Clinical decision support system, method and apparatus

Abstract

The field of the invention is the support and care of those impacted by autism or other forms of neurodiversity. Autism Spectrum Disorders (ASD), ADHD, BPD, and OCD represent a group of neurodevelopmental disorders characterized by social communication challenges, repetitive behaviors, and restricted interests. The accurate diagnosis and effective treatment of such conditions significantly improves patient outcomes. However, healthcare professionals face challenges in accurately diagnosing ASD and determining optimal treatment approaches due to the complex nature of the disorder and the heterogeneity of symptoms among individuals. The CDSS of the present invention provides a much needed solution.

Description

[0001]^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION CLINICAL DECISION SUPPORT SYSTEM, METHOD AND APPARATUS FIELD AND BACKGROUND OF THE INVENTION Clinical Decision Support System (CDSS) to assist caregivers in delivery of treatment to people impacted by Autism Spectrum Disorder (ASD) and other forms of neurodiversity. This patent disclosure provides a Clinical Decision Support System, “CDSS”, for use by clinicians seeking to treat a wide array of neurodevelopmental conditions, including Autism Spectrum Disorders (ASD), Attention Deficit Hyperactivity Disorder (ADHD), and other forms of neurodiversity which often emerge as co-morbidities of any particular diagnosis. It is today recognized that the line between where ASD ends and, e.g. ADHD begins, includes significant overlaps. In fact, in at least one model see Fig. 1A, a significant amount of overlap is shown between diagnoses with such diverse spectra as Borderline Personality Disorder, (BPD), ADHD, and ASD (see Dr. Neff’s posting at https: / / neurodivergentinsights.com / misdiagnosis-monday / borderline-personality-disorder-adhd-and-autism, accessed on June 6, 2023; see also, for example, Dudas et al., (2017) “The overlap between autistic spectrum conditions and borderline personality disorder.” PLoS ONE 12(9): e0184447. https: / / doi.org / 10.1371 / journal. pone.0184447). The overlaps and conflation of these various conditions is at least one contributing factor in the below discussed explosive rise in such diagnoses in recent years, hi- lighting the critical need for the present invention. The present invention addresses these divergent and overlapping behavioral profiles, to rationalize therapeutic interventions optimized as between ASD, ADHD, Obsessive Compulsive Disorder (OCD), Oppositional Defiance Disorder (ODD), BPD, and the like. These conditions represent a group of neurodevelopmental disorders characterized by social communication challenges, repetitive behaviors, and restricted interests. The accurate diagnosis and effective, rational, outcome-based treatment of ASD, ADHD, OCD, BPD, and other conditions or co- morbidities, were such is available, is anticipated to significantly improve patient outcomes. ^ Page 1 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION However, healthcare professionals face challenges not only in accurately diagnosing, but also in determining optimal treatment approaches, due to the complex nature of these disorders and the heterogeneity of symptoms among individuals. The first CDSS, called MYCIN, was built in the early 1970s at Stanford University. It outperformed medical staff in evaluation accuracy, but was slow in performance and too ahead of its time to be adopted. Computerized systems can take a labor-intensive job of sifting through tons of data and making countless comparisons to narrow down the number of possible decisions - from hundreds and thousands to just a few . In the field of Clinical Treatment planning and execution, binary thinking, by definition, is the position or framework in which only two sides to a given issue are recognized, and one can only pick one or the other of these options. Binary thinking helps us feel a sense of certainty. Also known as dichotomous thinking, this way of thinking becomes simple for us to move through complex ideas and situations. However, gray areas exist between and often on either side of complex issues. This complexity and nuance is often ignored or it goes unnoticed. The uncertainty of complexity can be scary and anxiety-provoking, leading to reductionist binary thinking, especially during uncertain times such as the present. On average, in the United States, the average human makes about 35,000 decisions a day. Human brains are prone to error, especially, when dealing with large volumes of information in high-stress clinical environments. The world's complexity can be overwhelming, especially when thinking about the global pandemic, social unrest, and climate change, and the sheer amount of data being generated moment by moment. When evaluating and comparing a range of data points, whether related to health outcomes, head counts, or menu prices, the relative strength of evidence can be lost if treated as simply one of two binaries which become ingrained in the "operating systems" of our brains, creating biases ^ Page 2 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION With reference to Fig. 1B, in 1999, a common textbook estimated the prevalence of autism diagnosed in the population to be about 1 in every 1,000 individuals. The gold standard treatment was called “Applied Behavior Analysis” or “ABA therapy”, for which certification was just beginning, meaning there was a dearth of providers. Neither funding nor insurance coverage was available. Due to a multitude of factors, many imagined and many real, between 2000 and 2023 ASD diagnoses have reached a prevalence of 1:36 individuals, a 250% increase! There is increased and earlier diagnosis thanks to the availability of services and coverage, and the reduction in the stigma once associated with an early childhood diagnosis of autism that helped motivate physicians' awareness. There are also legitimate changes in medical understanding of autism and neurodiversity, and indeed just more autism; Figure 1C shows rise in ABA providers but the relatively low experience of 50% of practitioners and the absence of standardized approaches to treatment of these various, divergent and overlapping conditions. With reference to Figure 2, there is now coverage for services in all 50 states, however, the growth of the autism service market has outpaced quality. Twenty years ago, there were I1,500 certified providers in the world. There are now 60,000 providers.There has been a 500% increase in providers in the past 10 years. However, with reference to Figure 3, over half of the providers have less than 5 years experience, there are still not enough providers, and there are not enough senior clinicians to support or mentor this young field, resulting in poor quality and disorganized provision of services. The collision of changes in the DSM criteria, the dawn and adoption of the internet, the resulting campaign of #autismawareness and #autismsupport, the inception and spread of insurance mandates, and the growth in the #abatherapy workforce, have all contributed to creating a flywheel of growth in the diagnosis, number of service recipients, and number of service providers. FIGURE 4 provides a graphic representation of the multitude of clinical indicators that have to be taken into account in making an accurate diagnosis of ASD. Then, due to the lack of ^ Page 3 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION standards, a black box of individual care giver skills, patient preferences, and environmental support systems that are available or not, define care. There is no centralized dogma or methodology to drive consistency, quality, and efficiency as therapeutic interventions are undertaken. Accordingly, there may be as many as 100 different treatment plans established for a given patient, if presented to 100 different clinicians. As a threshold to intervention, even the definition of medical necessity has been murky: "Medical necessity refers to a patient-centered determination of the most appropriate effective treatment option for each individual patient, made by a treating provider, in accordance with generally accepted standards of practice that are evidence-based, evidence-informed, or services based on consensus advisory opinion recommended by recognized health care professionals, are necessary to remediate, rehabilitate, or ameliorate the symptoms and other effects of diagnosed conditions in order to enhance health and safety, improve overall functioning, and prevent deterioration and regression. Medical necessity determinations are not made primarily for the economic benefit of the health plans and purchasers or for the convenience of the patient, treating provider, or other health care provider.” ACQ Accreditation Standards. While coherent English, this definition of Medical Necessity leaves interventions, payment or acceptance of