Detection of longitudinal progression of alzhemer

Abstract

The present disclosure relates to a method implemented by one or more computer devices, the method comprising detecting longitudinal progression of Alzheimer's disease (AD) in a patient. The method includes receiving verbal data including a description of a patient's one or more previous or current experiences of the patient, wherein the verbal data is captured at a plurality of times during a period of time. The method further includes analyzing the speech data to quantify a plurality of speech variables, wherein the plurality of speech variables includes a word length variable and a minor word usage variable. The method includes determining a comprehensive score based on a standardization of the quantized plurality of speech variables and a substantial weighting assigned to each of the quantized plurality of speech variables. Accordingly, the method includes detecting a predicted longitudinal change in the quantified speech variable based on the comprehensive score, and further estimating AD progress of the patient based on the predicted longitudinal change.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 354,165, filed on June 21, 2022, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present application relates generally to speech analysis, and more particularly to techniques for detecting longitudinal progression of Alzheimer's disease (AD) based on speech analysis. Background Art

[0004] Alzheimer's disease (AD) is a progressive neurodegenerative disease that may be characterized by a decline in a patient's memory, speech, and cognitive abilities, as well as adverse changes in a patient's mood and behavior. AD may generally be caused by one or more identified biological changes that may occur in a patient's brain over many years, such as excessive accumulation of amyloid beta (Aβ) plaques and tau tangles in the patient's brain. Specifically, while Aβ and tau proteins may generally be produced as part of the normal function of the brain, in patients diagnosed with AD, an overproduction of Aβ proteins, which may accumulate into plaques around brain cells, or an overproduction of tau proteins, which may misfold and accumulate into tangles within brain cells, may be observed.

[0005] Utilizing less invasive and less clinically intensive techniques to identify and detect early indications of cognitive decline in patients can help treat AD more effectively or prevent AD progression. For example, in many cases, a patient's speech may include at least some indication of a decline in the patient's cognitive abilities or adverse changes in cognitive abilities over time. In addition, because patients generally have access to personal electronic devices that may be suitable for capturing the patient's speech, speech samples can be readily analyzed for acoustic and linguistic properties and / or content. Summary of the invention

[0006] Embodiments of the present disclosure relate to one or more computing devices, methods, and non-transitory computer-readable media that can be used to detect predicted longitudinal changes in quantified speech variables associated with a patient as an estimate of the patient's Alzheimer's disease (AD) progression or the patient's AD treatment response. Specifically, according to embodiments of the present disclosure, one or more computing devices can utilize a machine learning model (e.g., a natural language processing (NLP) model, a transformer-based language model, an automatic speech recognition (ASR) model) to convert an original audio file of a patient's speech data captured at multiple moments during a period of time into a text transcript, and analyze linguistic speech variables (including word length variables and particle usage variables) and one or more acoustic speech variables to determine an estimate of the patient's AD progression or the patient's treatment response corresponding to the patient's speech data.

[0007] The patient speech data includes a record of the patient's description of one or more previous or current experiences of the patient. In certain embodiments, one or more computing devices may analyze the text transcript to quantify at least two speech variables extracted from either or both of one or more linguistic speech variables (e.g., a word length variable and a particle usage variable, and optionally a word frequency variable, a syntactic depth variable, a noun usage variable, or a pronoun usage variable) and one or more acoustic speech variables (e.g., one or more Mel-Frequency Cepstral Coefficient (MFCC) features). In one embodiment, the at least two speech variables quantified include a word length variable and a particle usage variable. In another embodiment, the at least two speech variables quantified include a word length variable and at least one MFCC feature, the at least one MFCC feature including a mean of the 11th MFCC coefficient (MFCC mean 11) variable, a variance of the first derivative of the 11th MFCC coefficient (MFCC variance 25) variable, or a variance of the first derivative of the 12th MFCC coefficient (MFCC variance 26) variable.

[0008] In some embodiments, one or more computing devices may then generate a composite score based on normalization of the quantified at least two speech variables extracted from either or both of the one or more linguistic speech variables and the one or more acoustic speech variables and substantial weighting of the quantified at least two speech variables extracted from either or both of the one or more linguistic speech variables and the one or more acoustic speech variables. For example, in some embodiments, the quantified at least two speech variables extracted from either or both of the one or more linguistic speech variables (e.g., word length variables and particle usage variables, and optionally word frequency variables, syntactic depth variables, noun usage variables, or pronoun usage variables) and the one or more acoustic speech variables (e.g., one or more Mel-Frequency Cepstral Coefficient (MFCC) features) may be normalized and combined into a composite score (e.g., an equally weighted composite score, a weighted composite score). In one embodiment, the quantified at least two speech variables used to generate the composite score may include a word length variable and a particle usage variable. In another embodiment, the quantified at least two speech variables used to generate the composite score may include a word length variable and at least one of an MFCC mean 11 variable, an MFCC variance 25 variable, or an MFCC variance 26 variable.

[0009] In certain embodiments, one or more computing devices may then determine a predicted longitudinal change in the quantified speech variable as an estimate of the patient's AD progression or the patient's AD treatment response based on the composite score. In this way, the present technology may provide an alternative to more invasive and clinically intensive tests for screening AD patients over time. In fact, by generating a composite score based on quantified at least two speech variables extracted from either or both of one or more linguistic speech variables and one or more acoustic speech variables identified as indicative of progressive longitudinal change, the present technology may provide a quantified estimate of the patient's AD progression or the patient's AD treatment response using only the patient's speech.

[0010] In certain embodiments, one or more computing devices may receive speech data comprising a record of a patient's description of one or more previous or current experiences of the patient, wherein the speech data is captured at multiple moments during a period of time. For example, in some embodiments, one or more computing devices may receive speech data by receiving an audio file comprising an electronic record of the patient's speech. In one embodiment, the electronic record of the patient's speech may include an electronic record of one or more verbal responses of the patient to a Clinical Dementia Rating (CDR) interview. In certain embodiments, the speech data is captured on an initial date and one or more dates selected from the group consisting of: approximately 0.25, 0.5, 0.75, 1, 3, 6, 9, 12, 15, 18, 21, 24, 27, 30, 33, and 36 months from the initial date.

[0011] In some embodiments, one or more computing devices may then analyze the speech data to quantify multiple speech variables. In some embodiments, one or more computing devices may analyze the speech data to determine the quantified multiple speech variables by: analyzing the speech data using one or more natural language processing (NLP) machine learning models. Multiple speech variables include word length variables and particle usage variables. In some embodiments, multiple speech variables may further include word frequency variables, syntactic depth variables, noun usage variables, or pronoun usage variables. In some embodiments, multiple speech variables may further include one or more Mel frequency cepstral coefficients (MFCC) features. For example, in some embodiments, one or more MFCC features may include the mean of the 11th MFCC coefficient (MFCC mean 11), the variance of the first-order derivative of the 11th MFCC coefficient (MFCC variance 25), or the variance of the first-order derivative of the 12th MFCC coefficient (MFCC variance 26).

[0012] In some embodiments, one or more computing devices may then determine a composite score based at least in part on the normalization or weighting of the quantified multiple speech variables. For example, in some embodiments, determining the composite score may include normalizing the quantified multiple speech variables, applying equal weighting to each of the quantified multiple speech variables, and combining the standardized and equally weighted quantified multiple speech variables to generate the composite score. In some embodiments, one or more computing devices may then detect predicted longitudinal changes in the quantified speech variables based on the composite score. In some embodiments, one or more computing devices may then estimate the patient's AD progression based on the predicted longitudinal changes. For example, in some embodiments, estimating AD progression based on predicted longitudinal changes may include correlating the composite score with one or more clinical assessment metrics.

[0013] In some embodiments, one or more clinical assessment metrics can be selected from the group consisting of: Mini-Mental State Examination (MMSE) score, Clinical Dementia Rating (CDR) interview, Clinical Dementia Rating-Sum of Boxes (CDR-SB) scale, Alzheimer's Disease Assessment Scale-Cognitive (ADAS-Cog) subscale battery, Alzheimer's Disease Cooperative Research Group-Activities of Daily Living Checklist (ADCS-ADL) scale, Neuropsychiatric Inventory (NPI) scale, Neuropsychiatric Inventory-Questionnaire (NPI-Q), Alzheimer's Caregiver Global Impression (CaGI) scale, Instrumental Activities of Daily Living (IADL) scale, Amsterdam Activities of Daily Living Questionnaire (A-IADL-Q), and Repeatable Battery of Neuropsychological Status (RBANS) scale.

[0014] In some embodiments, one or more computing devices may determine whether a patient is responsive to treatment based on the estimated AD progression. In some embodiments, one or more computing devices may transmit a notification of the estimated AD progression to a computing device associated with a clinician. In some embodiments, in response to estimating AD, one or more computing devices may generate a recommendation for adjusting a treatment regimen for the patient. For example, in some embodiments, the treatment regimen may include: a therapeutic agent consisting of at least one compound selected from the group consisting of: compounds for oxidative stress, anti-apoptotic compounds, metal chelators, inhibitors of DNA repair, 3-amino-1-propanesulfonic acid (3APS), 1,3-propane disulfonate (1,3PDS), secretase activators, β- and γ-secretase inhibitors, tau proteins, anti-tau antibodies, anti-tau agents, gene therapy, neurotransmitters, β-sheet disruptors, anti-inflammatory molecules, atypical antipsychotics, cholinesterase inhibitors, other drugs and nutritional supplements; selected from the group consisting of Therapeutic agents: symptomatic drugs, neurological drugs, corticosteroids, antibiotics, antiviral agents, anti-tau antibodies, tau inhibitors, anti-β-amyloid (anti-Aβ) antibodies, β-amyloid aggregation inhibitors, target-binding therapeutics, anti-BACE1 antibodies, BACE1 inhibitors, cholinesterase inhibitors, NMDA receptor antagonists, monoamine depleting agents, dihydroergotamine mesylate, anticholinergic antiparkinsonian agents, dopaminergic antiparkinsonian agents, tetrabenazine, anti-inflammatory agents, hormones, vitamins, dimebolin, homotaurine, serotonin receptor activity modulators, interferons and glucocorticoids.

[0015] In certain embodiments, the symptomatic drug may be selected from the group consisting of: cholinesterase inhibitors, galantamine, rivastigmine, donepezil, N-methyl-D-aspartate receptor antagonists, memantine, and food supplements (optionally wherein the food supplement is ). In some embodiments, the anti-tau antibody can be selected from the group consisting of an N-terminal binder, an intermediate domain binder, and a fibrillar tau binder. In certain embodiments, the anti-tau antibody is selected from the group consisting of semorinemab, BMS-986168, C2N-8E12, gosuranemab, tilavonemab, and zagotenemab. In some embodiments, the therapeutic agent can be a therapeutic agent that specifically binds to a target, and the target is selected from the group consisting of β-secretase, tau, presenilin, amyloid precursor protein or a portion thereof, β-amyloid peptide or an oligomer or fibril thereof, death receptor 6 (DR6), receptor for advanced glycation end products (RAGE), parkin, and huntingtin.

[0016] In certain embodiments, the therapeutic agent may be a monoamine depleting agent, optionally tetrabenazine. In some embodiments, the therapeutic agent may be an anticholinergic anti-Parkinson's disease agent selected from the group consisting of procyclidine, diphenhydramine, trihexylphenidyl, benztropine, biperiden, and trihexyphenidyl. In some embodiments, the therapeutic agent can be a dopaminergic anti-Parkinson's disease agent selected from the group consisting of entacapone, selegiline, pramipexole, bromocriptine, rotigotine, selegiline, ropinirole, rasagiline, apomorphine, carbidopa, levodopa, pergolide, tolcapone and amantadine. In some embodiments, the therapeutic agent can be an anti-inflammatory agent selected from the group consisting of non-steroidal anti-inflammatory drugs and indomethacin. In some embodiments, the therapeutic agent can be a hormone selected from the group consisting of estrogen, progesterone and leuprolide. In some embodiments, the therapeutic agent can be a vitamin selected from the group consisting of folic acid and nicotinamide. In some embodiments, the therapeutic agent can be xaliproden or homotaurine, which is 3-aminopropanesulfonic acid or 3APS. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 An example embodiment of a telehealth services environment is presented that can be used to detect predicted longitudinal changes in a quantified speech variable associated with a patient as an estimate of the patient's Alzheimer's disease (AD) progression or the patient's treatment response.

[0018] Figure 2 A flow chart of a method for detecting predicted longitudinal changes in quantified speech variables, including word length variables and particle usage variables associated with a patient, as an estimate of the patient's AD progression or the patient's AD treatment response is presented.

[0019] Figure 3AA flow chart of a method for detecting predicted longitudinal changes in quantified speech variables, including word length variables and Mel-Frequency Cepstral Coefficient (MFCC) variables associated with a patient, as an estimate of the patient's AD progression or the patient's AD treatment response is presented.

[0020] Figure 3B A flow chart of a method for detecting predicted longitudinal changes in quantified speech variables, including particle usage variables and Mel-Frequency Cepstral Coefficient (MFCC) variables associated with a patient, as an estimate of the patient's AD progression or treatment response in the AD patient is presented.

[0021] Figure 4 Graphs depicting the longitudinal trajectories of the patient's linguistic and acoustic-speech variables as they change linearly over time are presented.

[0022] Figure 5 Tabular graphs showing standardized effect sizes for changes from baseline to endpoint in clinical rating scores as related to the composite score.

[0023] Figure 6 An exemplary computing system is shown.

[0024] Figure 7 Shown is included as Figure 6 Diagram of an exemplary artificial intelligence (AI) architecture that is a portion of an exemplary computing system. DETAILED DESCRIPTION

[0025] The present disclosure relates to one or more computing devices, methods, and non-transitory computer-readable media that can be used to detect predicted longitudinal changes in quantified speech variables associated with a patient as an estimate of the patient's Alzheimer's disease (AD) progression or the patient's AD treatment response. Specifically, according to an embodiment of the present disclosure, one or more computing devices can utilize a machine learning model (e.g., a natural language processing (NLP) model, a transformer-based language model, an automatic speech recognition (ASR) model) to convert an original audio file of the patient's speech data captured at multiple moments during a period of time into a text transcript, and analyze linguistic speech variables (including word length variables and particle usage variables) and one or more acoustic speech variables to determine an estimate of the patient's AD progression or the patient's treatment response corresponding to the patient's speech data.

