Predictive analysis tool for visual quality optimization

Abstract

Provided herein is a predictive analysis tool for optimizing the visual quality of a subject. The tool uses at least one of an optical quality index of the whole eye, an optical quality index of the cornea, or a lenticular dysfunction index as a preoperative condition input into the tool. The output is a type and at least one outcome of a technique performed on the eye of the subject. For each component in the pre-operative condition, an association between the measurement data of the pre-operative condition from the cloud library and the input data of the pre-operative condition is calculated to enable recommendation by the physician.

Description

Cross-references to related applications

[0001] This international patent application claims the benefit of priority to U.S. Provisional Patent Application Serial No. 63 / 500,255, filed May 4, 2023, pursuant to 35 USC §119(e), the entire contents of which are incorporated herein by reference. Background of the Invention Invention Field

[0002] This invention relates to the field of ophthalmology and analytical tools that can be used in ophthalmic endeavors. More particularly, this invention is an ophthalmic approach for ophthalmic examination and treatment, especially for predicting and optimizing ophthalmic surgical planning (including the selection of techniques, instrumental support, and replacement objects, such as intraocular lenses) based on visual quality measurements (visual quality is represented by its descriptive components: visual quality index (QVI), corneal performance index (CPI), and lens dysfunction index (DLI)).

[0003] Related Art

[0004] In the late 1940s, H. Ridley's work on replacing the lens of the cataract with an intraocular implant spurred research that provided a comprehensive description of human visual quality. F.W. Campbell and R.W. Gubisch, in their pioneering study of the optical quality of the human eye (J. Physiol., 1966, 186, pp. 558-578), utilized the modulation transfer function and its Fourier transform, namely the line spread function.

[0005] J. Liang and Dr. Williams focused on the impact of higher-order aberrations on retinal image quality (J. Opt. Soc. Am. A, 1997, 11, pp. 2873-2883). In U.S. Patent 7,357,509, Dr. Williams et al. proposed several metrics for predicting the subjective impact of wavefront aberrations on the eye, based on wavefront error or slope, critical pupil area, curvature parameters, point spread function, optical transfer function, etc. Other techniques include fitting spherical-cylindrical surfaces, using multivariate metrics, and customizing metrics for patient characteristics such as age.

[0006] These indicators are insufficient to predict the success rate of the planned surgery. Parameters for replacing the intraocular lens and the implantation technique have not been considered. Experience from similar cases should also be incorporated into the planning process.

[0007] K. Angelides proposed a management system for developing personalized health improvement programs that includes internet use for individual participants facing chronic diseases or persistent discomfort (US Patent 10,199,126). Its principles involve storing current information about the patient's condition and continuously obtaining external advice.

[0008] When planning ophthalmic surgery, physicians need to use stored experience and intentionally acquired data. For clinical use, empirical indices of visual quality are used, based on the Quality of Visual Index (QVI), Corneal Performance Index (CPI), and Lens Dysfunction Index (DLI), calculated from measured aberrations, taking into account empirically proven interactions between higher-order corneal and lens aberrations (F. Faria-Correia et al. J RefractSurg. 2016, 32, pp. 244-248).

[0009] Therefore, there is a recognized need in the art for an improved means of determining vision correction options and planning surgery accordingly. In particular, existing technologies lack a predictive analysis tool that utilizes descriptive components such as the Quality of Visual Index (QVI), Corneal Performance Index (CPI), and Lens Dysfunction Index (DLI). This invention addresses this long-standing need and expectation in the art. Summary of the Invention

[0010] This invention is a predictive analytics tool for visual surgical planning, comprising a large multi-input multi-output (MIMO) cloud library, an aberrometer with a wavefront analyzer, a central processing unit (CPU), a multiplexer, a Wi-Fi modem, and a signal splitter. In the preoperative phase, based on data collected by the aberrometer, the wavefront analyzer provides the CPU with indices of the eye's optical quality, corneal optical quality, lens optical dysfunction, and tear film condition. Upon obtaining requested access to the MIMO cloud library, the CPU allows the Wi-Fi modem to transmit data from the wavefront analyzer to the multiplexer and upload data to the cloud library via one of its open multi-input channels. Through one of the open multi-access cloud library outputs, the CPU accesses data stored in the cloud library and selects preoperative data most relevant to the current patient's data. The requested data is downloaded to the CPU via the Wi-Fi modem and the signal splitter. Through interactive operations via a central processor, doctors adjust the patient's condition and planned surgical goals to align with postoperative outcomes. This is achieved using surgical techniques, materials, and instruments employed by certified surgeons. After the surgery, the postoperative results, along with the surgical conditions, are uploaded to a cloud database.