treatments to wide interpretations, and errors in treatment for patients. Accordingly, in light of the many problems noted above in the field, there is a long-felt need for a systematic, methodology and apparatus, to guide a course of practice which in fact systematizes therapeutic interventions, starting with a workable definition of Medical Necessity, which is incorporated into an holistic approach to segmenting different therapeutic interventions according to what is ultimately most effective in treating such conditions, without necessarily being bound to a particular “diagnosis”. ^ Page 4 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION SUMMARY OF THE INVENTION The present invention comprises a Clinical Decision Support System (CDSS) designed to assist healthcare professionals in appropriately treating patients diagnosed with Autism Spectrum Disorders (ASD), or other form of neurodiversity. The system of this invention incorporates advanced data analysis techniques, machine learning algorithms, and evidence-based guidelines to provide personalized recommendations based on patient-specific data, while operating agnostically with respect to “diagnosis”. The CDSS of this invention comprises several modules, including: (a) an interface layer or module, for input of information such as behavioral, medical, or genetic or combinations of such information from various sources, including electronic health records, caregiver reports, and wearable devices, and for receipt, display or transmission of clinical decision support from the system; (b) an engine to manage all elements of the system, and (c) a data management layer or module. The data analysis module applies machine learning algorithms, including natural language processing and feature selection techniques, to analyze the patient data and identify indicators of appropriate ASD interventions, in a preferred embodiment, leveraging the power of artificial intelligence to recognize patterns, detect correlations, and extract relevant information from textual data to provide actionable insights in preferred treatment modalities predictive of successful therapeutic intervention for a given patient. The treatment recommendations of the CDSS are derived from utilization and refinement of the treatment of different patients presenting with any of a variety of ASD diagnoses or diagnoses of neurodivergence. To ensure best practices in the field, factors such as patient preferences, co- morbidities, previous treatment responses, evidence-based guidelines, scientific literature, and expert knowledge are used to produce treatment recommendations tailored to a given individual's needs, facilitating efficient decision-making and enhancing patient care. ^ Page 5 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION BRIEF DESCRIPTION OF THE DRAWINGS Figure 1, Fig. 1A, provides a graphic representation showing the overlaps between conditions including but not limited to ASD, ADHD, and BPD; Fig. 1B, provides a graphic representation of the rise in autism prevalence between 2000 and 2023, a 250% increase; Figure 1C shows rise in ABA providers but the relatively low experience of 50% of practitioners and the absence of standardized approaches to treatment of these various, divergent and overlapping conditions. Figure 2 provides a further representation of autism prevalence increase with further granularity. Figure 3 provides a graphic representation of the many therapeutic considerations currently going into a "black box” due to the lack of a standardized therapeutic approach and the relative inexperience of practitioners. Figure 4 provides a further graphic representation of the plethora of considerations necessary to arrive at an effective and efficient treatment plan for any given patient; it shows the complexity of the black box into which such considerations are currently funneled, due to the absence of objective standards as to when it is necessary for an intervention to occur, what that therapeutic intervention should be, i.e. an effective treatment plan based on delivery of objectively measurable value. Figure 5, in Fig. 5A provides a high-level graphic representation of one embodiment of the CDSS of the present invention, including an interface layer, an engine, and a data management layer, each of which are discussed in further detail herein below; Fig. 5B provides a further graphic representation of an embodiment of the CDSS according to the current invention, including: (a) an input module, which includes at least (i) Patient Clinical Data, (ii) Clinician choices, and (iii) “domain knowledge”; ^ Page 6 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION (b) an engine to sift the input to produce a custom treatment pathway optimized and personalized by the engine for a particular patient; and (c) Output of custom treatment pathways to support clinical decision-making. Figure 6 provides a graphic representation of the Custom CDSS engine according to this invention, depicted in Fig.5B. Figure 7 shows an exemplary set of data inputs, and defined tools suggested by the CDSS engine of this invention, for treatment of a given patient presenting with the given set of “x-ed” deficits at different ages of development. Figure 8 provides a graphic showing how appropriateness of treatment is addressed according to the present invention, considering both the chronological age of the patient and relevant developmental milestones, to arrive at an appropriate goal to be achieved by the intervention. Figure 9 shows interactions between a non-knowledge-based CDSS, showing how, rather than consulting with a library of predefined if / then rules, the present svstem learns from past experiences and finds patterns in historical data, using either or both (i) genetic algorithms (GA) reflecting the mechanics of heredity and natural selection, such that, just as species change from generation to generation to better fit their environment, GAs adapt to a new task, producing a number of random solutions and then iteratively evaluating and improving them until the most fitting option is found, and (ii) Artificial Neural Networks (ANN) that mimic human thinking. Similar to human brains, ANNs have a set of "neurons" called "neurods." They are linked to each other with weighted connections that act as nerve synapses transmitting signals across the neural network; non-knowledge-based systems come with a promise to significantly cut healthcare costs and relieve the pressure on medical experts. However, there are issues preventing their large-scale adoption. They include a compute-intensive and time-consuming training process and the requirement of large datasets needed to improve accuracy of models. But the main obstacle is the lack of interpretability as systems can't explain the reasoning behind generated decisions. ^ Page 7 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION Due to drawbacks mentioned, modern CDSSs, unlike the present invention, are primarily knowledge-based. FIGURE 10, Fig. 10A, shows the key interfaces between considerations of Medical Necessity and Quality of Life (QoL) goals utilized by the present CDSS engine to arrive at an appropriate goal for a given patient, including (i) treatment tied to a relevant assessment, (ii) impact of the treatment on the symptom under consideration, (iii) impact of the treatment on QoL, (iv) baseline data for the given individual, (v) the social validity of the treatment, (vi) and DSM criteria; furthermore, in figure 10B, a further filter is described as the “Ethical Efficacy Model of Selection”, whereby, as can be seen from the figure, the interactions between the following six considerations are balanced: .A. Client treatment preferences, which is balanced agains both (i) potential harm at which this patient is at risk of due to the diagnosed condition, and the (ii) low generality, i.e. high specificity of the condition; B. Clinician competence, which is balanced against both (ii) low generality, i.e. high specificity of the condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not; C. Environmental supports, which is balanced against both (i) potential harm at which this patient is at risk of due to the diagnosed condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not. FIGURE 11, Fig. 11A, provides a depiction of a payment based outcome goal, while Fig. 11B, shows how the method applied according to the present invention, namely, the scientific method, satisfies this objective; and finally, in Fig. 11C, how the mutual goal of achieving efficient, effective and optimal outcomes is achieved, i.e. by balancing and integrating payor, provider, and patient needs and considerations in the reimbursement process. FIGURE 12, Fig.12A considers adoption and potential impact of this invention; Fig.12B. FIGURE 13A provides a representation of adoption rate estimates; Fig.13B, notes that insurance companies are early adopters of new tech. ^ Page 8 