[0026] The patient speech data includes a recording of the patient's description of one or more previous or current experiences of the patient. In certain embodiments, one or more computing devices may analyze the text transcript to quantify at least two speech variables extracted from either or both of one or more linguistic speech variables (e.g., word length variables and particle usage variables, and optionally word frequency variables, syntactic depth variables, noun usage variables, or pronoun usage variables) and one or more acoustic speech variables (e.g., one or more Mel-Frequency Cepstral Coefficient (MFCC) features).

[0027] In some embodiments, one or more computing devices may then generate a composite score based on normalization of the quantified at least two speech variables extracted from either or both of the one or more linguistic speech variables and the one or more acoustic speech variables and substantial weighting of the quantified at least two speech variables extracted from either or both of the one or more linguistic speech variables and the one or more acoustic speech variables. For example, in some embodiments, the quantified at least two speech variables extracted from either or both of the one or more linguistic speech variables (e.g., word length variables and particle usage variables, and optionally word frequency variables, syntactic depth variables, noun usage variables, or pronoun usage variables) and the one or more acoustic speech variables (e.g., one or more Mel-Frequency Cepstral Coefficient (MFCC) features) may be normalized and combined into a composite score (e.g., an equally weighted composite score, a weighted composite score). In one embodiment, the quantified at least two speech variables used to generate the composite score may include a word length variable and a particle usage variable. In another embodiment, the quantified at least two speech variables used to generate the composite score may include a word length variable and at least one of an MFCC mean 11 variable, an MFCC variance 25 variable, or an MFCC variance 26 variable.

[0028] In certain embodiments, one or more computing devices may then determine a predicted longitudinal change in the quantified speech variable as an estimate of the patient's AD progression or the patient's AD treatment response based on the composite score. In this way, the present technology may provide an alternative to more invasive and clinically intensive tests for screening AD patients over time. In fact, by generating a composite score based on quantified at least two speech variables extracted from either or both of one or more linguistic speech variables and one or more acoustic speech variables identified as indicative of progressive longitudinal change, the present technology may provide a quantified estimate of the patient's AD progression or the patient's AD treatment response using only the patient's speech.

[0029] As will be further described herein with respect to therapy or treatment:

[0030] Therapeutic agents may include neuronal transmission enhancers, psychotropic drugs, acetylcholinesterase inhibitors, calcium channel blockers, biogenic amines, benzazepines Sedatives; enhancers of acetylcholine synthesis, storage, or release; acetylcholine postsynaptic receptor agonists; monoamine oxidase A or B inhibitors; N-methyl-D-aspartate glutamate receptor antagonists; nonsteroidal anti-inflammatory drugs; antioxidants; or serotonin receptor antagonists. In particular, the therapeutic agent may comprise at least one compound selected from the following: compounds against oxidative stress, anti-apoptotic compounds, metal chelators, inhibitors of DNA repair (such as pirenzepine and metabolites), 3-amino-1-propanesulfonic acid (3APS), 1,3-propane disulfonate (1,3PDS), secretase activators, β- and γ-secretase inhibitors, tau proteins, anti-tau antibodies or anti-tau agents, neurotransmitters, β-sheet disruptors, anti-inflammatory molecules, "atypical antipsychotics" (such as, for example, clozapine, ziprasidone, risperidone, aripiprazole or olanzapine) or cholinesterase inhibitors (ChEI) (such as tacrine, rivastigmine, donepezil and / or galantamine) and other drugs or nutritional supplements (such as, for example, vitamin B12, cysteine, acetylcholine precursors, lecithin, choline, ginkgo biloba extract, acetyl-L-carnitine, idebenone, propentofylline and / or xanthine derivatives).

[0031] In some embodiments, the therapeutic agent is a tau inhibitor. Non-limiting examples of tau inhibitors include methyl thiocyanate, LMTX (also known as methylthionine hydrogen mesylate or Trx-0237; TauRx Therapeutics Ltd.), Rember TM (methylene blue or methylene blue [MTC]; Trx-0014; TauRx Therapeutics Ltd), PBT2 (Prana Biotechnology), and PTI-51-CH3 (TauPro TM ; ProteoTech).

[0032] In some embodiments, the therapeutic agent is an anti-tau antibody. "Anti-tau immunoglobulin," "anti-tau antibody," and "antibody that binds to tau" are used interchangeably herein and refer to an antibody that is capable of binding to tau (e.g., human tau) with sufficient affinity such that the antibody can be used as a diagnostic and / or therapeutic agent targeting tau. In some embodiments, the extent of binding of the anti-tau antibody to unrelated, non-tau proteins is less than about 10% of the binding of the antibody to tau, as measured, for example, by radioimmunoassay (RIA). In certain embodiments, the dissociation constant (K) of the antibody that binds to tau is less than about 10% of the binding of the antibody to tau. D ) is ≤1 μM, ≤100 nM, ≤10 nM, ≤1 nM, ≤0.1 nM, ≤0.01 nM or ≤0.001 nM (e.g., 10 -8M or smaller, e.g. 10 -8 M to 10 -13 M, for example 10 -9 M to 10 -13 M). In certain embodiments, the anti-tau antibody binds to an epitope of tau that is conserved among tau from different species. In some cases, the antibody binds to monomeric tau, oligomeric tau, and / or phosphorylated tau. In some embodiments, the anti-tau antibody binds to monomeric tau, oligomeric tau, non-phosphorylated tau, and phosphorylated tau with comparable affinities, such as affinities that differ by no more than 50 times from one another. In some embodiments, antibodies that bind to monomeric tau, oligomeric tau, non-phosphorylated tau, and phosphorylated tau are referred to as "pan-tau antibodies." In some embodiments, the anti-tau antibody binds to an epitope within the N-terminal region of tau, such as within / spanning residues 6 to 23, such as within the N-terminal region of tau. In a specific embodiment, the anti-tau antibody is sirenazumab.

[0033] In some embodiments, the anti-tau antibody is one or more selected from the group consisting of different N-terminal binders, middle domain binders, and fibrillar tau binders. Non-limiting examples of other anti-tau antibodies include BIIB092 or BMS-986168 (Biogen, Bristol-Myers Squibb); APN-mAb005 (Aprinoia Therapeutics / Samsung Biologics), BIIB076 (Biogen / Eisai), ABBV-8E12 or C2N-8E12 (AbbVie, C2N Diagnostics, LLC); antibodies disclosed in WO2012049570, WO2014028777, WO2014165271, WO2014100600, WO2015200806, US8980270 or US8980271; E2814 (Eisai), gonelizumab (Biogen), tipranezumab (Abbvie) and zagteneizumab (Lilly).

[0034] In some embodiments, the therapeutic agent is an anti-tau agent. Non-limiting examples include BIIB080 (Biogen / Ionis), LY3372689 (Lilly), PNT001 (Pinteon Therapeutics), OLX-07010 (Oligomerix, Inc.), TRx-0237 / LMTX (TauRx), JNJ-63733657 (Janssen), tau siRNA (Lilly / Dicerna), and PSY-02 (Psy Therapeutics).

[0035] In some embodiments, the therapeutic agent is at least one compound for treating AD selected from the group consisting of GV-971 (Green Valley), CT1812 (Cognition Therapeutics), ATH-1017 (AthiraPharma), COR388 (Cortexyme), simufilam (Cassava), semaglutide (Novo Nordisk), Blarcamesine (Anavex Life Sciences), AR1001 (AriBio), nilotinib BE (KeifeRx / LifeMolecular Imaging / Sun Pharma), ALZ-801 (Alzheon), AL003 (Alector / AbbVie), Lomecel-B (Longeveron), UB-311 (Vaxxinity), XPro1595 / pegineamine (INmune Bio), NLY-01 (D&DBiotech), Varoglutamstat / PQ912 (Vivoryon / Nordic / Simcere), canakinumab (Novartis), Obicetrapib (New Amsterdam Pharma), AADvac1 (Axon Neuroscience), ANVS-401 / Posiphen (Annovis Bio), TB006 (TureBinding), BI 474121 (Boehringer Ingelheim), NuCerin (Shaperon / Kukjeon), (Alzinova) ALZ-101, NNI-362 (Neuronascent), MK-1942 (Merck), E2511 (Eisai), IGC-AD1 (India Globalization Capital), AL001 (AlzamendNeuro), AL002 (Alzamend Neuro), AL101 (Alector / GSK), MW-151 (ImmunoChemTherapeutics), DNL-788 / SAR443820 (Denali / Sanofi), ALN-APP (Alnylam / Regeneron), E2F4DN (Tetraneuron), EmtinB (NeuroScientific Biopharma), NIT-001 (Neurostech), ACD679 (AlzeCure Pharma), ACD680 (AlzeCurePharma), YDC-103 (YD Global LifeScience), BMD-001 (Biorchestra), STL-101 (Stellate Therapeutics), AV-1959R (Nuravax), AV1959D (Nuravax), AV1980R (Nuravax), Duvax (Nuravax), Dapansutrile (Olatec) Therapeutics), LX1001 (Cornell University), BDNF (UC San Diego), ST-501 (Biogen), AMT-240 (uniQure), SOL-410 (Sola), SOL-258 (Sola), AAVhmAb, SHP-231 (Shape), SHP-232 (Shape), TEL-01 (Telocyte), GT-0007X (Gene Therapy).

[0036] In some embodiments, the therapeutic agent is a general misfolding inhibitor, such as NPT088 (NeuroPhage Pharmaceuticals).

[0037] In some embodiments, the therapeutic agent is a neurological drug. Neurological drugs include, but are not limited to, antibodies or other binding molecules (including, but not limited to, small molecules, peptides, aptamers, or other protein binding agents) that specifically bind to a target selected from the group consisting of: beta secretase, presenilin, amyloid precursor protein or a portion thereof, beta amyloid peptide or an oligomer or fibril thereof, death receptor 6 (DR6), receptor for advanced glycation end products (RAGE), parkin, and huntingtin; NMDA receptor antagonists (i.e., memantine), monoamine depleting agents (i.e., tetrabenazine); dihydroergoline mesylate; anticholinergic anti-Parkinson's disease agents (i.e., procyclidine, diphenhydramine, trihexyphenidyl, benztropine, biperiden, and trihexyphenidyl); dopaminergic anti-Parkinson's disease agents (i.e., entacapone, selegiline, pramipexole, bromocriptine, rotigotine, selegiline, ropinirole, rasagiline, apomorphine, carbidopa, levodopa, pergolide, tadalafil ... tetrabenazine; anti-inflammatory drugs (including but not limited to nonsteroidal anti-inflammatory drugs (i.e., indomethacin and other compounds listed above); hormones (i.e., estrogens, progesterone, and leuprolide); vitamins (i.e., folic acid and niacinamide); tiropin; homotaurine (i.e., 3-aminopropanesulfonic acid; 3APS); serotonin receptor activity modulators (i.e., xaliproden); interferons and glucocorticoids or corticosteroids The term "corticosteroid" includes, but is not limited to, fluticasone (including fluticasone propionate (FP)), beclomethasone, budesonide, ciclesonide, mometasone, flunisolide, betamethasone, and triamcinolone. "Inhalable corticosteroid" means a corticosteroid suitable for delivery by inhalation. Exemplary inhalable corticosteroids are fluticasone, beclomethasone dipropionate, budesonide, mometasone furoate, ciclesonide, flunisolide, and triamcinolone acetonide.

[0038] In certain specific embodiments, the therapeutic agent is one or more selected from the following groups: corticosteroids, antibiotics, antiviral agents, anti-tau antibodies, tau inhibitors, anti-β-amyloid antibodies, β-amyloid aggregation inhibitors, anti-BACE1 antibodies, BACE1 inhibitors; therapeutic agents that specifically bind to targets: cholinesterase inhibitors; NMDA receptor antagonists; monoamine depleting agents; dihydroergotamine mesylate; anticholinergic anti-Parkinson's disease agents; dopamine anti-Parkinson's disease agents; tetrabenazine; anti-inflammatory agents; hormones; vitamins; Danpifen; homotaurine; serotonin receptor activity modulators; interferons and glucocorticoids.

[0039] Non-limiting examples of anti-Aβ antibodies include crenuzumab, sulanizumab (Lilly), bapinezumab, aducanumab, gantuzumab, donetumab (Lilly), LY3372993 (Lilly), ACU193 (Acumen Pharmaceuticals), SHR-1707 (Hengrui USA / Atridia), ALZ-201 (Alzinova), PMN-310 (ProMIS neurosciences), and lencanezumab (BAN-2401; Biogen, Eisai Co., Ltd.). Non-limiting exemplary β-amyloid aggregation inhibitors include ELND-005 (also known as AZD-103 or scyllo-inositol), homotaurine, and PTI-80 ( ProteoTech). Non-limiting examples of BACE inhibitors include E-2609 (Biogen, Eisai Co., Ltd.), AZD3293 (also known as LY3314814; AstraZeneca, Eli Lilly & Co), MK-8931 (verubecestat), and JNJ-54861911 (Janssen, Shionogi Pharma).

[0040] In some embodiments, the therapeutic agent is an "atypical antipsychotic" such as, for example, clozapine, ziprasidone, risperidone, aripiprazole, or olanzapine, used to treat positive and negative psychotic symptoms, including hallucinations, delusions, thought disorder (manifested by marked incoherent, derailed, digressive) and bizarre or disorganized behavior, as well as anhedonia, flat affect, apathy, and social withdrawal.

[0041] In some embodiments, the other therapeutic agents include, for example, those discussed in WO 2004 / 058258 (see particularly pages 16 and 17), including therapeutic drug targets (pages 36-39), alkanesulfonic acids and alkanol sulfates (pages 39-51), cholinesterase inhibitors (pages 51-56), NMDA receptor antagonists (pages 56-58), estrogens (pages 58-59), nonsteroidal anti-inflammatory drugs (pages 60-61), antioxidants (pages 61-62), peroxisome proliferator-activated receptor (PPAR) agonists (pages 63-67) , cholesterol-lowering agents (pp. 68-75); amyloid inhibitors (pp. 75-77), amyloid formation inhibitors (pp. 77-78), metal chelators (pp. 78-79), antipsychotics and antidepressants (pp. 80-82), nutritional supplements (pp. 83-89), and compounds that increase the availability of biologically active substances in the brain (see pp. 89-93) and prodrugs (pp. 93 and 94), which document is incorporated herein by reference, but in particular the compounds mentioned on the pages indicated above.