[0011] Other and additional aspects, features, benefits, and advantages of the invention will become apparent from the following description of presently preferred embodiments of the invention as presented for the purposes of this disclosure. Attached Figure Description

[0012] To provide a detailed understanding of the above-described features of the invention, a more specific description of the invention, which has been briefly outlined above, is illustrated in the accompanying drawings. These drawings form part of this specification. However, although the accompanying drawings illustrate preferred embodiments of the invention, they should not be construed as limiting the scope of the invention.

[0013] FIG. 1 This is a schematic diagram of an electronic component that includes predictive analytics tools.

[0014] FIG. 2 The Dysfunction Index of the Lens (DLI) indicates a decline in visual function.

[0015] FIGS. 3A-3D Stage I cataracts were indicated by the lens dysfunction index. FIG. 3A Phase II FIG. 3B Phase III FIG. 3C ), spectra of states I, II and III ( FIG. 3D The study, which included 30,000 DLI scans based on patient age and cataract surgery history, presented the results. FIG. 3E ).

[0016] FIGS. 4A-4B The angular α and angular κ distances in the eye are shown. FIG. 4A ) and the results of a study based on the angle κ / α of 6800+ eyes ( FIG. 4B ).

[0017] FIGS. 5A-5B It shows an angle α with a low value. FIG. 5A ) and extremely high angle α ( FIG. 5B The optical system alignment measurement results in the eyes of the subjects.

[0018] FIGS. 6A-6D The results of corneal manifestations are shown. FIG. 6A ), corneal axis diagram ( FIG. 6B ), corneal manifestations at different radii ( FIG. 6C ) and corneal performance score ( FIG. 6D Examples of ).

[0019] FIG. 7 An example of the overall optical performance results is shown.

[0020] FIGS. 8A-8H The left (OS) eye of three subjects was shown. FIGS. 8A-8B8E-8F) and right (OD) eye ( FIGS. 8C-8D 8G-8H) preoperative ( FIG. 8A , 8C 8E, 8G) and postoperative ( FIG. 8B , 8D Lens pathology during 8F and 8H surgeries.

[0021] FIGS. 9A-9C The corneal pathology of three subjects is shown.

[0022] FIGS. 10A-10C Postoperative problems are shown.

[0023] FIGS. 11A-11B The data shows population statistics for CPI performance, including absolute counts ( FIG. 11A ) and relative frequency ( FIG. 11B ).

[0024] FIGS. 12A-12C The data shows population statistics for visual quality of vision (QVI) performance, including absolute counts ( FIG. 12A ), relative frequency ( FIG. 12B ) and the distribution of QVI scores for each of the deciles of the 4th to 10th age groups ( FIG. 12C ).

[0025] FIGS. 13A-13D The CPI (corneal performance index) is shown for each of the postoperative, preoperative, and non-operative populations. FIG. 13A ), Lens Dysfunction Index (DLI) FIGS. 13B-13C ) and Visual Quality Index (QVI) FIG. 13D The distribution of scores.

[0026] FIGS. 14A-14C It shows the initial ring ( FIG. 14A ), loss of sharpness ( FIG. 14B ) and discontinuity ( FIG. 14C Placido image.

[0027] FIGS. 15A-15B A normal tear film is shown. FIG. 15A ) and dry eyes ( FIG. 15B Tear film analysis and tear film analysis showed () FIG. 15C ). Detailed Implementation

[0028] As used herein, when used in conjunction with the term "comprising" in the claims and / or description, the term "a" or "an" may mean "one (type)," but also has the same meaning as "one (type) or more (types)," "at least one (type)," and "one (type) or more than one (type)." Some embodiments of the invention may consist of or substantially consist of one or more elements, method steps, and / or methods of the invention. It is understood that any method described herein can be implemented with respect to any other method described herein.

[0029] As used herein, the term “or” in the claims is used to mean “and / or” unless it is explicitly stated that it refers only to alternatives or that the alternatives are mutually exclusive (although this disclosure supports the definition of “and / or” referring only to alternatives).

