tube (1); a first slide groove (14) adapted to the plurality of arc-shaped plates (13) is provided on the suction cup (3); the plurality of arc-shaped plates (13) are respectively slidably connected in the corresponding first slide groove (14); the tops of the plurality of arc-shaped plates (13) are fixedly connected with push rods (15); a second slide groove (16) adapted to the plurality of push rods (15) is provided on the suction cup (3); the plurality of push rods (15) are respectively slidably connected in the corresponding second slide groove (16); the second slide groove (16) is communicated with the first slide groove (14); a plurality of arc-shaped grooves (17) adapted to the plurality of arc-shaped plates (13) are provided on the guide tube (1); the plurality of arc-shaped grooves (17) are evenly distributed along the length direction of the guide tube (1).

4. The solitary pulmonary nodule puncture sampling device according to claim 3, characterized in that: A protrusion (18) is fixedly connected to one side wall of the plurality of arc-shaped plates (13), and a limiting groove (19) adapted to the protrusion (18) is provided on the side wall of the plurality of arc-shaped plates (13) away from the protrusion (18), and the protrusion (18) is embedded in the corresponding limiting groove (19).

5. The solitary pulmonary nodule puncture sampling device according to claim 1, characterized in that: The first through hole (4) is a strip-shaped hole, and a plurality of support rods (20) are fixedly connected in the first through hole (4), and the plurality of support rods (20) are evenly distributed along the length direction of the guide tube (1).

6. The solitary pulmonary nodule puncture sampling device according to claim 1, characterized in that: The lower end of the guide tube (1) is cut with a first bevel (21), and the lower end of the puncture needle (2) is cut with a second bevel (22) adapted to the first bevel (21), and the second bevel (22) can be in the same inclined plane as the first bevel (21).

7. The solitary pulmonary nodule puncture sampling device according to claim 1, characterized in that: A blade (23) is fixedly connected to the side wall of the sampling hole (5), and the blade (23) extends along the length direction of the sampling hole (5).

8. The solitary pulmonary nodule puncture sampling device according to claim 1, characterized in that: The negative pressure suction component (7) comprises a negative pressure pump (24), and the input end of the negative pressure pump (24) is connected to the upper end of the puncture needle (2).

9. A method for constructing a risk prediction model for solitary pulmonary nodules, comprising the solitary pulmonary nodule puncture sampling device according to claim 1, characterized in that: Step 1: First collect the imaging characteristic parameters and clinical parameters of the patient's solitary pulmonary nodule; Step 2: Input imaging feature parameters and clinical parameters into the Brock model, PKUPH model, and Mayo model, respectively, and calculate the malignancy risk scores of the Brock model, PKUPH model, and Mayo model; Step 3: Determine the prediction errors of the Brock model, PKUPH model, and Mayo model through variance analysis, and assign weight coefficients accordingly; Step 4: Use the weighted average algorithm to integrate and optimize to obtain a comprehensive risk score. When the comprehensive risk score is less than the set value, directly establish a comprehensive prediction model; When the comprehensive risk score is greater than the set value, a tissue sample of the patient's solitary pulmonary nodule is collected by the solitary pulmonary nodule puncture sampling device, and a pathological analysis of the tissue sample is performed. A comprehensive prediction model is established based on the pathological analysis results and the average value of the comprehensive risk score.

10. The method for constructing a risk prediction model for solitary pulmonary nodules according to claim 9, characterized in that: The weight coefficients were distributed as follows: 40% for the Brock model, 30% for the Mayo model, and 30% for the PKUPH model.

Images