[0042] As further described herein, measures of Alzheimer's disease severity and progression include:

[0043] Mini-mental state examination ("MMSE") is a brief clinical cognitive examination, commonly used to screen for dementia and other cognitive deficits (Folstein et al. J Psychiatr Res 1975; 12: 189-98). MMSE provides a total score of 0-30. Scores of 26 and lower are generally considered to indicate the presence of a deficit. The lower the numerical score of the MMSE, the greater the deficit or impairment of the tested patient relative to another individual with a higher score. An increase in the MMSE score may indicate an improvement in the patient's condition, while a decrease in the MMSE score may indicate a worsening of the patient's condition. In some embodiments, a stable MMSE score may indicate a slowing, delay or cessation of AD progression, or the absence of new clinical, functional or cognitive symptoms or impairment, or the overall stability of the disease.

[0044] The Clinical Dementia Rating ("CDR") (Morris Neurology 1993; 43: 2412-4) is a semi-structured interview that produces five levels of impairment in each of the following six categories of cognitive-based functioning: memory, orientation, judgment and problem solving, community affairs, home and hobbies, and personal care. The CDR was originally designed to use an overall score: 0-no dementia; 0.5-probable dementia, 1-mild dementia, 2-moderate dementia, 3-severe dementia.

[0045] The complete CDR-SB score is based on the sum of the scores for all 6 boxes. Subscores for each of the boxes or components can also be obtained separately, such as CDR / Memory or CDR / Judgment and Problem Solving. As used herein, a "decline in CDR-SB performance" or an "increase in CDR-SB score" indicates a worsening of the patient's condition and can reflect the progression of AD.

[0046] The term "CDR-SB" refers to the Clinical Dementia Rating-Sum of Boxes, which provides a score between 0 and 18 (O'Bryant et al., 2008, Arch Neurol 65: 1091-1095). The CDR-SB score is based on a semi-structured interview with a patient and a caregiver information provider, and produces five levels of performance impairment for each of the following six categories of cognitive function: memory, orientation, judgment / problem solving, community affairs, family and hobbies, and personal care. The test is performed on both the patient and the caregiver, and each component (or each "box") is scored on a scale of 0 to 3 (five degrees are 0, 0.5, 1, 2, and 3). The sum of the scores of the six categories is the CDR-SB score. The decline in the CDR-SB score may indicate an improvement in the patient's condition, while the increase in the CDR-SB score may indicate a worsening of the patient's condition. In some embodiments, a stable CDR-SB score may indicate a slowdown, delay, or stop of AD progression, or no new clinical, functional, or cognitive symptoms or damage, or the overall stability of the disease.

[0047] The Alzheimer's Disease Assessment Scale-Cognitive Subscale ("ADAS Cog") is a scale commonly used to assess cognitive abilities in clinical trials for mild to moderate AD (Rozzini et al. Int J Geriatr Psychiatry 2007; 22: 1217-22.; Connor and Sabbagh, J Alzheimers Dis. 2008; 15: 461-4; Ihl et al. Int J Geriatr Psychiatry 2012; 27: 15-21). ADAS-Cog is an examiner-administered battery of scales that assess multiple cognitive domains, including memory, comprehension, practice, orientation, and spontaneous speech (Rosen et al. 1984, Am J Psychiatr 141: 1356-64; Mohs et al. 1997, Alzheimer Dis Assoc Disord 11(S2): S13-S21). ADAS-Cog is the standard primary endpoint in AD treatment trials (Mani 2004, Stat Med 23: 305-14). The higher the numerical score on ADAS-Cog, the greater the defect or damage of the test patient relative to another individual with a lower score. ADAS-Cog can be used to assess whether the treatment for AD is effective. An increase in ADAS-Cog scores indicates a worsening of the patient's condition, while a decrease in ADAS-Cog scores indicates an improvement in the patient's condition. In certain embodiments, a stable ADAS-Cog score can indicate a slowing down, delay or cessation of AD progression, or the absence of new clinical or cognitive symptoms or damage, or the overall stability of the disease.

[0048] ADAS-Cog12 is a 70-point version of the ADAS-Cog plus a 10-point delayed word recall item that assesses recall of a learned word list. ADAS-Cog11 is another version with a range of 0-70. Other ADAS-Cogs include ADAS-Cogl3 and ADAS-Cogl4.

[0049] A decrease in ADAS-Cog11 score may indicate an improvement in the patient's condition, while an increase in ADAS-Cog11 score may indicate a worsening of the patient's condition. In some embodiments, a stable ADAS-Cog11 score may indicate a slowing, delay, or cessation of AD progression, or a decrease in the progression of clinical or cognitive decline, or the absence of new clinical or cognitive symptoms or impairment, or overall stability of the disease.

[0050] The component subtests of ADAS-Cog11 can be divided into three cognitive domains: memory, language and practice (Verma et al., Alzheimer's Research & Therapy, 2015). This "classification" can improve the sensitivity of measuring cognitive decline, for example, when paying attention to mild to moderate AD stages (Verma, 2015). Therefore, the changes of each of the ADAS-Cog11 scores in the three cognitive domains can be analyzed: memory domain, language domain and practice domain. The memory domain value of ADAS-Cog11 scores can be referred to as "ADAS-Cog11 memory domain score" or simply "memory domain" in this article. Memory decline slowing can refer to reducing the loss rate of memory ability and / function, retaining memory and / or reducing memory loss. For example, the score of ADAS-Cog11 memory domain is smaller (or the negative value is smaller), which can prove that memory decline slows down.

[0051] Similarly, the language domain value of the ADAS-Cog 11 score may be referred to herein as the "ADAS-Cog 11 language domain score" or simply the "language domain"; and the practice domain value of the ADAS-Cog 11 score may be referred to herein as the "ADAS-Cog 11 practice domain score" or simply the "practice domain". Practice may refer to planning and / or performing simple tasks and / or practice may refer to the ability to conceptualize, plan, and perform complex sequences of motor actions, as well as the ability to copy drawings or three-dimensional structures and follow commands.

[0052] The memory domain score is further divided into multiple components, including scores that reflect the subject's ability to recognize and / or recall words, thereby assessing the ability of "word recognition" or "word recall." The word recognition assessment of the ADAS-Cog11 memory domain score may be referred to herein as the "ADAS-Cog11 word recognition score" or simply the "word recognition score." For example, equivalent alternative forms of the subtests for word recall and word recognition can be used for continuous testing applications for a given patient. For example, a smaller score (or a smaller negative value) for the word recognition component of the ADAS-Cog11 memory domain can demonstrate a slowdown in memory decline.

[0053] The Alzheimer's Disease Cooperative Study Group-Activities of Daily Living Inventory or the Alzheimer's Disease Cooperative Study Group-Activities of Daily Living Scale ("ADCS-ADL; "Galasko et al. Alzheimer Dis Assoc Disord 1997; 11 (Suppl 2): ​​S33-9) is the most widely used scale for assessing functional outcomes in AD patients (Vellas et al. Lancet Neurol. 2008; 7: 436-50). Scores range from 0 to 78, with higher scores indicating better ADL function. ADCS-ADL is administered to caregivers and covers basic ADL (e.g., eating and going to the toilet) and more complex ADL or instrumental ADL (e.g., using the phone, managing finances, preparing meals) (Galasko et al. Alzheimer Disease and Associated Disorders, 1997 11 (Suppl 2), S33-S39).

[0054] The Neuropsychiatric Inventory ("NPI") (Cummings et al. Neurology 1994; 44: 2308-14) is a widely used scale for assessing behavioral symptoms of AD, including their frequency, severity, and associated distress. Individual symptom scores range from 0 to 12, and total NPI scores range from 0 to 144. The NPI is administered to caregivers and refers to the patient's behavior over the previous month.

[0055] The Alzheimer's Disease Caregiver Global Impression Scale ("CaGI-Alz") is a new scale used in the clinical study described herein and consists of four items that assess the caregiver's perception of change in the severity of the patient's disease. All items are scored on a 7-point Likert scale ranging from 1 (much improved since the start of treatment / previous CaGI Alz rating) to 7 (much worse since the start of treatment / previous CaGI Alz).

[0056] The term "IADL" refers to the Instrumental Activities of Daily Living scale (Lawton, MP and Brody, EM, 1969, Gerontologist 9: 179-186). This scale measures the ability to perform typical daily activities, such as housework, laundry, operating the telephone, shopping, preparing meals, etc. The lower the score, the more impaired the individual is in performing activities of daily living.

[0057] Another scale that can be used is the Amsterdam Activities of Daily Living Questionnaire (A-IADL-Q).

[0058] Figure 1 An example embodiment of a telehealth service environment 100 according to an embodiment of the present disclosure is shown, which can be used to detect predicted longitudinal changes in quantified speech variables associated with a patient as an estimate of the patient's AD progression or treatment response of the AD patient. As depicted, the telehealth service environment 100 may include a plurality of patients 102A, 102B, 102C, and 102D, each of which is associated with a corresponding electronic device 104A, 104B, 104C, and 104D, which may be suitable for allowing the plurality of patients 102A, 102B, 102C 102D to launch and participate in corresponding telehealth applications 106A (e.g., "telehealth application 1"), 106B (e.g., "telehealth application 2"), 106C (e.g., "telehealth application 3"), and 106D (e.g., "telehealth application N").

[0059] In certain embodiments, such as Figure 1 As depicted, the respective electronic devices 104A, 104B, 104C, and 104D may be coupled to a telehealth services platform 112 via one or more communication networks 110. In certain embodiments, the telehealth services platform 112 may include, for example, a cloud-based computing architecture suitable for hosting and serving telehealth applications 106A (e.g., “telehealth application 1”), 106B (e.g., “telehealth application 2”), 106C (e.g., “telehealth application 3”), and 106D (e.g., “telehealth application N”) executed on the respective electronic devices 104A, 104B, 104C, and 104D. For example, in one embodiment, the telehealth services platform 112 may include a platform as a service (PaaS) architecture, a software as a service (SaaS) architecture, an infrastructure as a service (IaaS) architecture, a computing as a service (CaaS) architecture, a data as a service (DaaS) architecture, a database as a service (DBaaS) architecture, or other similar cloud-based computing architectures (e.g., “X” as a service (XaaS)).

[0060] In certain embodiments, such as Figure 1As further depicted, the telemedicine service platform 112 may include one or more processing devices 114 (e.g., servers) and one or more data stores 116. For example, in some embodiments, the one or more processing devices 114 (e.g., servers) may include one or more general purpose processors, graphics processing units (GPUs), application specific integrated circuits (ASICs), systems on chips (SoCs), microcontrollers, field programmable gate arrays (FPGAs), central processing units (CPUs), application processors (APs), vision processing units (VPUs), neural processing units (NPUs), neural decision processors (NDPs), deep learning processors (DLPs), tensor processing units (TPUs), neuromorphic processing units (NPUs), or any of a variety of other processing devices or accelerators that may be suitable for providing processing and / or computational support for telemedicine applications 106A (e.g., “telemedicine application 1”), 106B (e.g., “telemedicine application 2”), 106C (e.g., “telemedicine application 3”), and 106D (e.g., “telemedicine application N”). Similarly, the data store 116 may include, for example, one or more internal databases that may be used to store information associated with the plurality of patients 102A, 102B, 102C, and 102D (eg, audio files of the patient speech data 118 ).

[0061] In certain embodiments, as previously described, the telehealth services platform 112 may be a hosting and service platform for telehealth applications 106A (e.g., “telehealth application 1”), 106B (e.g., “telehealth application 2”), 106C (e.g., “telehealth application 3”), and 106D (e.g., “telehealth application N”) executed on respective electronic devices 104A, 104B, 104C, and 104D. For example, in some embodiments, the telehealth applications 106A (e.g., “telehealth application 1”), 106B (e.g., “telehealth application 2”), 106C (e.g., “telehealth application 3”), and 106D (e.g., “telehealth application N”) may each include, for example, a telehealth mobile application (e.g., a mobile “app”) that may be used to allow multiple patients 102A, 102B, 102C, and 102D to remotely access health care services and medical care services and / or interact with one or more patient-selected clinicians (e.g., clinician 126) as part of an on-demand health care service.

[0062] In certain embodiments, one or more of the plurality of patients 102A, 102B, 102C, and 102D may include one or more patients suffering from AD, one or more patients suspected of suffering from AD, and / or one or more patients predisposed to developing AD. Figure 1 As further depicted, in certain embodiments, one or more of the plurality of patients 102A, 102B, 102C, and 102D may receive a speech-based assessment for detecting a predicted longitudinal change in an associated quantified speech variable as an estimate of AD progression or AD treatment response for one or more of the plurality of patients 102A, 102B, 102C, and 102D. For example, in certain embodiments, one or more of the plurality of patients 102A, 102B, 102C, and 102D may input speech 108A, 108B, 108C, 108D using telemedicine applications 106A (e.g., “telemedicine application 1”), 106B (e.g., “telemedicine application 2”), 106C (e.g., “telemedicine application 3”), and 106D (e.g., “telemedicine application N”) executed on respective electronic devices 104A, 104B, 104C, and 104D. For example, in some embodiments, the input speech 108A, 108B, 108C, 108D may include, for example, an electronic recording of speech by the plurality of patients 102A, 102B, 102C, and 102D.

[0063] In some embodiments, the input speech 108A, 108B, 108C, 108D can be executed in response to one or more requests provided, for example, by the telemedicine services platform 112 via telemedicine applications 106A (e.g., “telemedicine application 1”), 106B (e.g., “telemedicine application 2”), 106C (e.g., “telemedicine application 3”), and 106D (e.g., “telemedicine application N”) to one or more of multiple patients 102A, 102B, 102C, and 102D. In other embodiments, one or more of the multiple patients 102A, 102B, 102C, and 102D can utilize one or more microphones of corresponding electronic devices 104A, 104B, 104C, and 104D to record input speech 108A, 108B, 108C, 108D without first being prompted by telemedicine application 106A (e.g., “telemedicine application 1”), 106B (e.g., “telemedicine application 2”), 106C (e.g., “telemedicine application 3”), and 106D (e.g., “telemedicine application N”).