[0030] As used herein, unless the context otherwise requires, “comprising” and its variations such as “including” and “containing” should be understood to mean including the stated item, element, or step, or a group of items, elements, or steps, but not excluding any other item, element, or step, or a group of items, elements, or steps. Similarly, “another” or “other” may mean at least a second or more of the same or different claim elements or components thereof.

[0031] As used in this article, "patient" and "subject" are interchangeable.

[0032] In one embodiment of the invention, a predictive analysis tool for optimizing the visual quality of a subject is provided, comprising a large multi-input multi-output (MIMO) cloud library with password access for authorized users, the multi-input data containing at least one component of the preoperative condition, and the multi-output data containing the type of technique performed on the subject's eyes and at least one outcome.

[0033] In this implementation, at least one component may include the optical quality index of the entire eye, the optical quality index of the cornea, or the lens dysfunction index. Furthermore, in this implementation, multiple input data of the preoperative condition can be measured for the subject to be treated. Additionally, for each component of the preoperative condition, the correlation between the measured data of the preoperative condition and the multiple input data of the preoperative condition from a cloud database can be calculated. Furthermore, at least one case with the highest preoperative condition correlation can be selected from the cloud database, and its ranking can be defined in a multidimensional vector space for each type of technique performed within the multiple output data from the cloud database and at least one outcome. Furthermore, a list of recommended techniques can be output for final approval by a physician.

[0034] The invention presented herein utilizes higher-order aberration data, in the form of indices, based on proprietary measurements of the corneal optical plane defined at the anterior surface of the cornea (including its tear film), where higher-order aberrations of the intraocular optical system are determined by subtracting corneal higher-order aberrations from those of the entire eye. Cumulative scores of each of these three indices—CPI, DLI, and QVI—in the eye before and after surgery, and before and after wearing corrective devices (such as contact lenses or glasses), can provide a tabular representation of data for future comparisons and analyses of patient outcomes. These indices are quantified in numerical ranges from 0 to 10 for such comparisons.

[0035] Examples of patients' visual outcomes at specific time points before or after any procedure (whether surgical or non-surgical) can be provided in tabular form during the creation of datasets that take into account patients' age, sex, and other population statistics, including patients' refractive errors. At the retinal plane, by utilizing the numerical differences between pre- and post-procedure, visual quality, as represented by deficiencies or decreases in higher-order aberrations, can now be measured for each component of the cornea, intraocular optical system, and the entire eye. In determining the most likely outcomes for new patients undergoing similar procedures or receiving specific implants (such as, but not limited to, intraocular lenses), the accumulated pre- and post-operative examinations from thousands or even millions of cases form raw data to provide predictive tools.

[0036] The predictive analytics tool for visual surgical planning consists of the following components: a large-scale multi-input multi-output (MIMO) cloud library 1, an aberrometer 2, a wavefront analyzer 3, a central processing unit 4, a multiplexer 5, a Wi-Fi modem 6, and a signal splitter 7. The MIMO cloud library 1 has multiple inputs for receiving information and data from qualified clients and multiple outputs for sending them information stored in its large database. The current patient's preoperative data is acquired by the aberrometer 2 and appropriately processed by its wavefront analyzer 3; these are typically integrated in a shared enclosure, such as the iTrace instrument from Tracey Technologies, Corp., TX. The wavefront analyzer 3 is electrically connected to the central processing unit 4, to which it transmits the current patient's preoperative data and to which it receives commands to initiate communication with the multiplexer 5. The Wi-Fi modem 6, controlled by the central processing unit 4, receives commands to upload the patient's preoperative data from the wavefront analyzer 3, along with other accompanying information (including the patient's personal information), from the central processing unit 4 to the cloud library 1. Alternatively, this predictive analytics tool is available in the absence of multiplexers and signal splitters.

[0037] In the preoperative phase, based on data collected by the aberrometer, the wavefront analyzer provides the central processing unit (CPU) with indices of the eye's optical quality, corneal optical quality, lens optical dysfunction, and tear film condition. After obtaining requested access to the MIMO cloud library, the CPU allows the Wi-Fi modem to transmit data from the wavefront analyzer to the multiplexer and upload data to the cloud library via one of its open multiple inputs. Through one of the open multiple-access cloud library outputs, the CPU accesses the data stored in the cloud library and selects the preoperative data most relevant to the current patient. The requested data is downloaded to the CPU via the Wi-Fi modem and multiplexer. Interacting with the CPU, the physician adjusts the patient's condition and planned surgical goals to align with postoperative outcomes, utilizing the surgical techniques, materials, and instruments used by certified surgeons. After surgery, the postoperative results, along with the surgical conditions, are uploaded to the cloud library.