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION FIGURE 14 shows a sample treatment plan that can be produced according the CDSS of the present invention. DETAILED DISCLOSURE OF THE PREFERRED EMBODIMENTS OF THE INVENTION As noted above, this patent disclosure provides a Clinical Decision Support System, “CDSS”, for use by clinicians seeking to treat a wide array of neurodevelopmental conditions, including Autism Spectrum Disorders (ASD), Attention Deficit Hyperactivity Disorder (ADHD), and other forms of neurodiversity which often emerge as co-morbidities of any particular diagnosis. The overlaps and conflation of these various conditions is at least one contributing factor in the explosive rise in such diagnoses in recent years, hi-lighting the critical need for the present invention. The present invention addresses these divergent and overlapping behavioral profiles, to rationalize therapeutic interventions optimized as between ASD, ADHD, Obsessive Compulsive Disorder (OCD), Oppositional Defiance Disorder (ODD), BPD, and the like, while being largely agnostic to such diagnoses. These conditions represent a group of neurodevelopmental disorders characterized by social communication challenges, repetitive behaviors, and restricted interests. The accurate diagnosis and effective, rational, outcome-based treatment of ASD, ADHD, OCD, BPD, and other conditions or co-morbidities, were such available, is anticipated to significantly improve patient outcomes. However, healthcare professionals face challenges not only in accurately diagnosing, but also in determining optimal treatment approaches, due to the complex nature of these disorders and the heterogeneity of symptoms among individuals. The present invention addresses and overcomes these problems in the art. With respect to filters referred to herein for implementation in a CDSS according to this invention, those skilled in the art will appreciate that the filters utilized herein are applicable ^ Page 9 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION across the range of neurodiversity referenced herein as co-morbidities with ASD, are defined by consideration of and consistency with therapeutic indicators, and are applicable across the full scope of the claims. Of course, in some instances, the system, method and apparatus according to this invention is useful, including when ASD, or ADHD, or BPD, or OCD is a relatively minor component of the neurodiversity challenges of a given patient. Furthermore, based on the present disclosure, as knowledge builds regarding the various conditions addressed herein, the relevant therapeutic indicators and hence the filters defined herein and equivalents thereof are refined and become increasingly specialized, based on the range of symptoms clinicians are presented with and the outcomes of various treatment modalities adopted across the spectrum of such conditions. Figure 1, Fig. 1A, provides a graphic representation showing the overlaps between conditions including but not limited to ASD, ADHD, and BPD; Fig. 1B, provides a graphic representation of the rise in autism prevalence between 2000 and 2023, a 250% increase; Figure 1C shows rise in ABA providers but the relatively low experience of 50% of practitioners and the absence of standardized approaches to treatment of these various, divergent and overlapping conditions. This data is supported by the additional data shown in Figure 2, autism prevalence increase with further granularity. The state of the art is represented in Figure 3, which provides a graphic representation of the many therapeutic considerations currently going into a therapeutic "black box”, due to the lack of a standardized therapeutic approach and the relative inexperience of practitioners. Finally, in Figure 4, a further graphic representation is provided of the plethora of considerations necessary to arrive at an effective and efficient treatment plan for any given patient. This shows the complexity of the black box into which such considerations are currently funneled, due to the absence of objective standards as to when it is necessary for an intervention to occur what that therapeutic intervention should be, i.e. an effective treatment plan based on delivery of objectively measurable value. It is believed that similar increases have been observed in the areas of ADHD, OCD, and other related forms of neurodivergence addressed and discussed herein. ^ Page 10 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION Referring now to Figure 5, which, in Fig.5A provides a high-level graphic representation of one embodiment of the CDSS of the present invention, including an interface layer, an engine, and a data management layer, each of which is discussed in further detail herein below; in Fig. 5B, a further graphic representation of an embodiment of the CDSS according to the current invention is provided, including: (a) an input module, which includes at least (i) Patient Clinical Data, (ii) Clinician choices, and (iii) “domain knowledge”; (b) an engine to sift the input to produce a custom treatment pathway optimized and personalized by the engine for a particular patient; and (c) Output of custom treatment pathways to support clinical decision-making. Figure 6 provides a graphic representation of the Custom CDSS engine according to this invention, depicted in Fig.5B. The engine 100 is implemented, for example, via a Software as a Service “SAAS” model, or is sold outright to enterprises needing CDSS. The Custom CDSS according to this invention includes a system, method and device, each of which requires balancing of key therapeutic considerations. A primary set of therapeutic indicators, (1) includes, at a minimum: (1) toileting 101, sleep 102, feeding 103, and communication 104, and these indicators are heavily weighted as required treatment indicators. A secondary set of therapeutic indicators (2) includes, at a minimum: caregiver guidance 105, access to care 106, and transition of care 107, and these therapeutic indicators are likewise weighted by the engine; a third set of therapeutic indicators (3) includes, at a minimum: (3) medical necessity 108, goal selection 109, and data collection 110; a fourth set of therapeutic indicators (4), includes, at a minimum, ops forecasts 111, client intake 112, and intensity of treatment 113. In Figure 7, an exemplary set of data inputs are shown, and an exemplary set of therapeutic tools are suggested by the CDSS engine for treatment of a given patient presenting with the given set of “x-ed” deficits at different ages of development. ^ Page 11 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION Additional elements of the CDSS Engine according to the present invention are next addressed and described in sufficient detail such that, based on the present disclosure, a skilled artisan is fully enabled to practice this the full scope of this invention as defined in the claims. An appropriateness of treatment metric includes, as shown in Figure 8, weighing of candidate therapeutic options with appropriateness of treatment by considering both the chronological age of the patient and relevant developmental milestones to arrive at an appropriate goal to be achieved were the therapeutic treatment intervention suggested by the CDSS of this invention to be implemented. In Figure 9 interactions are shown between a non-knowledge-based CDSS, showing how, rather than consulting with a library of predefined if / then rules, the present system learns from past experiences and finds patterns in historical data, using either or both (i) genetic algorithms (GA) reflecting the mechanics of heredity and natural selection, such that, just as species change from generation to generation to better fit their environment, GAs adapt to a new task, producing a number of random solutions and then iteratively evaluating and improving them until the most fitting option is found, and (ii) Artificial Neural Networks (ANN) that mimic human thinking. Similar to human brains, ANNs have a set of "neurons" called "neurods." They are linked to each other with weighted connections that act as nerve synapses transmitting signals across the neural network; non-knowledge-based systems come with a promise to significantly cut healthcare costs and relieve the pressure on medical experts. However, there are issues preventing their large-scale adoption. They include a compute-intensive and time-consuming training process and the requirement of large datasets needed to improve accuracy of models. But the main obstacle is the lack of interpretability as systems can't explain the reasoning behind generated decisions. Due to drawbacks mentioned, modern CDSSs, unlike the present invention, are primarily knowledge-based. The present invention solves these issues. With reference to FIGURE 10, Fig. 10A, shows the key interfaces between considerations of Medical Necessity and Quality of Life (QoL) goals utilized by the present