[0064] For example, in some embodiments, as part of a speech-based assessment, the telehealth service platform 112 can generate and provide one or more speech-based tasks that prompt one or more of the plurality of patients 102A, 102B, 102C, and 102D to generate speech and record the speech through one or more microphones of the corresponding electronic devices 104A, 104B, 104C, and 104D. In one embodiment, the speech-based assessment can include, for example, a description of an image that can be displayed via the telemedicine applications 106A, 106B, 106C, and 106D, a reading of a book passage that can be presented via the telemedicine applications 106A, 106B, 106C, and 106D, a series of question-answering tasks that can be presented via the telemedicine applications 106A, 106B, 106C, and 106D, or other speech-based assessments based on medical-grade neuropsychological speech and language assessments.

[0065] In some embodiments, the speech-based assessment may include a series of question-response tasks based on a Clinical Dementia Rating (CDR) interview. For example, in some embodiments, the series of question-response tasks based on a CDR interview may include a series of question-response tasks related to, for example, the recent daily activities of one or more of the plurality of patients 102A, 102B, 102C, and 102D, work-related activities of one or more of the plurality of patients 102A, 102B, 102C, and 102D, hobby-related activities of one or more of the plurality of patients 102A, 102B, 102C, and 102D, or other previous or current experiences and / or activities that would be expected to be easily recalled by a cognitively healthy patient. In some embodiments, the speech-based assessment may be performed at different times within a given period of time. For example, in some embodiments, the speech-based assessment may be performed on an initial date and then again, for example, on one or more dates selected from the group consisting of approximately 0.25 months, 0.5 months, 0.75 months, 1 month, 3 months, 6 months, 9 months, 12 months, 15 months, 18 months, 21 months, 24 months, 27 months, 30 months, 33 months, and / or 36 months from the initial date.

[0066] In certain embodiments, upon completion of the speech-based assessment by one or more of the plurality of patients 102A, 102B, 102C, and 102D, one or more of the corresponding electronic devices 104A, 104B, 104C, and 104D may then transmit one or more audio files of the patient speech data 118 to the telemedicine services platform 112. In certain embodiments, the one or more audio files of the patient speech data 118 may be stored to one or more data stores 116 of the telemedicine services platform 112. In certain embodiments, one or more processing devices 114 (e.g., servers) may then access the one or more audio files of the patient speech data 118 and analyze the one or more audio files of the patient speech data 118 to quantify one or more speech variables using the one or more audio files of the patient speech data 118. For example, in some embodiments, one or more processing devices 114 (e.g., servers) can utilize one or more machine learning models (e.g., natural language processing (NLP) models, transformer-based language models, automatic speech recognition (ASR) models) to convert an original audio file of the patient speech data 118 into a text representation (e.g., a transcript) or other representation data to quantify at least two speech variables extracted, for example, from either or both of one or more linguistic speech variables and one or more acoustic speech variables from the patient speech data 118. In one embodiment, the at least two speech variables quantified include a word length variable and a particle usage variable. In another embodiment, the at least two speech variables quantified include a word length variable and at least one MFCC feature (including an MFCC mean 11 variable, an MFCC variance 25 variable, or an MFCC variance 26 variable).

[0067] In some embodiments, the one or more linguistic speech variables may include one or more of a word length speech variable, a particle usage speech variable, a word frequency speech variable, a syntactic depth speech variable, a noun usage speech variable, and a pronoun usage speech variable. For example, in some embodiments, a word length speech variable (e.g., the number of characters included in a word spoken by one or more of the plurality of patients 102A, 102B, 102C, and 102D) measures the length of words in the speech of one or more of the plurality of patients 102A, 102B, 102C, and 102D in characters. The particle usage speech variable measures the usage rate of different particles (e.g., prepositions used in conjunction with another word to form a multi-word phrase, clause, or sentence). The word frequency speech variable measures the average frequency (e.g., lexical richness) of words used by one or more of the plurality of patients 102A, 102B, 102C, and 102D based on, for example, frequency norms in a standard corpus.

[0068] In some embodiments, the syntactic depth speech variable measures the complexity of syntactic structures used by one or more of the plurality of patients 102A, 102B, 102C, and 102D (e.g., phrase length, clause complexity, and ratios of different syntactic structures). The noun usage speech variable measures the usage of different parts of speech (such as nouns), while the pronoun usage speech variable measures the usage of different parts of speech (such as pronouns). Similarly, in some embodiments, one or more acoustic speech variables may include one or more Mel-frequency cepstral coefficient (MFCC) features. One or more MFCC features may include the mean of the 11th MFCC coefficient (MFCC mean 11), the variance of the first-order derivative of the 11th MFCC coefficient (MFCC variance 25), and the variance of the first-order derivative of the 12th MFCC coefficient (MFCC variance 26).

[0069] In some embodiments, one or more processing devices 114 (e.g., a server) can then generate a composite score based on the normalization of the quantified at least two speech variables extracted from either or both of the one or more linguistic speech variables and the one or more acoustic speech variables and the substantial weighting of the quantified at least two speech variables extracted from either or both of the one or more linguistic speech variables and the one or more acoustic speech variables. For example, in some embodiments, the quantified at least two speech variables extracted from either or both of the one or more linguistic speech variables (e.g., a word length variable and a particle usage variable, and optionally a word frequency variable, a syntactic depth variable, a noun usage variable, or a pronoun usage variable) and one or more acoustic speech variables (e.g., one or more Mel-Frequency Cepstral Coefficient (MFCC) features) can be normalized, for example by subtracting the mean of the speech variables across multiple patients 102A, 102B, 102C, and 102D and then dividing by the standard deviation. In some embodiments, the quantified at least two speech variables extracted from any one or both of the one or more linguistic speech variables (e.g., word length variable and particle usage variable, and optionally word frequency variable, syntactic depth variable, noun usage variable, or pronoun usage variable) and one or more acoustic speech variables (e.g., one or more Mel-frequency cepstral coefficient (MFCC) features) may then be substantially weighted (e.g., weights include: word length variable=1.0, word frequency variable=0.9, syntactic depth variable=0.9, noun usage variable=0.8, pronoun usage variable=0.8, particle usage variable=1.0) and combined into a composite score (e.g., an equally weighted composite score, a weighted composite score). In one embodiment, the substantial weighting may refer to, for example, a weight assigned to the quantified plurality of speech variables so as not to neglect any of the quantified plurality of speech variables. In one embodiment, the quantified at least two speech variables used to generate the composite score may include a word length variable and a particle usage variable. In another embodiment, the quantified at least two speech variables used to generate the composite score may include a word length variable and at least one of an MFCC mean 11 variable, an MFCC variance 25 variable, or an MFCC variance 26 variable.

[0070] For example, in some embodiments, at least two quantified speech variables extracted from either or both of one or more linguistic speech variables (e.g., word length variables and particle usage variables, and optionally word frequency variables, syntactic depth variables, noun usage variables, or pronoun usage variables) and one or more acoustic speech variables (e.g., one or more Mel-Frequency Cepstral Coefficient (MFCC) features) may be combined to generate a composite score for measuring or predicting longitudinal changes over time.

[0071] In some embodiments, one or more processing devices 114 (e.g., servers) may generate a composite score by: 1) normalizing at least two quantized speech variables extracted from either or both of one or more linguistic speech variables (e.g., word length variable and particle usage variable, and optionally word frequency variable, syntactic depth variable, noun usage variable, or pronoun usage variable) and one or more acoustic speech variables (e.g., one or more Mel-frequency cepstral coefficient (MFCC) features), 2) applying equal weighting (e.g., weights include: word length variable=0.9, word frequency variable=0.9, syntactic depth variable=0.9, noun usage variable=0.9, pronoun usage variable=0.9, particle usage variable=0.9) to each of the at least two quantized speech variables extracted from either or both of the one or more linguistic speech variables and one or more acoustic speech variables (e.g., one or more Mel-frequency cepstral coefficient (MFCC) features), and 3) combining the normalized and equally weighted quantized multiple speech variables to generate a composite score. In one embodiment, the at least two quantified speech variables used to generate the composite score may include a word length variable and a particle usage variable. In another embodiment, the at least two quantified speech variables used to generate the composite score may include a word length variable and at least one of a MFCC mean 11 variable, a MFCC variance 25 variable, or a MFCC variance 26 variable.

[0072] In some embodiments, one or more processing devices 114 (e.g., a server) may then determine a measured or predicted longitudinal change in the quantified speech variable based on the generated composite score. Figure 4 and 5 It will be further appreciated that the quantified one or more linguistic speech variables (e.g., word length variables and particle usage variables, and optionally word frequency variables, syntactic depth variables, noun usage variables, or pronoun usage variables) and the quantified one or more acoustic speech variables (e.g., one or more Mel-Frequency Cepstral Coefficient (MFCC) features) can each be associated with longitudinal change, and therefore, the composite score can include an overall prediction of longitudinal change in the quantified speech variables.

[0073] In certain embodiments, one or more processing devices 114 (e.g., a server) may then estimate AD progression for one or more of the plurality of patients 102A, 102B, 102C, and 102D based on the predicted longitudinal changes. For example, in some embodiments, one or more processing devices 114 (e.g., a server) may estimate AD progression for one or more of the plurality of patients 102A, 102B, 102C, and 102D based on correlation of the composite score with one or more clinical assessment metrics. For example, in some embodiments, one or more processing devices 114 (e.g., a server) may utilize one or more linear mixed models (LMMs) or one or more other similar statistical models to correlate the effect of change over time relative to the composite score with the effect of change over time relative to, for example, one or more of the MMSE score, CDR interview, CDR-SB score, ADAS-Cog score, ADCS-ADL score, NPI score, NPI-Q score, CaGI score, IADL score, A-IADL-Q score, or RBANS score. Based on the correlation of the composite score with the one or more clinical assessment metrics, one or more processing devices 114 (eg, servers) may then generate an estimate 120 of AD progression for one or more of the plurality of patients 102A, 102B, 102C, and 102D.

[0074] In certain embodiments, such as Figure 1 As further illustrated, the one or more processing devices 114 (e.g., a server) may then transmit the generated estimate 120 of AD progression to a computing device 122 and present a notification or report 124 to a clinician 126, which may be associated with a corresponding patient in the plurality of patients 102A, 102B, 102C, and 102D. In one embodiment, the one or more processing devices 114 (e.g., a server) may also transmit the generated estimate 120 of AD progression to a corresponding patient in the plurality of patients 102A, 102B, 102C, and 102D via a respective electronic device 104A, 104B, 104C, or 104D. In some embodiments, the clinician 126 can review the notification or report 124 and communicate with a corresponding patient among the plurality of patients 102A, 102B, 102C, and 102D via the corresponding telehealth application 106A (e.g., “telehealth application 1”), 106B (e.g., “telehealth application 2”), 106C (e.g., “telehealth application 3”), or 106D (e.g., “telehealth application N”) regarding the cognitive health of the corresponding patient among the plurality of patients 102A, 102B, 102C, and 102D.

[0075] For example, in certain embodiments, based on the medical review and analysis of the generated estimate 120 of AD progression, the clinician 126 may transmit, via the computing device 122, a recommendation for adjusting a treatment regimen or therapeutic regimen for a corresponding patient in the plurality of patients 102A, 102B, 102C, and 102D. In response to receiving the input of the clinician 126 via the computing device 122, one or more processing devices 114 (e.g., a server) may generate a recommendation for adjusting a treatment regimen that includes, for example, a therapeutic agent consisting of at least one compound selected from the group consisting of: a compound for oxidative stress, an anti-apoptotic compound, a metal chelator, an inhibitor of DNA repair, 3-amino-1-propanesulfonic acid (3APS), 1,3-propane disulfonate (1,3PDS), a secretase activator, a β- and γ-secretase inhibitor, a tau protein, an anti-tau antibody, an anti-tau agent, a gene therapy, a neurotransmitter, a β sheet disruptor, an anti-inflammatory molecule, an atypical antipsychotic , cholinesterase inhibitors, other drugs and nutritional supplements; therapeutic agents selected from the group consisting of symptomatic drugs, neurological drugs, corticosteroids, antibiotics, antiviral agents, anti-tau antibodies, tau inhibitors, anti-β-amyloid (anti-Aβ) antibodies, β-amyloid aggregation inhibitors, target-binding therapeutic agents, anti-BACE1 antibodies, BACE1 inhibitors, cholinesterase inhibitors, NMDA receptor antagonists, monoamine depleting agents, dihydroergotamine mesylate, anticholinergic anti-Parkinson's disease agents, dopaminergic anti-Parkinson's disease agents, tetrabenazine, anti-inflammatory agents, hormones, vitamins, Danpifen, homotaurine, serotonin receptor activity modulators, interferons and glucocorticoids. In certain embodiments, one or more processing devices 114 (e.g., a server) may then transmit, via a corresponding electronic device 104A, 104B, 104C, or 104D, a notification regarding a recommendation for administering a treatment regimen or therapeutic regimen to a corresponding patient among the plurality of patients 102A, 102B, 102C, and 102D.

[0076] Figure 2 A flow chart of a method 200 for detecting predicted longitudinal changes in quantified speech variables (including word length variables and particle usage variables associated with a patient) as an estimate of the patient's AD progression or AD patient's treatment response according to an embodiment of the present disclosure is shown. The method 200 may utilize one or more processing devices (e.g., as described above with respect to Figure 1The remote health service platform 112 discussed is carried out, and the one or more processing devices may include hardware (for example, a general-purpose processor, a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a system on a chip (SoC), a microcontroller, a field-programmable gate array (FPGA), a central processing unit (CPU), an application processor (AP), a visual processing unit (VPU), a neural processing unit (NPU), a neural decision processor (NDP), a deep learning processor (DLP), a tensor processing unit (TPU), a neuromorphic processing unit (NPU), or any other processing device that may be suitable for processing various medical profile data and / or speech data and making one or more decisions based thereon), software (for example, instructions running / executed on one or more processors), firmware (for example, microcode), or some combination thereof.