[0038] Other and additional aspects, features, benefits, and advantages of the invention will become apparent from the following description of presently preferred embodiments of the invention as presented for the purposes of this disclosure.

[0039] Example 1

[0040] Disfunction Index (DLI)

[0041] The Dysfunction Index (DLI) is a single numerical value calculated from the eye's intraocular optical system, with the lens (natural or artificial) being the primary contributor. DLI is calculated from higher-order aberrations within the eye's intraocular optical system (e.g., via an aberrometer, more preferably via a true-forward ray-tracing aberrometer device), but can be similarly generated by other wavefront-based devices such as those using Hartmann-Shack sensors. DLI scores visual quality from the intraocular optical system (primarily the lens) on a scale of 0 to 10. Lower values ​​are associated with more dysfunctional lenses (negatively affecting the patient's visual quality) and can indicate early cataracts. Essentially, a low DLI is associated with an increased order of higher-order aberrations and is primarily associated with early cataract formation in patients over 50 years of age (especially below 5.0 – see references). Post-cataract surgery evaluation of DLI is also a useful tool for assessing the visual quality and performance of artificial lenses, as a high DLI close to 10 indicates very good optical lens performance, with a DLI score of q0 being ideal and promoting excellent vision. It is important to note that DLI, along with all visual quality indices, is independent of measurements of refractive errors from the spherical and cylindrical lenses. FIG. 2The DLI scale is shown, where green on the color scale represents "good," while warm colors correspond to decreased visual function. The letter "E" image reflects the visual quality from the intraocular optical system (lens).

[0042] Disfunction Syndrome

[0043] Stage I of lens aging occurs in the mid-40s to early 50s, characterized by decreased accommodative ability and lens aberrations. In this stage, the lens hardens and loses accommodative ability, leading to presbyopia. Higher-order lens aberrations progress to a DLI < 5, and visual quality declines. Stage II of lens aging occurs in the 50s to 60s and, in addition to the symptoms of Stage I, includes forward scattering of light through the lens. In this stage, there is increased higher-order lens aberration, with a DLI < 4. Small aggregates of lens proteins cause forward scattering, i.e., glare, and patients perceive bright colors as more "brownish." Stage III of lens aging occurs in the 60s to 80s and, in addition to the symptoms of Stages I and II, includes backscattering of light and lens opacity (cataracts). In this stage, large aggregates of lens proteins are present, causing backscattering or opacity of light and decreased visual function (poor contrast sensitivity), and glasses cannot correct to any normal acuity.

[0044] FIGS. 3A-3E A representative DLI patient is shown. FIG. 3A The image shows a 45-year-old patient with early stage I cataracts. FIG. 3B The patient presented with a stage II cataract, exhibiting observable opacity and a low DLI score. The cornea will support a toroidal high-end intraocular lens. FIG. 3C The patient presented with stage III cataracts, exhibiting a very low DLI score and a high degree of opacity (white area). The cornea was problematic, with irregularities in optical support for the advanced intraocular lens. FIG. 3D These are DLI spectra of lens aging stages I, II, and III. FIG. 3E This presentation shows the results of a large-scale DLI study from the Mayo Clinic, based on patient age and cataract surgery status. 30,000 scans were performed on patients aged 9 to 99 years.

[0045] Optical Alignment Measurement

[0046] FIG. 4A The positions of angles α ( ) and κ ( ) are shown as the distances from the vertical axis (VA) to the optical center (OC) of the cornea and to the center of the pupil (PC), respectively. FIG. 4BThe results are shown from a large-scale study of angle κ and angle α from over 6,800 eyes at the Mayo Clinic. Most angular displacements were horizontal and nasal-biased. Over 29% had results greater than 0.5 mm (500 micrometers). FIGS. 5A-5B These are two cases, showing good optical alignment (low angle α) in the first subject and extremely high angle α in the second subject. These subjects are respectively good candidates for multifocal intraocular lenses (MIOL) and poor candidates for MIOL.