CDSS engine to arrive ^ Page 12 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION at an appropriate goal for a given patient, including (i) treatment tied to a relevant assessment, (ii) impact of the treatment on the symptom under consideration, (iii) impact of the treatment on QoL, (iv) baseline data for the given individual, (v) the social validity of the treatment, (vi) and DSM criteria; furthermore, in figure 10B, a further filter is described as the “Ethical Efficacy Model of Selection”, “EEMS”, whereby, as can be seen from the figure, the interactions between the following six considerations are balanced: .A. Client treatment preferences, which is balanced agains both (i) potential harm at which this patient is at risk of due to the diagnosed condition, and the (ii) low generality, i.e. high specificity of the condition; B. Clinician competence, which is balanced against both (ii) low generality, i.e. high specificity of the condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not; C. Environmental supports, which is balanced against both (i) potential harm at which this patient is at risk of due to the diagnosed condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not. Selecting the "best" treatment, communication modality, intervention, and the like, is always and always has to be a weighted choice. In rare circumstances the client, environment, and clinician might all agree on the "best" choice, with there being no inherent deficit in any element considered alone. In other circumstances, there may only be a "match" between two out of three elements of the EEMS, which means that there will be two options each with potential benefits and risks which can and should be presented to the client for informed consent. In other rare circumstances, there may be a three-way "tie" between choices, and making the balance between potential benefits and risks even more complex, and making it even more critical to understand and communicate with all stakeholders to achieve balanced treatment plan, notwithstanding these considerations being in tension. The engine of the present CDSS identifies, isolates and balances these considerations as one of the critical filters implemented by the engine. With reference to FIGURE 10, Fig. 10A, shows the key interfaces between considerations of Medical Necessity and Quality of Life (QoL) goals utilized by the present CDSS engine to arrive at an appropriate goal for a given patient, including (i) treatment tied to a relevant assessment, (ii) impact of the treatment on the symptom under consideration, (iii) impact of the treatment on ^ Page 13 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION QoL, (iv) baseline data for the given individual, (v) the social validity of the treatment, (vi) and DSM criteria; furthermore, in Fig. 10B, a further filter is described as the “Ethical Efficacy Model of Selection”, whereby, as can be seen from the figure, the interactions between the following six considerations are balanced: .A. Client treatment preferences, which is balanced agains both (i) potential harm at which this patient is at risk of due to the diagnosed condition, and the (ii) low generality, i.e. high specificity of the condition; B. Clinician competence, which is balanced against both (ii) low generality, i.e. high specificity of the condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not; C. Environmental supports, which is balanced against both (i) potential harm at which this patient is at risk of due to the diagnosed condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not. In Value Based Reimbursement (VBR) provides an alternative and methodology to transcend what is often a “zero-sum game” impasse. The CDSS of the present invention provides a solution in the best interest of all three parties, Payor, Provider, and Patient, by ensuring consistency with the overarching filter defining the mutual goal of: Efficient, Effective, with Optimal Outcomes. To be effective, this filter and CDSS requires transparency and agreements on clinical standards in order to correctly compare "apples to apples." Referring not to FIGURE 11, Fig. 11A, a depiction is provided of a payment based outcome goal, while Fig.11B, shows how the method applied according to the present invention, namely, the scientific method, satisfies this objective; in Fig.11C, the mutual goal of achieving efficient, effective and optimal outcomes is achieved by balancing and integrating payor, provider, and patient needs and considerations in the reimbursement process. FIGURE 12, Fig. 12A considers adoption and potential impact of this invention; Fig. 12B. FIGURE 13A provides a representation of adoption rate estimates; Fig.13B, notes that insurance companies are early adopters of new tech. FIGURE 14 shows a sample treatment plan that can be produced according the CDSS of the present invention. Further definitions of filters utilized according to the Custom CDSS of the present invention include: ^ Page 14 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION Medical Necessity: In resolving this inquiry, the present invention utilizes the following at least three (3) filters: 1. Is the intervention tied to the Assessment and Symptoms? 2. Are the goals of the intervention provided with a baseline rather than “0 %” as a baseline? 3.Does at least one of the following apply to the intervention? It: i.Prevents further regression ii. Ensures Health, Safety, or Function iii. Allows for Further Integration Quality of Life (“QoL”) Quality of life defined by the World Health Organization as "an individual's perception of their position in life in the context of the culture and value systems in which they live and in relation to their goals, expectations, standards and concerns". Standard indicators of the quality of life include wealth, employment, the environment, physical and mental health, education, recreation and leisure time, social belonging, religious beliefs, safety, security and freedom. QoL has a wide range of contexts, including the fields of international development, healthcare, politics and employment. Health related QoL (HRQoL) is an evaluation of QoL and its relationship with health. An individual’s perception of their position in life” in the context of their own culture, values, goals and standards. As opposed to these difficult to quantify determinants of QoL, the Custom CDSS of the present invention utilizes the following filter: Maximum happiness and freedom at an individual level. If the therapeutic intervention is shown to be well suited to achieving this definition of QoL, per ^ Page 15 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION the present CDSS, the intervention is given significant weighting. The present invention recognizes that QoL and Risk are two sides of the same coin. To increase one is to mitigate or avoid the other. Socially Significant Outcome The present CDSS filters input to determine whether the therapeutic intervention results in a Socially Significant outcome, as measured by rating at least the following filters as to whether the intervention: i. Is in line with Standards of Practice ii. Is clinically “appropriate” iii. Is not selected primarily for Convenience to patient iv. Is not selected primarily for Economic benefit of plans or purchasers v. Is the most efficient & cost-effective intervention of those available. Intensity of Therapeutic Intervention This CDSS filter ensures that a “one size fits all” -approach is not adopted but is rather driven by data showing successful outcomes with levels of intensity adapted to the patient’s needs and to guard against clinical decision making being subverted by operational considerations. Adoption It is relevant to turn for a moment to the question of adoption of a novel technology such as the present CDSS. It has been stated that: “The future of clinical service delivery is integrated, customized, personalized, data-driven and technology enabled. It is person-centered, with care and services provided in the setting and manner most appropriate to the needs of the individual... ^ Page 16 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION Consequently, the future of clinical service delivery is not either / or, either virtual or in-person, residential or home, hospital or rehab – it is multiple choice. Each point of contact will serve a unique purpose in the care continuum to ensure healthcare can achieve the triple aim of improved client experience, better outcomes at lower costs and improving the health of the overall population.” (Netsmart and OPEN MINDS). In short, the future of clinical service delivery is not either / or. It is a much more nuanced, requires taking into account constantly evolving knowledge and information. The CDSS of the present invention provides such a solution. In short, the present system, method and device of the present invention inquires: who, i.e. what phenotype or profile of ASD