[0077] The method 200 may begin at block 202, where one or more processing devices receive speech data including a patient's description of one or more previous or current experiences of the patient, where the speech data is captured at multiple moments during a period of time. For example, in some embodiments, the patient speech data may include a record of one or more responses of the patient to questions or prompts included in a clinical dementia rating (CDR) interview. The method 200 may then continue at block 204, where the one or more processing devices analyze the speech data to quantify multiple speech variables, where the multiple speech variables include a word length variable and a particle usage variable. For example, in some embodiments, the word length speech variable may include a measure of the number of characters included in a word spoken by one or more of the multiple patients 102A, 102B, 102C, and 102D. Similarly, the particle usage speech variable may include a measure of the rate of use of different particles (e.g., prepositions used in conjunction with another word to form a multi-word phrase, fragment, or sentence) spoken by one or more of the multiple patients 102A, 102B, 102C, and 102D.

[0078] The method 200 may then continue at block 206, where one or more processing devices determine a composite score based on the normalization of the quantified plurality of speech variables and the substantive weighting assigned to each of the quantified plurality of speech variables. For example, in some embodiments, the quantized at least two speech variables extracted from either or both of the one or more linguistic speech variables (e.g., a word length variable and a particle usage variable, and optionally a word frequency variable, a syntactic depth variable, a noun usage variable, or a pronoun usage variable) and one or more acoustic speech variables (e.g., one or more Mel-Frequency Cepstral Coefficient (MFCC) features) may be normalized, substantive weighted, and combined into a composite score (e.g., an equally weighted composite score, a weighted composite score). In one embodiment, the quantized at least two speech variables used to generate the composite score may include a word length variable and a particle usage variable. In another embodiment, the quantized at least two speech variables used to generate the composite score may include a word length variable and at least one of an MFCC mean 11 variable, an MFCC variance 25 variable, or an MFCC variance 26 variable.

[0079] The method 200 may then continue at box 208, where one or more processing devices detect predicted longitudinal changes in the quantified plurality of speech variables based on the composite score. The method 200 may then end at box 210, where one or more processing devices estimate the patient's AD progression based on the predicted longitudinal changes. For example, in some embodiments, one or more processing devices may estimate AD progression based on the predicted longitudinal changes by correlating the composite score with one or more clinical assessment metrics (e.g., MMSE scores, CDR interviews, CDR-SB scores, ADAS-Cog scores, ADCS-ADL scores, NPI scores, NPI-Q scores, CaGI scores, IADL scores, A-IADL-Q scores, or RBANS scores).

[0080] Figure 3A A flow chart of a method 300A for detecting predicted longitudinal changes in quantified speech variables (including word length variables and MFCC variables associated with a patient) as an estimate of the patient's AD progression or AD patient's treatment response according to an embodiment of the present disclosure is shown. The method 300A may utilize one or more processing devices (e.g., as described above with respect to Figure 1The remote health service platform 112 discussed is carried out, and the one or more processing devices may include hardware (for example, a general-purpose processor, a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a system on a chip (SoC), a microcontroller, a field-programmable gate array (FPGA), a central processing unit (CPU), an application processor (AP), a visual processing unit (VPU), a neural processing unit (NPU), a neural decision processor (NDP), a deep learning processor (DLP), a tensor processing unit (TPU), a neuromorphic processing unit (NPU), or any other processing device that may be suitable for processing various medical profile data and / or speech data and making one or more decisions based thereon), software (for example, instructions running / executed on one or more processors), firmware (for example, microcode), or some combination thereof.

[0081] Method 300A may begin at block 302, where one or more processing devices receive speech data including a patient's description of one or more previous or current experiences of the patient, where the speech data is captured at multiple moments during a period of time. For example, in some embodiments, the patient speech data may include a record of one or more responses of the patient to questions or prompts included in a clinical dementia rating (CDR) interview. Method 300A may then continue at block 304, where one or more processing devices analyze the speech data to quantify multiple speech variables, where the multiple speech variables include word length variables and Mel-frequency cepstral coefficient (MFCC) speech variables. For example, in some embodiments, the word length speech variable may include a measure of the number of characters included in a word spoken by one or more of the multiple patients 102A, 102B, 102C, and 102D. Similarly, the MFCC speech variable may include the mean of the 11th MFCC coefficient (MFCC mean 11), the variance of the first derivative of the 11th MFCC coefficient (MFCC variance 25), or the variance of the first derivative of the 12th MFCC coefficient (MFCC variance 26).

[0082] The method 300A may then continue at block 306, where one or more processing devices determine a composite score based on the normalization of the quantified plurality of speech variables and the substantive weighting assigned to each of the quantified plurality of speech variables. For example, in some embodiments, the quantized at least two speech variables extracted from either or both of the one or more linguistic speech variables (e.g., a word length variable and a particle usage variable, and optionally a word frequency variable, a syntactic depth variable, a noun usage variable, or a pronoun usage variable) and one or more acoustic speech variables (e.g., one or more Mel-Frequency Cepstral Coefficient (MFCC) features) may be normalized, substantive weighted, and combined into a composite score (e.g., an equally weighted composite score, a weighted composite score). For example, the quantized at least two speech variables used to generate the composite score may include a word length variable and at least one of a MFCC mean 11 variable, a MFCC variance 25 variable, or a MFCC variance 26 variable.

[0083] Method 300A may then continue at box 308, where one or more processing devices detect predicted longitudinal changes in the quantified plurality of speech variables based on the composite score. Method 300A may then end at box 310, where one or more processing devices estimate the patient's AD progression based on the predicted longitudinal changes. For example, in some embodiments, one or more processing devices may estimate AD progression based on the predicted longitudinal changes by correlating the composite score with one or more clinical assessment metrics (e.g., MMSE scores, CDR interviews, CDR-SB scores, ADAS-Cog scores, ADCS-ADL scores, NPI scores, NPI-Q scores, CaGI scores, IADL scores, A-IADL-Q scores, or RBANS scores).

[0084] Figure 3B A flow chart of a method 300B for detecting predicted longitudinal changes in quantified speech variables (including particle usage speech variables and MFCC speech variables associated with a patient) as an estimate of the patient's AD progression or AD patient's treatment response according to an embodiment of the present disclosure is shown. The method 300B may utilize one or more processing devices (e.g., as described below with respect to Figure 6 and 7The one or more processing devices may include hardware (e.g., a general purpose processor, a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a system on a chip (SoC), a microcontroller, a field programmable gate array (FPGA), a central processing unit (CPU), an application processor (AP), a visual processing unit (VPU), a neural processing unit (NPU), a neural decision processor (NDP), a deep learning processor (DLP), a tensor processing unit (TPU), a neuromorphic processing unit (NPU), or any other processing device that may be suitable for processing various medical profile data and / or speech data and making one or more decisions based thereon), software (e.g., instructions running / executed on one or more processors), firmware (e.g., microcode), or some combination thereof.

[0085] Method 300B may begin at box 312, where one or more processing devices receive speech data including a patient's description of one or more previous or current experiences of the patient, where the speech data is captured at multiple moments during a period of time. For example, in some embodiments, the patient speech data may include a record of one or more responses of the patient to questions or prompts included in a clinical dementia rating (CDR) interview. Method 300B may then continue at box 314, where one or more processing devices analyze the speech data to quantify multiple speech variables, where the multiple speech variables include particle usage variables and Mel frequency cepstral coefficient (MFCC) variables. For example, in some embodiments, the particle usage speech variable may include a measure of the usage rate of different particles (e.g., prepositions used in conjunction with another word to form a multi-word phrase, fragment, or sentence). Similarly, the MFCC speech variable may include the mean of the 11th MFCC coefficient (MFCC mean 11), the variance of the first derivative of the 11th MFCC coefficient (MFCC variance 25), or the variance of the first derivative of the 12th MFCC coefficient (MFCC variance 26).

[0086] The method 300B may then continue at block 316, where one or more processing devices determine a composite score based on the normalization of the quantified plurality of speech variables and the substantive weights assigned to each of the quantified plurality of speech variables. For example, in some embodiments, the quantified at least two speech variables extracted from either or both of the one or more linguistic speech variables (e.g., a word length variable and a particle usage variable, and optionally a word frequency variable, a syntactic depth variable, a noun usage variable, or a pronoun usage variable) and one or more acoustic speech variables (e.g., one or more Mel-Frequency Cepstral Coefficient (MFCC) features) may be normalized, substantive weighted, and combined into a composite score (e.g., an equally weighted composite score, a weighted composite score). For example, the quantized at least two speech variables used to generate the composite score may include a word length variable and at least one of a MFCC mean 11 variable, a MFCC variance 25 variable, or a MFCC variance 26 variable.

[0087] Method 300B may then continue at box 318, where one or more processing devices detect predicted longitudinal changes in the quantified plurality of speech variables based on the composite score. Method 300B may then end at box 320, where one or more processing devices estimate the patient's AD progression based on the predicted longitudinal changes. For example, in some embodiments, one or more processing devices may estimate AD progression based on the predicted longitudinal changes by correlating the composite score with one or more clinical assessment metrics (e.g., MMSE scores, CDR interviews, CDR-SB scores, ADAS-Cog scores, ADCS-ADL scores, NPI scores, NPI-Q scores, CaGI scores, IADL scores, A-IADL-Q scores, or RBANS scores).

[0088] Figure 4 A graph 400 depicting longitudinal trajectories of patient linguistic and acoustic speech variables as linearly changing over time is shown in accordance with an embodiment of the present disclosure. In certain embodiments, graphs 402, 404, 406, 408, 410, and 412 may show a plurality of quantified linguistic speech variables, including, for example, word length speech variables (e.g., graph 402), syntactic depth speech variables (e.g., graph 404), word frequency speech variables (e.g., graph 406), noun usage speech variables (e.g., graph 408), particle usage speech variables (e.g., graph 410), and pronoun usage speech variables (e.g., graph 412).

[0089] In certain embodiments, graphs 402, 404, 406, 408, 410, and 412 show Pearson correlation coefficients (e.g., “R” represents a number between −1 and +1 that reflects the tendency for two random variables to have a linear association) and / or Pearson correlation p-values ​​(e.g., “p” represents an indication of whether the correlation is statistically significant) for a plurality of quantified linguistic speech variables, including, for example, a word length speech variable (e.g., graph 402), a syntactic depth speech variable (e.g., graph 404), a word frequency speech variable (e.g., graph 406), a noun usage speech variable (e.g., graph 408), a particle usage speech variable (e.g., graph 410), and a pronoun usage speech variable (e.g., graph 412), each of which is plotted against time (e.g., a baseline initial date, approximately 6 months from the initial date, approximately 12 months from the initial date, and approximately 18 months from the initial date).

[0090] In one embodiment, the Pearson correlation p-value for each of a plurality of quantified linguistic speech variables, including, for example, a word length speech variable (e.g., graph 402), a syntactic depth speech variable (e.g., graph 404), a word frequency speech variable (e.g., graph 406), a noun usage speech variable (e.g., graph 408), a particle usage speech variable (e.g., graph 410), and a pronoun usage speech variable (e.g., graph 412), has a statistically significant time effect at p<0.001 because each of these variables is plotted against time (e.g., baseline initial date, approximately 6 months from the initial date, approximately 12 months from the initial date, and approximately 18 months from the initial date). Specifically, as Figure 4 As depicted, each of the longitudinal trajectories for a word length speech variable (e.g., graph 402), a syntactic depth speech variable (e.g., graph 404), a word frequency speech variable (e.g., graph 406), a noun use speech variable (e.g., graph 408), a particle use speech variable (e.g., graph 410), and a pronoun use speech variable (e.g., graph 412) tends over time in a direction corresponding to, for example, one or more patients utilizing shorter, more frequent words, simpler sentence grammar, fewer nouns, and more particles and pronouns. Thus, Figure 4 Graphs 402, 404, 406, 408, 410, and 412 illustrate correlations of linguistic speech variables with longitudinal changes over time (eg, over approximately 18 months).

[0091] Similarly, in some embodiments, graphs 414, 416, and 418 can show multiple quantified acoustic speech variables, including, for example, an 11th MFCC coefficient (MFCC mean 11) speech variable (e.g., graph 414), a variance of the first derivative of the 11th MFCC coefficient (MFCC variance 25) (e.g., graph 416), and a variance of the first derivative of the 12th MFCC coefficient (MFCC variance 26) (e.g., graph 418), each of which is plotted against time (e.g., a baseline initial date, approximately 6 months from the initial date, approximately 12 months from the initial date, and approximately 18 months from the initial date). In one embodiment, the Pearson correlation p-value for each of a plurality of quantified acoustic speech variables, including, for example, the 11th MFCC coefficient (MFCC mean 11) speech variable (e.g., graph 414), the variance of the first derivative of the 11th MFCC coefficient (MFCC variance 25) (e.g., graph 416), and the variance of the first derivative of the 12th MFCC coefficient (MFCC variance 26) (e.g., graph 416), has a statistically significant time effect at p<0.001 because each of these variables is plotted against time (e.g., baseline initial date, approximately 6 months from the initial date, approximately 12 months from the initial date, and approximately 18 months from the initial date). Thus, Figure 4 Graphs 414, 416, and 418 of FIG. 4 show correlations of acoustic-speech variables with longitudinal changes over time (eg, over approximately 18 months).

[0092] Figure 5A tabular graph 500 showing standardized effect sizes of changes in clinical assessment scores from baseline to endpoint as related to composite scores according to an embodiment of the present disclosure is shown. For example, in one embodiment, a composite score 502 may be generated based on a plurality of speech variables, the plurality of speech variables including a word length speech variable, a word frequency speech variable, a syntactic depth speech variable, a noun usage speech variable, a pronoun usage speech variable, a particle usage speech variable, a mean of the 11th MFCC coefficient (MFCC mean 11) speech variable, a variance of the first derivative of the 11th MFCC coefficient (MFCC variance 25) speech variable, and a variance of the first derivative of the 12th MFCC coefficient (MFCC variance 26) speech variable. Specifically, according to an embodiment of the present disclosure, the comprehensive score 502 can be generated by: standardizing and equally weighting each of the word length speech variable, word frequency speech variable, syntactic depth speech variable, noun usage speech variable, pronoun usage speech variable, particle usage speech variable, the mean of the 11th MFCC coefficient (MFCC mean 11) speech variable, the variance of the first-order derivative of the 11th MFCC coefficient (MFCC variance 25) speech variable, and the variance of the first-order derivative of the 12th MFCC coefficient (MFCC variance 26) speech variable, and combining these speech variables into the comprehensive score 502.