[0047] Example 2

[0048] Corneal Performance Index (CPI)

[0049] The Corneal Performance Index (CPI™) is a single numerical value that scores the visual quality impact of higher-order aberrations produced at the anterior surface of the cornea. FIG. 6A The corneal optical power (including the tear film on the anterior surface of the cornea) is a key contributor to a patient's overall vision. The optical power of the cornea (including the tear film on the anterior surface of the cornea) produces most of the eye's refractive (focusing) ability. This visual quality index of the cornea is on a scale of 0 to 10, accompanied by bars showing how the score will be adjusted based on pupil size (e.g., from 2.50 mm to 4.00 mm, or any selected pupil size, typically up to 6.0 mm in diameter). The CPI value is automatically calculated from higher-order aberrations of the cornea and is typically targeted at larger pupil sizes (4–6 mm) that represent night vision, as this is usually the worst-case scenario with the lowest CPI, while 10 is ideal for perfect vision. However, if chosen in this way, the CPI can also be affected by the optical alignment between the corneal pupil and the natural lens, as this is crucial for determining high-end IOL candidate eligibility and selecting the IOL type (such as multifocal, astigmatic, aspheric, or monofocal). CPI has created a new standard to help eye care practitioners determine whether custom procedures such as LASIK or special contact lenses are needed to provide patients with the best possible visual quality after conventional spectacle correction for spherical and cylindrical refractive errors.

[0050] The Corneal Performance Index (CPI) rates the optical quality of the cornea by analyzing higher-order aberrations that reduce optical quality. It also considers optical alignment and pupil size as factors in daytime and nighttime analysis. FIG. 6A CPI is a visual quality index that measures the corneal performance at different radii of vision and within each radius. FIG. 6B CPI uses corneal topography images, cropped at different radii ranging from 2.5 to 4.5 mm, and then calculates a score for each of these points. FIG. 6C CPI attempts to address this issue by viewing corneal manifestations at different radii and obtaining those manifestations within each radius.FIG. 6D ).

[0051] Example 3

[0052] Visual Quality Index

[0053] The Quality of Visual Index (QVI) is a numerical score from 0 to 10 that rates the overall visual quality of the eye, utilizing higher-order aberrations measured at the retinal plane using ray tracing or wavefront techniques. Therefore, the QVI does not involve higher-level processing in the visual cortex, as its image generation at the retinal plane is strictly based on the eye's optical properties. Thus, the QVI uses only higher-order aberration information to generate its score. This QVI is designed to correlate with patient visual satisfaction after wearing standard optical corrections (such as standard glasses correcting low-order refractive errors, common spherical errors in myopia and hyperopia, with or without cylindrical astigmatism correction). The QVI is a 0-10 score for visual performance to identify complaints from patients who currently do not meet expectations by the typical 20 / 20 Snellen visual acuity standard. Many patients achieve 20 / 20 but are still dissatisfied with their vision because they still experience some blurriness or halos, etc. The QVI, or any other similar indicator (such as the WVI), is designed to objectively quantify the visual impairment experienced by such patients daily or nightly with or without spectacle correction, thus providing a new standard of visual quality care. The QVI quantifies the overall optical performance of the entire eye because it relates to the optical image focused on the retinal plane (primarily the macula) and can be selected for a specific pupil size or for an overall value. FIG. 7 ).

[0054] Example 4

[0055] Lens and Corneal Pathology and Post-Surgical Issues

[0056] Example of Lens Pathology for 3 Subjects

[0057] In case 1, the left eye (OS) is an example of lens dysfunction. FIG. 8A Slit-lamp examination revealed no cloudiness, but the patient's vision was impaired. FIG. 8B The same patient was shown Hand Postoperative improvement.

[0058] In case 2, the right eye (OD) showed signs of the patient's condition. Hand Early-onset cataracts before surgery FIG. 8C And with Symfony ZXR00 intraocular lenses Hand Postoperative cataracts FIG. 8D The patient is in HandPreoperative early-onset cataract in the left eye was shown FIG. 8E In the middle, while using Tecnis Multifocal ZLB00 Hand Postoperative findings FIG. 8F middle.

[0059] In case 3, Hand The patient had cataracts and had been treated for dry eye (keratoconjunctivitis sicca) before surgery. FIG. 8G ), and Hand Postoperatively, Symfony ZXR00 was obtained.

[0060] Example of Corneal Pathology for 3 Subjects

[0061] In case 4, the patient was a keratoconus patient with moderate corneal and overall visual performance. FIG. 9A ).

[0062] In case 5, the patient was a keratoconus patient with poor corneal and overall visual performance. FIG. 9B ).

[0063] In case 6, the patient had Reiss-Buckler corneal dystrophy ( FIG. 9C ).