does well, under what type of intervention, in what type of setting, with with what kind of provider, at what level of intensity. Having taught how to make and use this invention herein above, those skilled in the art will appreciate that this invention includes a system, a method and an apparatus to provide Clinical Decision Support to assist clinicians treating a wide spectrum of disorders. In one embodiment, the system includes a. an interface layer to (i) receive ASD therapeutic indicators included in information from as large a body of information as possible of ASD patient diagnoses, said ASD therapeutic indicators to include the diagnosis, the therapeutic intervention applied, and the therapeutic outcome, and (ii) for delivery of clinical decision support following processing by the CDSS; b. an engine for processing said information by applying a plurality of filters to said body of information to establish the presence, absence, and if present, magnitude of each indicator in select panel of ASD therapeutic indicators; and c. a treatment recommendation module for said delivery of said clinical decision support following processing by said engine. The CDSS filters and balances ASD therapeutic indicators including but not limited to: (1) a primary set of therapeutic indicators, comprising indicators of toileting, sleep, feeding, and communication; and optionally also comprising; (2) a secondary set of therapeutic indicators comprising indicators of caregiver guidance, access to care, and transition of care; (3) a third set ^ Page 17 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION of therapeutic indicators comprising indicators of medical necessity, goal selection, and data collection; and (d) a fourth set of therapeutic indicators comprising ops forecasts, client intake, and intensity of treatment. Preferably, a filter is applied defining appropriateness of treatment metric weighing of candidate therapeutic options with appropriateness of treatment by considering both the chronological age of the patient and relevant developmental milestones to arrive at an appropriate goal to be achieved were the therapeutic treatment intervention suggested by the CDSS to be implemented. In certain embodiments, the CDSS utilizes both (A) knowledge-based CDSS, by consulting with a library of predefined if / then rules, to learn from information from therapeutic interventions, finds patterns in historical data, using either or both (i) genetic algorithms (GA) reflecting the mechanics of heredity and natural selection, such that, just as species change from generation to generation to better fit their environment, GAs adapt to a new task, producing a number of random solutions and then iteratively evaluating and improving them until the most fitting option is found, and (ii) Artificial Neural Networks (ANN) that mimic human thinking using a set of "neurons" called “neurods" linked to each other with weighted connections that act as nerve synapses transmitting signals across the neural network; and (B) non-knowledge-based systems requiring compute-intensive training processes and large datasets needed to improve accuracy of models. A further filter included in select embodiments of the CDSS of the present invention applies an “Ethical Efficacy Model of Selection” filter, whereby the interactions between the following six considerations are balanced: .A. Client treatment preferences, which is balanced agains both (i) potential harm at which this patient is at risk of due to the diagnosed condition, and the (ii) low generality, i.e. high specificity of the condition; B. Clinician competence, which is balanced against both (ii) low generality, i.e. high specificity of the condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not; and C. Environmental supports, which is balanced against both (i) potential harm at which this patient is at risk of due ^ Page 18 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION to the diagnosed condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not. In yet additional embodiments according to this invention, the CDSS comprises a filter defined by payment based outcome goal, namely, achieving efficient, effective and optimal outcomes, said filter operating by balancing and integrating payor, provider, and patient needs and considerations in a reimbursement process integrated into or with said CDSS. A further filter defining Medical Necessity (“MN”) and Quality of Life (QoL) goals to arrive at an appropriate goal for a given patient, includes ensuring (i) treatment is tied to a relevant assessment, (ii) impact of the treatment on the symptom under consideration, (iii) impact of the treatment on QoL, (iv) baseline data for the given individual, (v) the social validity of the treatment, (vi) and DSM criteria. At least one, a combination of, or all of the following filters is further applied in certain embodiments of the invention: A. Medical necessity filters including at least: 1. Is the intervention tied to the Assessment and Symptoms? 2. Are the goals of the intervention provided with a baseline rather than “0 %” as a baseline? 3.Does at least one of the following apply to the intervention? It: i.Prevents further regression ii. Ensures Health, Safety, or Function iii. Allows for Further Integration B. Quality of life (QoL) filter to define maximum happiness and freedom at an individual level, such that, if a therapeutic intervention is shown to be well suited to achieving this definition of QoL, the intervention is given significant weighting; C. Socially Significant outcome filter, as measured by rating at least the following filters as to whether the intervention: ^ Page 19 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION i. Is in line with Standards of Practice; ii. Is clinically “appropriate”; iii. Is not selected primarily for Convenience to patient; iv. Is not selected primarily for Economic benefit of plans or purchasers; and v. Is the most efficient & cost-effective intervention of those available; and D. Level of Intensity filter adapted to the patient’s needs and to guard against clinical decision making being subverted by operational considerations. In certain embodiments, the user interface module is configured to display treatment recommendations to a healthcare professional, the data input module is configured to receive input from wearable devices, electronic health records, and caregiver reports the data analysis module utilizes natural language processing algorithms to extract relevant information from textual patient data, the data analysis module includes feature selection algorithms to identify the most significant variables contributing to the ASD treatment, the treatment recommendation module considers patient preferences, co-morbidities, and response to previous treatments in generating personalized treatment recommendations; and treatment recommendation module utilizes evidence-based guidelines, scientific literature, and expert knowledge in generating treatment recommendations. It is noted that, while this system is largely agnostic to a patient’s initial diagnosis, that information may nonetheless be included as data points in a given patient’s data provided to the system. In addition diagnoses and therapeutic outcomes are likewise included and fed back into the set of all data against which a given patient’s data is to be compared by the CDSS. Over time, therefore, the system’s filters and therapeutic suggestions are increasingly guided by the actual therapeutic outcomes for patients, which are constantly fed back into the system. Thus, the more information the system is provided about a given patient and the more it is fed back the therapeutic modes of treatment and therapeutic outcomes for other patients, the more accurate the predictive power of the system becomes in providing predictive clinical decision support. In this way, any single factor, such as diagnosis, does not play a greater role than it should in the CDSS’s therapeutic suggestions. ^ Page 20 of 32 ^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION Those skilled in the art will appreciate, based own the present disclosure, the teaching in the appended drawings and the attached claims that in certain embodiments of this invention, a CDSS, CDSM, or apparatus is implicated which includes some, a combination, or all of the filters defined herein. Any reasonable and workable combination of filters as defined herein, and in particular with reference to specific embodiments shown, for example, in figure 6, permutations, combinations, variations, and equivalents to the therapeutic indicators, and the filters based on such therapeutic indicators, is encompassed by the present disclosure and claims. In certain embodiments, machine learning (ML), artificial intelligence (AI), and the like may be implemented to maximize the efficiency of various embodiments of the present invention. ^ Page 21 of 32