[0093] In other embodiments, the composite score 502 may be generated based on: normalization of at least two speech variables extracted from any one or both of one or more linguistic speech variables (e.g., word length variable and particle usage variable, and optionally word frequency variable, syntactic depth variable, noun usage variable, or pronoun usage variable) and one or more acoustic speech variables (e.g., MFCC mean 11, MFCC variance 25, MFCC variance 26); and substantial weighting of at least two speech variables extracted from any one or both of one or more linguistic speech variables and one or more acoustic speech variables. In some embodiments, substantial weighting may refer to, for example, weights assigned to at least two speech variables extracted from any one or both of one or more linguistic speech variables and one or more acoustic speech variables so as not to neglect any one of the one or more linguistic speech variables and one or more acoustic speech variables. In one embodiment, the quantified at least two speech variables used to generate the composite 502 score may include a word length variable and a particle usage variable. In another embodiment, the quantified at least two speech variables used to generate the composite score 502 may include a word length variable and at least one of an MFCC mean 11 variable, an MFCC variance 25 variable, or an MFCC variance 26 variable.

[0094] In certain embodiments, such as Figure 5As depicted in the table 500 of , the generated composite score 502 (e.g., composite score = 0.29) has a similar effect size for detecting longitudinal change compared to the following items: CDR-Sum of Boxes score 504 (e.g., CDR-SB = 0.30), Alzheimer's Disease Cooperative Study Group-Activities of Daily Living Inventory (ADCS-ADL) score 506 (e.g., ADCS-ADL = -0.30), Mini-Mental State Examination (MMSE) score 508 (e.g., MMSE = -0.23), Alzheimer's Disease Assessment Scale-Cognitive Subscale (ADAS-Cog) score 510 (e.g., ADAS-Cog = 0.22), and Repeatable Battery of Neuropsychological Status (RBANS) score 512 (e.g., RBANS = -0.15). Therefore, Figure 5 Tabular graph 500 demonstrates that a composite score 502 (eg, composite score = 0.29) generated as described herein can be used to accurately detect predicted longitudinal changes in a quantified speech variable associated with a patient as an estimate of the patient's AD progression or the patient's AD treatment response.

[0095] Figure 6 An example computing system 600 according to an embodiment of the present disclosure is shown, which can be used to detect predicted longitudinal changes in quantified speech variables associated with a patient, and detect the severity and progression of AD in the patient based on the predicted longitudinal changes in the quantified speech variables. In some embodiments, the computing system 600 can perform one or more steps of one or more methods described or shown herein. In some embodiments, the computing system 600 provides the functionality described or shown herein. In some embodiments, software running on the computing system 600 performs one or more steps of one or more methods described or shown herein, or provides the functionality described or shown herein. Certain embodiments include one or more portions of one or more computing systems 600. Herein, where appropriate, references to a computer system may include a computing device, and vice versa. In addition, where appropriate, references to a computer system may include one or more computer systems.

[0096] The present disclosure contemplates any suitable number of computing systems 600. The present disclosure contemplates computing systems 600 taking any suitable physical form. By way of example and not limitation, computing system 600 may be an embedded computing system, a system on a chip (SOC), a single board computer system (SBC) (e.g., a computer-on-module (COM) or a system-on-module (SOM)), a desktop computer system, a laptop or notebook computer system, an interactive kiosk, a mainframe, a computer system network, a mobile phone, a personal digital assistant (PDA), a server, a tablet computer system, an augmented / virtual reality device, or a combination of two or more thereof. Where appropriate, computing system 600 may include one or more computing systems 600; may be integrated or distributed; may span multiple locations; may span multiple machines; may span multiple data centers; or may reside in a cloud, which may include one or more cloud components in one or more networks.

[0097] Where appropriate, computing system 600 may perform one or more steps of one or more methods described or illustrated herein without substantial spatial or temporal limitations. As an example and not limitation, computing system 600 may perform one or more steps of one or more methods described or illustrated herein in real time or in batch mode. Where appropriate, computing system 600 may perform one or more steps of one or more methods described or illustrated herein at different times or at different locations.

[0098] In some embodiments, computing system 600 includes processor 602, memory 604, storage device 606, input / output (I / O) interface 608, communication interface 610, and bus 612. Although the present disclosure describes and illustrates a particular computer system having a particular number of particular components in a particular arrangement, the present disclosure contemplates any suitable computer system having any suitable number of any suitable components in any suitable arrangement. In some embodiments, processor 602 includes hardware for executing instructions, such as those constituting a computer program. As an example and not limitation, to execute instructions, processor 602 may retrieve (or fetch) instructions from internal registers, internal caches, memory 604, or storage device 606; may decode and execute these instructions; and may then write one or more results to internal registers, internal caches, memory 604, or storage device 606. In some embodiments, processor 602 may include one or more internal caches for data, instructions, or addresses. Where appropriate, the present disclosure contemplates processor 602 including any suitable number of any suitable internal caches. As an example and not limitation, processor 602 may include one or more instruction caches, one or more data caches, and one or more translation lookaside buffers (TLBs). The instructions in the instruction cache may be copies of the instructions in memory 604 or storage 606, and the instruction cache may speed up the retrieval of those instructions by processor 602.

[0099] The data in the data cache may be: a copy of the data in the memory 604 or storage device 606 for operation by instructions executed at the processor 602; the result of the previous instruction executed at the processor 602 for access or writing to the memory 604 or storage device 606 by subsequent instructions executed at the processor 602; or other suitable data. The data cache may speed up the read or write operation of the processor 602. The TLB may speed up the virtual address translation of the processor 602. In some embodiments, the processor 602 may include one or more internal registers for data, instructions, or addresses. Where appropriate, the present disclosure contemplates a processor 602 including any suitable number of any suitable internal registers. Where appropriate, the processor 602 may include one or more arithmetic logic units (ALUs); may be a multi-core processor; or may include one or more processors 602. Although the present disclosure describes and illustrates a particular processor, the present disclosure contemplates any suitable processor.

[0100] In some embodiments, memory 604 includes a main memory for storing instructions for processor 602 to execute or data for processor 602 to operate on. As an example and not limitation, computing system 600 may load instructions from storage device 606 or another source (such as, for example, another computing system 600) to memory 604. Processor 602 may then load instructions from memory 604 to internal registers or internal caches. To execute the instructions, processor 602 may retrieve the instructions from the internal registers or internal caches and decode them. During or after execution of the instructions, processor 602 may write one or more results (which may be intermediate results or final results) to the internal registers or internal caches. Processor 602 may then write one or more of those results to memory 604.

[0101] In some embodiments, the processor 602 executes only instructions in one or more internal registers or internal caches or in the memory 604 (rather than the storage device 606 or elsewhere), and operates only on data in one or more internal registers or internal caches or in the memory 604 (rather than the storage device 606 or elsewhere). One or more memory buses (which may each include an address bus and a data bus) may couple the processor 602 to the memory 604. The bus 612 may include one or more memory buses, as described below. In some embodiments, one or more memory management units (MMUs) reside between the processor 602 and the memory 604 and facilitate access to the memory 604 requested by the processor 602. In some embodiments, the memory 604 includes a random access memory (RAM). Where appropriate, the RAM may be a volatile memory. Where appropriate, the RAM may be a dynamic RAM (DRAM) or a static RAM (SRAM). In addition, where appropriate, the RAM may be a single-port or multi-port RAM. The present disclosure contemplates any suitable RAM. Where appropriate, the memory 604 may include one or more memory devices 604. Although this disclosure describes and illustrates particular memory, this disclosure contemplates any suitable memory.

[0102] In some embodiments, the storage device 606 includes a mass storage device for data or instructions. As an example and not limitation, the storage device 606 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive, or a combination of two or more thereof. Where appropriate, the storage device 606 may include a removable or non-removable (or fixed) medium. Where appropriate, the storage device 606 may be inside or outside the computing system 600. In some embodiments, the storage device 606 is a non-volatile solid-state memory. In some embodiments, the storage device 606 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more thereof. The present disclosure contemplates a mass storage device 606 in any suitable physical form. Where appropriate, the storage device 606 may include one or more memory control units that facilitate communication between the processor 602 and the storage device 606. Where appropriate, storage 606 may include one or more storage devices 606. Although this disclosure describes and illustrates particular storage devices, this disclosure contemplates any suitable storage devices.

[0103] In some embodiments, the I / O interface 608 includes hardware, software, or both, which provides one or more interfaces for communicating between the computing system 600 and one or more I / O devices. Where appropriate, the computing system 600 may include one or more of these I / O devices. One or more of these I / O devices can enable communication between a person and the computing system 600. As an example and not limitation, the I / O device may include a keyboard, a keypad, a microphone, a monitor, a mouse, a printer, a scanner, a speaker, a still camera, a stylus, a tablet computer, a touch screen, a trackball, a camera, another suitable I / O device, or a combination of two or more thereof. The I / O device may include one or more sensors. The present disclosure contemplates any suitable I / O device and any suitable I / O interface 606 for them. Where appropriate, the I / O interface 608 may include one or more devices or software drivers (enabling the processor 602 to drive one or more of these I / O devices). Where appropriate, the I / O interface 608 may include one or more I / O interfaces 606. Although the present disclosure describes and illustrates a specific I / O interface, the present disclosure encompasses any suitable I / O interface.

[0104] In some embodiments, the communication interface 610 includes hardware, software, or both that provides one or more interfaces for communication (such as, for example, packet-based communication) between the computing system 600 and one or more other computer systems 600 or one or more networks. As an example and not limitation, the communication interface 610 may include a network interface controller (NIC) or network adapter for communicating with an Ethernet or other wire-based network, or a wireless NIC (WNIC) or wireless adapter for communicating with a wireless network (such as a WI-FI network). The present disclosure contemplates any suitable network and any suitable communication interface 610 for it.

[0105] As an example and not limitation, the computing system 600 may communicate with one or more parts of an ad hoc network, a personal area network (PAN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), or the Internet, or a combination of two or more thereof. One or more parts of one or more of these networks may be wired or wireless. As an example, the computing system 600 may communicate with a wireless PAN (WPAN) (such as, for example, a BLUETOOTH WPAN), a WI-FI network, a WI-MAX network, a cellular phone network (such as, for example, a global system for mobile communications (GSM) network), or other suitable wireless networks, or a combination of two or more thereof. Where appropriate, the computing system 600 may include any suitable communication interface 610 for any of these networks. Where appropriate, the communication interface 610 may include one or more communication interfaces 610. Although the present disclosure describes and illustrates a specific communication interface, the present disclosure encompasses any suitable communication interface.

[0106] In some embodiments, bus 612 includes hardware, software, or both that couples components of computing system 600 to each other. By way of example and not limitation, bus 612 may include an accelerated graphics port (AGP) or other graphics bus, an extended industry standard architecture (EISA) bus, a front side bus (FSB), a HyperTransport (HT) interconnect, an industry standard architecture (ISA) bus, a wireless broadband interconnect, a low pin count (LPC) bus, a memory bus, a micro channel architecture (MCA) bus, a peripheral component interconnect (PCI) bus, a PCIe bus, a serial advanced technology attachment (SATA) bus, a video electronics standard association local (VLB) bus, or another suitable bus or a combination of two or more thereof. Where appropriate, bus 612 may include one or more buses 612. Although this disclosure describes and illustrates a particular bus, this disclosure contemplates any suitable bus or interconnect.

[0107] Herein, one or more computer-readable non-transitory storage media may include one or more semiconductor-based or other integrated circuits (ICs) (such as, for example, field programmable gate arrays (FPGAs) or application-specific ICs (ASICs)), hard disk drives (HDDs), hybrid hard disk drives (HHDs), optical disks, optical disk drives (ODDs), magneto-optical disks, magneto-optical disk drives, floppy disks, floppy disk drives (FDDs), magnetic tapes, solid-state drives (SSDs), RAM drives, SECURE DIGITAL cards or drives, any other suitable computer-readable non-transitory storage media, or any suitable combination of two or more thereof. Where appropriate, the computer-readable non-transitory storage medium may be a volatile storage medium, a non-volatile storage medium, or a combination of a volatile storage medium and a non-volatile storage medium.

[0108] Figure 7 An example artificial intelligence (AI) architecture 702 is shown according to an embodiment of the present disclosure (which can be used as described above with respect to Figure 6 A portion of the computing system 600 discussed is included in Figure 700, which example AI architecture can be used to detect predicted longitudinal changes in quantified speech variables associated with a patient, and detect the severity and progression of AD in the patient based on the predicted longitudinal changes in the quantified speech variables. In some embodiments, the AI ​​architecture 702 can be implemented using, for example, one or more processing devices, which can include hardware (e.g., a general-purpose processor, a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a system on a chip (SoC), a microcontroller, a field-programmable gate array (FPGA), a central processing unit (CPU), an application processor (AP), a visual processing unit (VPU), a neural processing unit (NPU), a neural decision processor (NDP), a deep learning processor (DLP), a tensor processing unit (TPU), a neuromorphic processing unit (NPU), and / or other processing devices that can be suitable for processing various medical profile data and making one or more decisions based thereon), software (e.g., instructions running / executing on one or more processing devices), firmware (e.g., microcode), or some combination thereof.

[0109] In certain embodiments, such as Figure 7As depicted, AI architecture 702 may include machine learning (ML) algorithms and functions 704, natural language processing (NLP) algorithms and functions 706, expert systems 708, computer-based vision algorithms and functions 710, speech recognition algorithms and functions 712, planning algorithms and functions 714, and robotics algorithms and functions 716. In certain embodiments, ML algorithms and functions 704 may include any statistically based algorithms that may be suitable for finding patterns across large amounts of data (e.g., “big data” such as genomics data, proteomics data, metabolomics data, metagenomics data, transcriptomics data, drug data, medical diagnostics data, medical procedure data, medical diagnosis data, medical symptom data, demographic data, patient lifestyle data, physical activity data, family history data, socioeconomic data, geographic environmental data, etc.). For example, in certain embodiments, ML algorithms and functions 704 may include deep learning algorithms 718, supervised learning algorithms 720, and unsupervised learning algorithms 722.