[0064] Troubleshooting Post-Surgical Issues

[0065] In case 7, a patient undergoing hyperopia ablation received a refractive lens replacement using the Tecnis Premium ZLB00 IOL. Hand Post-surgery, the overall eye condition was poor, with minimal variation between day and night. The problem lay in the superposition of aberrations in the cornea and lens. FIG. 10A A close examination of the aberration distribution map revealed that the lens exacerbated the patient's overall visual problems. The two main problems associated with overall vision were astigmatism and coma. FIG. 10B Given that the patient has a non-toroidal IOL, the patient's optical alignment at least partially explains the coma and internal cylinder observed in this patient. FIG. 10C ).

[0066] CPI, DLI, and QVI offer solutions for improving visual quality. They quantify the “invisible” aberrations of the eye that affect and reduce QOV, show when the crystalline optics “compensate for or counteract” the corneal optics or when both superimpose, and correlate with patient visual satisfaction. They also provide predictive analytics to select the best visual correction treatment and when to tailor it to optimize QOV.

[0067] This determined how these indicators behaved across different population groups. The performance of the CPI across different population groups is shown... FIGS. 11A-11B In the middle, and QVI's performance is shown FIGS. 12A-12B The text includes a diagram showing the distribution of QVI scores based on age decimals. FIG. 12C In addition, for CPI ( FIG. 13A DLI FIGS. 13B-13C ) and QVI ( FIG. 13D The scores for each of the indicators are distributed among the post-operative, pre-operative, and non-operative populations.

[0068] Example 5

[0069] Tear Function Index (TFI)

[0070] The Tear Function Index is a comprehensive index with a single numerical score ranging from 0 to 10, used to quantify tear film quality and stability, as it is related to visual function. A score of 10 is ideal for providing excellent visual quality, since the tear film is the provider of the optical surface performance of the cornea.

[0071] In addition to tear film quality, TFI also considers:

[0072] 1. Spatial distribution of tear film quality (central tear film variation within 4 mm is located within the pupil and is more important for vision), and a two-dimensional map using color can be generated on the corneal surface for visualization if needed.

[0073] 2. Tear film dynamics: The stability over time or the time to reach peak stability after blinking can be integrated into the TFI score.

[0074] TFI utilizes the analysis of Placido images of the corneal surface, but may also include other measures of the eye’s optical or physical properties, including assessment of tear film volume and / or evaluation of water or lipid content levels.

[0075] New tear film analysis software, used in conjunction with the Tear Film Index (TFI), helps diagnose ocular surface diseases and analyze their impact on visual quality. The goal is to differentiate between irregular corneal astigmatism and ocular surface diseases and guide doctors and patients to the optimal treatment plan.

[0076] Tear Film Analysis with Placido Images

[0077] FIG. 14A The Placido ring is shown. Analysis of a series of Placido images detects the ring sharpness. FIG. 14B ) and discontinuity ( FIG. 14CTFI using Placido images provides objective measurements of ring mass changes over time using Fourier domain analysis, objective topographic tear film breakup time, and automatic focus / alignment verification and blink exclusion. FIG. 15A It shows a normal tear film, and FIG. 15B The tear film of a dry eye is shown. FIG. 15C The tear film analysis results are shown.

Claims

1. A predictive analytics tool for optimizing visual quality in subjects, the predictive analytics tool comprising: A big data multiple-input multiple-output (MIMO) cloud library, the cloud library having password access for its authorized users, the multiple-input data containing at least one component of the preoperative condition, and the multiple-output data containing the type of technique performed on the subject's eyes and at least one outcome.

2. The predictive analysis tool according to claim 1, wherein the at least one component includes the optical quality index of the whole eye, the optical quality index of the cornea, or the lens dysfunction index.

3. The predictive analytics tool of claim 1, wherein the multi-input data measuring the preoperative condition of the subject to be treated.

4. The predictive analysis tool of claim 1, wherein for each component of the preoperative condition, the correlation between the measurement data of the preoperative condition and the multi-input data of the preoperative condition from the cloud database is calculated.

5. The predictive analytics tool of claim 1, wherein at least one case with the highest preoperative condition correlation is selected from the cloud database, and its ranking is defined in a multidimensional vector space for each type of the technique performed within the multi-output data from the cloud database and the at least one outcome.

6. The predictive analytics tool of claim 5, wherein a list of recommended techniques is output for final approval by a physician.

Images