Claims

^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION WHAT IS CLAIMED IS:

1. A Clinical Decision Support System (CDSS) comprising: a. an interface layer to (i) receive neurodiversity therapeutic indicators included in information from as large a body of information as possible of neurodiverse patients, said neurodiversity therapeutic indicators to include the diagnosis, the therapeutic intervention applied, and the therapeutic outcome, and (ii) for delivery of clinical decision support following processing by the CDSS; b. an engine for processing said information by applying a plurality of filters to said body of information to establish the presence, absence, and if present, magnitude of each indicator in select panel of neurodiversity therapeutic indicators; and c. a treatment recommendation module for said delivery of said clinical decision support following processing by said engine.

2. The CDSS according to claim 1 when applied to patients diagnosed with a neurodiverse condition selected from the group consisting of ASD, ADHD, BPD, and OCD.

3. The CDSS according to claim 2, which filters and balances therapeutic indicators comprising at least one, a combination, or all of the following filters: a. a primary set of therapeutic indicators, comprising indicators of toileting, sleep, feeding, and communication; b. a secondary set of therapeutic indicators comprising indicators of caregiver guidance, access to care, and transition of care; c. a third set of therapeutic indicators comprising indicators of medical necessity, goal selection, and data collection; d. a fourth set of therapeutic indicators comprising ops forecasts, client intake, and intensity of treatment. ^ Page 22 of 32^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION 4. The system according to claim 1 wherein a filter is applied defining appropriateness of a treatment metric which balances candidate therapeutic options with appropriateness of treatment by considering both the chronological age of the patient and relevant developmental milestones to arrive at an appropriate goal to be achieved were the therapeutic treatment intervention suggested by the CDSS to be implemented.

5. The CDSS according to claim 1 which utilizes both (A) knowledge-based CDSS, by consulting with a library of predefined if / then rules, to learn from information from therapeutic interventions, finds patterns in historical data, using either or both (i) genetic algorithms (GA) reflecting the mechanics of heredity and natural selection, such that, just as species change from generation to generation to better fit their environment, GAs adapt to a new task, producing a number of random solutions and then iteratively evaluating and improving them until the most fitting option is found, and (ii) Artificial Neural Networks (ANN) that mimic human thinking using a set of "neurons" called “neurods" linked to each other with weighted connections that act as nerve synapses transmitting signals across the neural network; and (B) non-knowledge-based systems requiring compute-intensive training processes and large datasets needed to improve accuracy of models.