[0110] In some embodiments, the deep learning algorithm 718 may include any artificial neural network (ANN) that can be used to learn deep representations and abstract concepts from large amounts of data. For example, the deep learning algorithm 718 may include ANNs such as perceptrons, multi-layer perceptrons (MLPs), autoencoders (AEs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), long short-term memories (LSTMs), gated recurrent units (GRUs), restricted Boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), generative adversarial networks (GANs) and deep Q-networks, neural autoregressive distribution estimation (NADEs), adversarial networks (ANs), attention models (AMs), spiking neural networks (SNNs), deep reinforcement learning, etc.

[0111] In some embodiments, the supervised learning algorithm 720 may include any algorithm that can be used to apply what has been learned in the past, for example, to new data to predict future events using labeled examples. For example, starting from an analysis of a known training data set, the supervised learning algorithm 720 can generate an inference function to make predictions about output values. The supervised learning algorithm 600 can also compare its output with the correct and expected output and find errors so that the supervised learning algorithm 720 can be modified accordingly. On the other hand, the unsupervised learning algorithm 722 may include any algorithm that can be applied, for example, when the data used to train the unsupervised learning algorithm 722 is neither classified nor labeled. For example, the unsupervised learning algorithm 722 can study and analyze how the system infers functions that describe hidden structures from unlabeled data.

[0112] In some embodiments, NLP algorithms and functions 706 may include any algorithm or function suitable for automatically manipulating natural language (such as speech and / or text). For example, in some embodiments, NLP algorithms and functions 706 may include content extraction algorithms or functions 724, classification algorithms or functions 726, machine translation algorithms or functions 728, question answering (QA) algorithms or functions 730, and text generation algorithms or functions 732. In some embodiments, content extraction algorithms or functions 724 may include means for extracting text or images from electronic documents (e.g., web pages, text editor documents, etc.) for use in, for example, other applications.

[0113] In some embodiments, the classification algorithm or function 726 may include any algorithm that can learn from the data input of the supervised learning model using a supervised learning model (e.g., logistic regression, naive Bayes, stochastic gradient descent (SGD), k-nearest neighbor, decision tree, random forest, support vector machine (SVM), etc.), and make new observations or classifications based on this. The machine translation algorithm or function 728 may include any algorithm or function that can be suitable for automatically converting a source text in one language into text in another language, for example. The QA algorithm or function 730 may include any algorithm or function that can be suitable for automatically answering questions asked by humans in natural language, such as algorithms or functions performed by voice-controlled personal assistant devices. The text generation algorithm or function 732 may include any algorithm or function that can be suitable for automatically generating natural language text.

[0114] In some embodiments, the expert system 708 may include any algorithm or function that may be suitable for simulating the judgment and behavior of a human or organization with professional knowledge and experience in a particular field (e.g., stock trading, medicine, sports statistics, etc.). The computer-based vision algorithm and function 710 may include any algorithm or function that may be suitable for automatically extracting information from an image (e.g., a photo image, a video image). For example, the computer-based vision algorithm and function 710 may include an image recognition algorithm 734 and a machine vision algorithm 736. The image recognition algorithm 734 may include any algorithm that may be suitable for automatically identifying and / or classifying, for example, objects, places, people, etc. that may be included in one or more image frames or other display data. The machine vision algorithm 736 may include any algorithm that may be suitable for allowing a computer to "see" or, for example, rely on an image sensor camera with dedicated optical elements to acquire images for processing, analysis, and / or measurement of various data characteristics for decision-making purposes.

[0115] In some embodiments, speech recognition algorithms and functions 712 may include any algorithm or function that may be suitable for recognizing spoken language and translating it into text, such as through automatic speech recognition (ASR), computer speech recognition, speech to text (STT) 738, or text to speech (TTS) 740, for example, in order to compute communication with one or more users via speech. In some embodiments, planning algorithms and functions 714 may include any algorithm or function that may be suitable for generating a sequence of actions, where each action may include its own set of prerequisites to be satisfied before performing the action. Examples of AI planning may include classical planning, reduction to other problems, time planning, probabilistic planning, preference-based planning, conditional planning, and the like. Finally, robotics algorithms and functions 716 may include any algorithm, function, or system that may enable one or more devices to replicate human behavior through, for example, motion, posture, performance tasks, decision making, emotions, and the like.

[0116] As used herein, "or" is inclusive and not exclusive, unless expressly stated otherwise or the context indicates otherwise. Thus, as used herein, "A or B" means "A, B, or both," unless expressly stated otherwise or the context indicates otherwise. Furthermore, as used herein, "and" means both jointly and severally, unless expressly stated otherwise or the context indicates otherwise. Thus, as used herein, "A and B" means "A and B, jointly or severally," unless expressly stated otherwise or the context indicates otherwise.

[0117] As used herein, “automatically” and its derivatives mean “without human intervention” unless expressly indicated otherwise or the context indicates otherwise.

[0118] The embodiments disclosed herein are merely examples, and the scope of the present disclosure is not limited thereto. Embodiments according to the present disclosure are particularly disclosed in the attached claims for methods, storage media, systems, and computer program products, wherein any feature mentioned in one claim category (e.g., method) can be claimed for protection in another claim category (e.g., system). Dependents or references in the attached claims are selected only for formal reasons. However, any subject matter resulting from intentional reference to any preceding claim (particularly multiple dependents) may also be claimed, so any combination of claims and their features may be disclosed and claimed regardless of the dependents selected in the attached claims. The subject matter that may be claimed includes not only a combination of features as listed in the attached claims, but also any other combination of features in the claims, wherein each feature mentioned in the claims may be combined with any other feature or combination of other features in the claims. In addition, any embodiment and feature described or depicted herein may be claimed in a separate claim and / or in any combination with any embodiment or feature described or depicted herein or with any feature of the attached claims.

[0119] The scope of the present disclosure covers all changes, substitutions, variations, alterations and modifications to the exemplary embodiments described or shown herein that will be understood by those of ordinary skill in the art. The scope of the present disclosure is not limited to the exemplary embodiments described or shown herein. In addition, although the present disclosure describes and illustrates the corresponding embodiments herein as including specific parts, elements, features, functions, operations or steps, any of these embodiments may include any combination or arrangement of any parts, elements, features, functions, operations or steps described or shown anywhere herein that will be understood by those of ordinary skill in the art. In addition, in the appended claims, references to devices or systems or parts of devices or systems adapted to, arranged to, capable of, configured to, enabled to, operable to or operated to perform specific functions, cover the device, system, component, whether or not it or the specific function is activated, turned on or unlocked, as long as the device, system or component is so adapted, arranged, capable of, configured to, enabled to, operable or operated. In addition, although the present disclosure describes or illustrates the specific advantages provided by certain embodiments, certain embodiments may not provide, partially provide or provide all of these advantages.

[0120] Example

[0121] The examples provided are:

[0122] 1. A method for detecting longitudinal progression of Alzheimer's disease (AD) in a patient, the method comprising:

[0123] receiving speech data comprising a patient's description of one or more previous or current experiences of the patient, wherein the speech data is captured at a plurality of moments during a period of time;

[0124] analyzing the speech data to quantify a plurality of speech variables, wherein the plurality of speech variables include a word length variable and a particle usage variable;

[0125] determining a composite score based on normalization of the quantified plurality of speech variables and a substantive weight assigned to each of the quantified plurality of speech variables;

[0126] detecting a predicted longitudinal change in the quantified plurality of speech variables based on the composite score; and

[0127] AD progression in the patient is estimated based on the predicted longitudinal changes.

[0128] 2. The method of embodiment 1, wherein the instructions to receive the speech data include instructions to receive an audio file including an electronic recording of the patient's speech.

[0129] 3. The method of any one of embodiments 1 to 2, wherein the electronic record of the patient's speech comprises an electronic record of one or more verbal responses of the patient to a Clinical Dementia Rating (CDR) interview.

[0130] 4. A method according to any one of embodiments 1 to 3, wherein the speech data is captured on an initial date and one or more dates selected from the group consisting of: approximately 0.25, 0.5, 0.75, 1, 3, 6, 9, 12, 15, 18, 21, 24, 27, 30, 33 and 36 months from the initial date.

[0131] 5. The method according to any one of embodiments 1 to 4, wherein the plurality of speech variables further comprises a word frequency variable, a syntactic depth variable, a noun usage variable, or a pronoun usage variable.

[0132] 6. The method of any one of embodiments 1 to 5, wherein the plurality of speech variables further comprises one or more Mel-Frequency Cepstral Coefficient (MFCC) features.

[0133] 7. A method according to any one of embodiments 1 to 6, wherein the one or more MFCC features include the mean of the 11th MFCC coefficient (MFCC mean 11), the variance of the first-order derivative of the 11th MFCC coefficient (MFCC variance 25), or the variance of the first-order derivative of the 12th MFCC coefficient (MFCC variance 26).

[0134] 8. The method of any one of embodiments 1 to 7, wherein determining the composite score comprises:

[0135] normalizing the quantified plurality of speech variables;

[0136] applying equal weighting to each of the quantified plurality of speech variables; and

[0137] The standardized and equally weighted quantified multiple speech variables are combined to generate the composite score.

[0138] 9. The method of any one of embodiments 1 to 8, wherein estimating the AD progression based on the predicted longitudinal change comprises correlating the composite score with one or more clinical assessment metrics.

[0139] 10. The method of any one of embodiments 1 to 9, wherein the one or more clinical assessment measures are selected from the group consisting of: Mini-Mental State Examination (MMSE) score, Clinical Dementia Rating (CDR) interview, Clinical Dementia Rating-Sum of Boxes (CDR-SB) scale, Alzheimer's Disease Assessment Scale-Cognitive (ADAS-Cog) subscale battery, Alzheimer's Disease Cooperative Research Group-Activities of Daily Living Checklist (ADCS-ADL) scale, Neuropsychiatric Inventory (NPI) scale, Neuropsychiatric Inventory-Questionnaire (NPI-Q), Alzheimer's Caregiver Global Impression (CaGI) scale, Instrumental Activities of Daily Living (IADL) scale, Amsterdam Activities of Daily Living Questionnaire (A-IADL-Q), and Repeatable Battery of Neuropsychological Status (RBANS) scale.

[0140] 11. The method according to any one of embodiments 1 to 10, further comprising determining whether the patient is responsive to treatment based on estimated AD progression.

[0141] 12. A method according to any one of embodiments 1 to 11, wherein analyzing the speech data to determine the quantified multiple speech variables includes utilizing one or more natural language processing (NLP) machine learning models to analyze the speech data.

[0142] 13. The method of any one of embodiments 1 to 12, further comprising transmitting a notification of the estimated AD progression to a computing device associated with a clinician.

[0143] 14. The method of any one of embodiments 1 to 13, further comprising transmitting a notification of the estimated AD progression to an electronic device associated with the patient.

[0144] 15. The method of any one of embodiments 1 to 14, further comprising generating a recommendation to adjust a treatment regimen for the patient in response to estimating the AD progression.

[0145] 16. The method of any one of embodiments 1 to 15, wherein the treatment regimen comprises: a therapeutic agent consisting of at least one compound selected from the group consisting of: compounds for oxidative stress, anti-apoptotic compounds, metal chelators, inhibitors of DNA repair, 3-amino-1-propanesulfonic acid (3APS), 1,3-propane disulfonate (1,3PDS), secretase activators, β- and γ-secretase inhibitors, tau proteins, anti-tau antibodies, anti-tau agents, gene therapy, neurotransmitters, β-sheet disruptors, anti-inflammatory molecules, atypical antipsychotics, cholinesterase inhibitors, other drugs and nutritional supplements agent; a therapeutic agent selected from the group consisting of: symptomatic drugs, neurological drugs, corticosteroids, antibiotics, antiviral agents, anti-tau antibodies, tau inhibitors, anti-β-amyloid (anti-Aβ) antibodies, β-amyloid aggregation inhibitors, target-binding therapeutic agents, anti-BACE1 antibodies, BACE1 inhibitors, cholinesterase inhibitors, NMDA receptor antagonists, monoamine depleting agents, dihydroergotamine mesylate, anticholinergic anti-Parkinson's disease agents, dopaminergic anti-Parkinson's disease agents, tetrabenazine, anti-inflammatory agents, hormones, vitamins, Danpifen, homotaurine, serotonin receptor activity modulators, interferons and glucocorticoids.

[0146] 17. The method of any one of embodiments 1 to 16, wherein the symptomatic drug is selected from the group consisting of: a cholinesterase inhibitor, galantamine, rivastigmine, donepezil, an N-methyl-D-aspartate receptor antagonist, memantine, and a food supplement (optionally wherein the food supplement is ).

[0147] 18. The method of any one of embodiments 1 to 17, wherein the anti-Aβ antibody is selected from the group consisting of bapineuzumab, solanezumab, aducanumab, gantenerumab, crenezumab, donanemab, and lecanemab.

[0148] 19. The method of any one of embodiments 1 to 18, wherein the anti-tau antibody is selected from the group consisting of an N-terminal binder, an intermediate domain binder, and a fibrillar tau binder.

[0149] 20. The method of any one of embodiments 1 to 19, wherein the anti-tau antibody is selected from the group consisting of cerenezumab, BMS-986168, C2N-8E12, gonelizumab, tipranezumab, and zagtenezumab.

[0150] 21. The method of any one of embodiments 1 to 20, wherein the therapeutic agent is a therapeutic agent that specifically binds to a target, and the target is selected from the group consisting of β-secretase, τ, presenilin, amyloid precursor protein or a portion thereof, β-amyloid peptide or an oligomer or fibril thereof, death receptor 6 (DR6), receptor for advanced glycation end products (RAGE), parkin, and huntingtin.

[0151] 22. The method of any one of embodiments 1 to 21, wherein the therapeutic agent is a monoamine depleting agent, optionally tetrabenazine.

[0152] 23. The method of any one of embodiments 1 to 22, wherein the therapeutic agent is an anticholinergic antiparkinsonian agent selected from the group consisting of procyclidine, diphenhydramine, trihexyphenidyl, benztropine, biperiden, and trihexyphenidyl.