6. The CDSS according to claim 1 which applies filters of Medical Necessity (“MN”) and Quality of Life (QoL) goals to arrive at an appropriate goal for a given patient, which includes (i) treatment tied to a relevant assessment, (ii) impact of the treatment on the symptom under consideration, (iii) impact of the treatment on QoL, (iv) baseline data for the given individual, (v) the social validity of the treatment, (vi) and DSM criteria.

7. The CDSS according to claim 1 which applies an “Ethical Efficacy Model of Selection” filter, whereby the interactions between the following six considerations are balanced: .A. Client treatment preferences, which is balanced agains both (i) potential harm at which this patient is at risk of due to the diagnosed condition, and the (ii) low generality, i.e. high specificity of the condition; B. Clinician competence, which is balanced against both (ii) low generality, i.e. high ^ Page 23 of 32^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION specificity of the condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not; and C. Environmental supports, which is balanced against both (i) potential harm at which this patient is at risk of due to the diagnosed condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not.

8. The CDSS according to claim 1 further comprising a filter defined by payment based outcome goal, namely, achieving efficient, effective and optimal outcomes, said filter operating by balancing and integrating payor, provider, and patient needs and considerations in a reimbursement process integrated into or with said CDSS.

9. The CDSS according to claim 1 wherein at least one, a combination of, or all of the following filters are utilized: A. Medical necessity filters including at least:

1. Is the intervention tied to the Assessment and Symptoms? 2. Are the goals of the intervention provided with a baseline rather than “0 %” as a baseline? 3.Does at least one of the following apply to the intervention? It: i.Prevents further regression ii. Ensures Health, Safety, or Function iii. Allows for Further Integration B. Quality of life (QoL) filter to define maximum happiness and freedom at an individual level, such that, if a therapeutic intervention is shown to be well suited to achieving this definition of QoL, the intervention is given significant weighting; C. Socially Significant outcome filter, as measured by rating at least the following filters as to whether the intervention: i. Is in line with Standards of Practice; ii. Is clinically “appropriate”; iii. Is not selected primarily for Convenience to patient; iv. Is not selected primarily for Economic benefit of plans or purchasers; and ^ Page 24 of 32^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION v. Is the most efficient & cost-effective intervention of those available; and D. Level of Intensity filter adapted to the patient’s needs and to guard against clinical decision making being subverted by operational considerations.

10. A Clinical Decision Support Method (CDSM) to assist clinicians treating a patient presenting with a diagnosis of neurodiversity, comprising: a. providing an interface layer to (i) receive neurodiversity therapeutic indicators included in information from as large a body of information as possible of neurodiverse patient diagnoses, said neurodiversity therapeutic indicators to include the diagnosis, the therapeutic intervention applied, and the therapeutic outcome, and (ii) for delivery of clinical decision support following processing by the CDSS; b. providing an engine for processing said information by applying a plurality of filters to said body of information to establish the presence, absence, and if present, magnitude of each indicator in select panel of neurodiversity therapeutic indicators; and c. delivering, via said interface layer, a treatment recommendation module for said delivery of said clinical decision support following processing by said engine.

11. The CDSM according to claim 10, when applied to patients diagnosed with a neurodiverse condition selected from the group consisting of ASD, ADHD, BPD, and OCD, and wherein said therapeutic indicators comprise at least one, a combination, or all of the following therapeutic indicators: a. primary set of therapeutic indicators, comprising indicators of toileting, sleep, feeding, and communication; and optionally also comprising: b. a secondary set of therapeutic indicators comprising indicators of caregiver guidance, access to care, and transition of care; c. a third set of therapeutic indicators comprising indicators of medical necessity, goal selection, and data collection; and d. a fourth set of therapeutic indicators comprising ops forecasts, client intake, and intensity of treatment. ^ Page 25 of 32^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION 12. The CDSM according to claim 10 wherein a filter is applied defining appropriateness of treatment metric weighing of candidate therapeutic options with appropriateness of treatment by considering both the chronological age of the patient and relevant developmental milestones to arrive at an appropriate goal to be achieved were the therapeutic treatment intervention suggested by the CDSS to be implemented.

13. The CDSM according to claim 10 which utilizes both (A) knowledge-based CDSS, by consulting with a library of predefined if / then rules, to learn from information from therapeutic interventions, finds patterns in historical data, using either or both (i) genetic algorithms (GA) reflecting the mechanics of heredity and natural selection, such that, just as species change from generation to generation to better fit their environment, GAs adapt to a new task, producing a number of random solutions and then iteratively evaluating and improving them until the most fitting option is found, and (ii) Artificial Neural Networks (ANN) that mimic human thinking using a set of "neurons" called “neurods" linked to each other with weighted connections that act as nerve synapses transmitting signals across the neural network; and (B) non-knowledge-based systems requiring compute-intensive training processes and large datasets needed to improve accuracy of models.

14. The CDSM according to claim 10, which applies an “Ethical Efficacy Model of Selection” filter, whereby the interactions between the following six considerations are balanced: .A. Client treatment preferences, which is balanced agains both (i) potential harm at which this patient is at risk of due to the diagnosed condition, and the (ii) low generality, i.e. high specificity of the condition; B. Clinician competence, which is balanced against both (ii) low generality, i.e. high specificity of the condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not; and C. Environmental supports, which is balanced against both (i) potential harm at which this patient is at risk of due to the diagnosed condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not. ^ Page 26 of 32^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION 15. The CDSM according to claim 10 further comprising applying a filter defined by payment based outcome goal, namely, achieving efficient, effective and optimal outcomes, said filter operating by balancing and integrating payor, provider, and patient needs and considerations in a reimbursement process integrated into or with said CDSS.

16. The CDSM according to claim 10 which applies filters of Medical Necessity (“MN”) and Quality of Life (QoL) goals to arrive at an appropriate goal for a given patient, which includes (i) treatment tied to a relevant assessment, (ii) impact of the treatment on the symptom under consideration, (iii) impact of the treatment on QoL, (iv) baseline data for the given individual, (v) the social validity of the treatment, (vi) and DSM criteria.

17. The CDSM according to claim 10 wherein at least one, a combination of, or all of the following filters are utilized: A. Medical necessity filters including at least:

1. Is the intervention tied to the Assessment and Symptoms? 2. Are the goals of the intervention provided with a baseline rather than “0 %” as a baseline? 3.Does at least one of the following apply to the intervention? It: i.Prevents further regression ii. Ensures Health, Safety, or Function iii. Allows for Further Integration B. Quality of life (QoL) filter to define maximum happiness and freedom at an individual level, such that, if a therapeutic intervention is shown to be well suited to achieving this definition of QoL, the intervention is given significant weighting; C. Socially Significant outcome filter, as measured by rating at least the following filters as to whether the intervention: i. Is in line with Standards of Practice; ii. Is clinically “appropriate”; iii. Is not selected primarily for Convenience to patient; ^ Page 27 of 32^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION iv. Is not selected primarily for Economic benefit of plans or purchasers; and v. Is the most efficient & cost-effective intervention of those available; and D. Level of Intensity filter adapted to the patient’s needs and to guard against clinical decision making being subverted by operational considerations.

18. An apparatus for providing Clinical Decision Support comprising: a. a user interface to (i) receive ASD therapeutic indicators included in information from as large a body of information as possible of ASD patient diagnoses, said ASD therapeutic indicators to include the diagnosis, the therapeutic intervention applied, and the therapeutic outcome, and (ii) for delivery of clinical decision support following processing by the CDSS; b. an engine for processing said information by applying a plurality of filters to said body of information to establish the presence, absence, and if present, magnitude of each indicator in select panel of ASD therapeutic indicators; and c. a treatment recommendation module for said delivery of said clinical decision support following processing by said engine.

19. The apparatus according to claim 19, which filters and balances ASD therapeutic indicators comprising at least one, a combination or all of the filters: a. primary set of therapeutic indicators, comprising indicators of toileting, sleep, feeding, and communication; and optionally also comprising: b. a secondary set of therapeutic indicators comprising indicators of caregiver guidance, access to care, and transition of care; c. a third set of therapeutic indicators comprising indicators of medical necessity, goal selection, and data collection; d. a fourth set of therapeutic indicators comprising ops forecasts, client intake, and intensity of treatment; and wherein a filter is applied defining appropriateness of treatment metric weighing of candidate therapeutic options with appropriateness of treatment by considering both the chronological age of the patient and relevant developmental milestones to arrive at an appropriate goal to be achieved were the therapeutic treatment intervention suggested by the ^ Page 28 of 32^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION CDSS to be implemented; and which utilizes both (A) knowledge-based CDSS, by consulting with a library of predefined if / then rules, to learn from information from therapeutic interventions, finds patterns in historical data, using either or both (i) genetic algorithms (GA) reflecting the mechanics of heredity and natural selection, such that, just as species change from generation to generation to better fit their environment, GAs adapt to a new task, producing a number of random solutions and then iteratively evaluating and improving them until the most fitting option is found, and (ii) Artificial Neural Networks (ANN) that mimic human thinking using a set of "neurons" called “neurods" linked to each other with weighted connections that act as nerve synapses transmitting signals across the neural network; and (B) non-knowledge-based systems requiring compute-intensive training processes and large datasets needed to improve accuracy of models; and which applies an “Ethical Efficacy Model of Selection” filter, whereby the interactions between the following six considerations are balanced: .A. Client treatment preferences, which is balanced agains both (i) potential harm at which this patient is at risk of due to the diagnosed condition, and the (ii) low generality, i.e. high specificity of the condition; B. Clinician competence, which is balanced against both (ii) low generality, i.e. high specificity of the condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not; and C. Environmental supports, which is balanced against both (i) potential harm at which this patient is at risk of due to the diagnosed condition, and (iii) whether a potential therapeutic regimen has been generally adopted in the field or not.

20. The apparatus according to claim 19 further comprising applying a filter defined by payment based outcome goal, namely, achieving efficient, effective and optimal outcomes, said filter operating by balancing and integrating payor, provider, and patient needs and considerations in a reimbursement process integrated into or with said CDSS; and which applies filters of Medical Necessity (“MN”) and Quality of Life (QoL) goals to arrive at an appropriate goal for a given patient, which includes (i) treatment tied to a relevant assessment, (ii) impact of the treatment on the symptom under consideration, (iii) impact of the treatment on QoL, (iv) baseline data for the given individual, (v) the social validity of the treatment, (vi) and DSM criteria; and wherein at least one, a combination of, or all of the following filters are utilized: ^ Page 29 of 32^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION A. Medical necessity filters including at least:

1. Is the intervention tied to the Assessment and Symptoms? 2. Are the goals of the intervention provided with a baseline rather than “0 %” as a baseline? 3.Does at least one of the following apply to the intervention? It: i.Prevents further regression ii. Ensures Health, Safety, or Function iii. Allows for Further Integration B. Quality of life (QoL) filter to define maximum happiness and freedom at an individual level, such that, if a therapeutic intervention is shown to be well suited to achieving this definition of QoL, the intervention is given significant weighting; C. Socially Significant outcome filter, as measured by rating at least the following filters as to whether the intervention: i. Is in line with Standards of Practice; ii. Is clinically “appropriate”; iii. Is not selected primarily for Convenience to patient; iv. Is not selected primarily for Economic benefit of plans or purchasers; and v. Is the most efficient & cost-effective intervention of those available; and D. Level of Intensity filter adapted to the patient’s needs and to guard against clinical decision making being subverted by operational considerations; said apparatus further comprising at least one, a combination or all of the following features: a. said user interface module configured to display treatment recommendations to a healthcare professional; b. said data input module is configured to receive input from wearable devices, electronic health records, and caregiver reports; c. said data analysis module utilizes natural language processing algorithms to extract relevant information from textual patient data; d. said data analysis module includes feature selection algorithms to identify the most significant variables contributing to the ASD treatment; ^ Page 30 of 32^ ^ATTORNEY DOCKET NUMBER NBS-1PCT^ ^ ^ PATENT APPLICATION e. said treatment recommendation module considers patient preferences, comorbidities, and response to previous treatments in generating personalized treatment recommendations; and f. said treatment recommendation module utilizes evidence-based guidelines, scientific literature, and expert knowledge in generating treatment recommendations. ^ Page 31 of 32

Images