[0153] 24. The method of any one of embodiments 1 to 23, wherein the therapeutic agent is a dopaminergic anti-Parkinson's disease agent selected from the group consisting of entacapone, selegiline, pramipexole, bromocriptine, rotigotine, selegiline, ropinirole, rasagiline, apomorphine, carbidopa, levodopa, pergolide, tolcapone, and amantadine.

[0154] 25. The method of any one of embodiments 1 to 24, wherein the therapeutic agent is an anti-inflammatory agent selected from the group consisting of nonsteroidal anti-inflammatory drugs and indomethacin.

[0155] 26. The method of any one of embodiments 1 to 25, wherein the therapeutic agent is a hormone selected from the group consisting of estrogen, progesterone, and leuprolide.

[0156] 27. The method of any one of embodiments 1 to 26, wherein the therapeutic agent is a vitamin selected from the group consisting of folic acid and niacinamide.

[0157] 28. The method of any one of embodiments 1 to 27, wherein the therapeutic agent is xaliproden or homotaurine, and the homotaurine is 3-aminopropanesulfonic acid or 3APS.

Claims

1. A method for detecting longitudinal progression of Alzheimer's disease (AD) in a patient, the method comprising: receiving speech data comprising a patient's description of one or more previous or current experiences of the patient, wherein the speech data is captured at a plurality of moments during a period of time; analyzing the speech data to quantify a plurality of speech variables, wherein the plurality of speech variables include a word length variable and a particle usage variable; determining a composite score based on normalization of the quantified plurality of speech variables and a substantive weight assigned to each of the quantified plurality of speech variables; detecting a predicted longitudinal change in the quantified plurality of speech variables based on the composite score; as well as AD progression in the patient is estimated based on the predicted longitudinal changes.

2. The method of claim 1, wherein receiving the speech data comprises receiving an audio file comprising an electronic recording of the patient's speech.

3. The method of claim 2, wherein the electronic record of the patient's speech comprises an electronic record of one or more verbal responses of the patient to a Clinical Dementia Rating (CDR) interview.

4. The method of claim 1, wherein the speech data is captured at an initial date and one or more dates selected from the group consisting of: approximately 0.25, 0.5, 0.75, 1, 3, 6, 9, 12, 15, 18, 21, 24, 27, 30, 33, and 36 months from the initial date.

5. The method of claim 1, wherein the plurality of speech variables further comprises a word frequency variable, a syntactic depth variable, a noun usage variable, or a pronoun usage variable.

6. The method of claim 1, wherein the plurality of speech variables further comprises one or more Mel-Frequency Cepstral Coefficient (MFCC) features.

7. The method according to claim 6, wherein the one or more MFCC features include the mean of the 11th MFCC coefficient (MFCC mean 11), the variance of the first-order derivative of the 11th MFCC coefficient (MFCC variance 25), or the variance of the first-order derivative of the 12th MFCC coefficient (MFCC variance 26).

8. The method of claim 1 , wherein determining the composite score comprises: normalizing the quantified plurality of speech variables; applying equal weighting to each of the quantified plurality of speech variables; and The standardized and equally weighted quantified multiple speech variables are combined to generate the composite score.

9. The method of claim 1, wherein estimating the AD progression based on the predicted longitudinal change comprises correlating the composite score with one or more clinical rating metrics.

10. The method of claim 9, wherein the one or more clinical assessment measures are selected from the group consisting of: Mini-Mental State Examination (MMSE) score, Clinical Dementia Rating (CDR) interview, Clinical Dementia Rating-Sum of Boxes (CDR-SB) scale, Alzheimer's Disease Assessment Scale-Cognitive (ADAS-Cog) subscale battery, Alzheimer's Disease Cooperative Research Group-Activities of Daily Living Checklist (ADCS-ADL) scale, Neuropsychiatric Inventory (NPI) scale, Neuropsychiatric Inventory-Questionnaire (NPI-Q), Alzheimer's Caregiver Global Impression (CaGI) scale, Instrumental Activities of Daily Living (IADL) scale, Amsterdam Activities of Daily Living Questionnaire (A-IADL-Q), and Repeatable Battery of Neuropsychological Status (RBANS) scale.

11. The method of claim 1, further comprising determining whether the patient is responsive to treatment based on estimated AD progression.

12. The method of claim 1, wherein analyzing the speech data to determine the quantified plurality of speech variables comprises analyzing the speech data using one or more natural language processing (NLP) machine learning models.

13. The method of claim 1, further comprising transmitting a notification of the estimated AD progression to a computing device associated with a clinician.

14. The method of claim 1, further comprising transmitting a notification of estimated AD progression to an electronic device associated with the patient.

15. The method of claim 1, further comprising generating a recommendation to adjust a treatment regimen for the patient in response to estimating the AD progression.

16. The method of claim 15, wherein the treatment regimen comprises: A therapeutic agent consisting of at least one compound selected from the group consisting of: compounds against oxidative stress, anti-apoptotic compounds, metal chelators, inhibitors of DNA repair, 3-amino-1-propanesulfonic acid (3APS), 1,3-propane disulfonate (1,3PDS), secretase activators, β- and γ-secretase inhibitors, tau proteins, anti-tau antibodies, anti-tau agents, gene therapy, neurotransmitters, beta sheet disruptors, anti-inflammatory molecules, atypical antipsychotics, cholinesterase inhibitors, other drugs and nutritional supplements; A therapeutic agent selected from the group consisting of: Symptomatic drugs, neurological drugs, corticosteroids, antibiotics, antiviral agents, anti-tau antibodies, tau inhibitors, anti-β-amyloid (anti-Aβ) antibodies, β-amyloid aggregation inhibitors, target-binding therapeutics, anti-BACE1 antibodies, BACE1 inhibitors, cholinesterase inhibitors, NMDA receptor antagonists, monoamine depleting agents, dihydroergotamine mesylate, anticholinergic antiparkinsonian agents, dopaminergic antiparkinsonian agents, tetrabenazine, anti-inflammatory agents, hormones, vitamins, tanpivirine, homotaurine, serotonin receptor activity modulators, interferons and glucocorticoids.

17. The method of claim 16, wherein the symptomatic drug is selected from the group consisting of: cholinesterase inhibitors, galantamine, rivastigmine, donepezil, N-methyl-D-aspartate receptor antagonists, memantine, and food supplements (optionally wherein the food supplement is ).

18. The method according to any one of claims 16 to 17, wherein the anti-Aβ antibody is selected from the group consisting of: bapinetumab, sorazumab, aducanumab, gantnerumab, cranizumab, donanatumab, and lencanezumab.

19. The method of any one of claims 15 to 18, wherein the anti-tau antibody is selected from the group consisting of an N-terminal binder, an intermediate domain binder, and a fibrillar tau binder.

20. The method of claim 19, wherein the anti-tau antibody is selected from the group consisting of cerenezumab, BMS-986168, C2N-8E12, gonelizumab, tipranezumab, and zagtenezumab.

21. The method of any one of claims 15 to 20, wherein the therapeutic agent is a therapeutic agent that specifically binds to a target, and the target is selected from the group consisting of β-secretase, τ, presenilin, amyloid precursor protein or a portion thereof, β-amyloid peptide or an oligomer or fibril thereof, death receptor 6 (DR6), receptor for advanced glycation end products (RAGE), parkin, and huntingtin.

22. The method of any one of claims 15 to 21, wherein the therapeutic agent is a monoamine depleting agent, optionally tetrabenazine.

23. The method of any one of claims 15 to 22, wherein the therapeutic agent is an anticholinergic antiparkinsonian agent selected from the group consisting of procyclidine, diphenhydramine, trihexyphenidyl, benztropine, biperiden, and trihexyphenidyl.

24. The method of any one of claims 15 to 23, wherein the therapeutic agent is a dopaminergic anti-Parkinson's disease agent selected from the group consisting of entacapone, selegiline, pramipexole, bromocriptine, rotigotine, selegiline, ropinirole, rasagiline, apomorphine, carbidopa, levodopa, pergolide, tolcapone, and amantadine.

25. The method of any one of claims 15 to 24, wherein the therapeutic agent is an anti-inflammatory agent selected from the group consisting of non-steroidal anti-inflammatory drugs and indomethacin.

26. The method of any one of claims 15 to 25, wherein the therapeutic agent is a hormone selected from the group consisting of estrogen, progesterone, and leuprolide.

27. The method of any one of claims 15 to 26, wherein the therapeutic agent is a vitamin selected from the group consisting of folic acid and niacinamide.

28. The method of any one of claims 15 to 27, wherein the therapeutic agent is xaliproden or homotaurine, the homotaurine being 3-aminopropanesulfonic acid or 3APS.

29. A system for detecting longitudinal progression of Alzheimer's disease (AD) in a patient, the system comprising one or more computing devices, comprising: one or more non-transitory computer-readable storage media including instructions; and One or more processors coupled to one or more storage media, the one or more processors configured to execute the instructions to: receiving speech data comprising a patient's description of one or more previous or current experiences of the patient, wherein the speech data is captured at a plurality of moments during a period of time; analyzing the speech data to quantify a plurality of speech variables, wherein the plurality of speech variables include a word length variable and a particle usage variable; determining a composite score based on normalization of the quantified plurality of speech variables and a substantive weight assigned to each of the quantified plurality of speech variables; detecting a predicted longitudinal change in the quantified plurality of speech variables based on the composite score; as well as AD progression in the patient is estimated based on the predicted longitudinal changes.

30. The system of claim 29, wherein the instructions to receive the speech data include instructions to receive an audio file including an electronic recording of the patient's speech.

31. The system of claim 30, wherein the electronic record of the patient's speech comprises an electronic record of one or more verbal responses of the patient to a Clinical Dementia Rating (CDR) interview.

32. A system according to claim 29, wherein the speech data is captured on an initial date and one or more dates selected from the group consisting of: approximately 0.25, 0.5, 0.75, 1, 3, 6, 9, 12, 15, 18, 21, 24, 27, 30, 33 and 36 months from the initial date.

33. The system of claim 29, wherein the plurality of speech variables further comprises a word frequency variable, a syntactic depth variable, a noun usage variable, or a pronoun usage variable.

34. The system of claim 29, wherein the plurality of speech variables further comprises one or more Mel-Frequency Cepstral Coefficient (MFCC) features.

35. A system according to claim 34, wherein the one or more MFCC features include the mean of the 11th MFCC coefficient (MFCC mean 11), the variance of the first-order derivative of the 11th MFCC coefficient (MFCC variance 25), or the variance of the first-order derivative of the 12th MFCC coefficient (MFCC variance 26).

36. The system of claim 29, wherein the instructions for determining the composite score further comprise instructions for: normalizing the quantified plurality of speech variables; applying equal weighting to each of the quantified plurality of speech variables; and The standardized and equally weighted quantified multiple speech variables are combined to generate the composite score.

37. The system of claim 29, wherein the instructions for estimating the AD progression based on the predicted longitudinal change further comprise instructions for correlating the composite score with one or more clinical assessment metrics.

38. The system of claim 37, wherein the one or more clinical assessment measures are selected from the group consisting of: Mini-Mental State Examination (MMSE) score, Clinical Dementia Rating (CDR) interview, Clinical Dementia Rating-Sum of Boxes (CDR-SB) scale, Alzheimer's Disease Assessment Scale-Cognitive (ADAS-Cog) subscale battery, Alzheimer's Disease Cooperative Research Group-Activities of Daily Living Checklist (ADCS-ADL) scale, Neuropsychiatric Inventory (NPI) scale, Neuropsychiatric Inventory-Questionnaire (NPI-Q), Alzheimer's Caregiver Global Impression (CaGI) scale, Instrumental Activities of Daily Living (IADL) scale, Amsterdam Activities of Daily Living Questionnaire (A-IADL-Q), and Repeatable Battery of Neuropsychological Status (RBANS) scale.

39. The system of claim 29, wherein the instructions further comprise instructions for determining whether the patient is responsive to treatment based on the estimated AD progression.

40. The system of claim 29, wherein the instructions to analyze the speech data to determine the quantified plurality of speech variables further comprise instructions to analyze the speech data using one or more natural language processing (NLP) machine learning models.

41. The system of claim 29, wherein the instructions further comprise instructions to transmit a notification of the estimated AD progression to a computing device associated with a clinician.

42. The system of claim 29, wherein the instructions further comprise instructions to transmit a notification of the estimated AD progression to an electronic device associated with the patient.

43. The system of claim 29, wherein in response to estimating the AD progression, the instructions further comprise instructions to generate a recommendation to adjust a treatment regimen for the patient.

44. The system of claim 43, wherein the treatment regimen comprises: A therapeutic agent consisting of at least one compound selected from the group consisting of: compounds against oxidative stress, anti-apoptotic compounds, metal chelators, inhibitors of DNA repair, 3-amino-1-propanesulfonic acid (3APS), 1,3-propane disulfonate (1,3PDS), secretase activators, β- and γ-secretase inhibitors, tau proteins, anti-tau antibodies, anti-tau agents, gene therapy, neurotransmitters, beta sheet disruptors, anti-inflammatory molecules, atypical antipsychotics, cholinesterase inhibitors, other drugs and nutritional supplements; A therapeutic agent selected from the group consisting of: Symptomatic drugs, neurological drugs, corticosteroids, antibiotics, antiviral agents, anti-tau antibodies, tau inhibitors, anti-β-amyloid (anti-Aβ) antibodies, β-amyloid aggregation inhibitors, target-binding therapeutics, anti-BACE1 antibodies, BACE1 inhibitors, cholinesterase inhibitors, NMDA receptor antagonists, monoamine depleting agents, dihydroergotamine mesylate, anticholinergic antiparkinsonian agents, dopaminergic antiparkinsonian agents, tetrabenazine, anti-inflammatory agents, hormones, vitamins, tanpivirine, homotaurine, serotonin receptor activity modulators, interferons and glucocorticoids.

45. The system of claim 44, wherein the symptomatic drug is selected from the group consisting of: cholinesterase inhibitors, galantamine, rivastigmine, donepezil, N-methyl-D-aspartate receptor antagonists, memantine, and a food supplement (optionally wherein the food supplement is ).

46. ​​The system of any one of claims 44 to 45, wherein the anti-Aβ antibody is selected from the group consisting of: bapinetumab, sorazumab, aducanumab, gantnerumab, craniluzumab, donanatumab, and lencanezumab.

47. The system of any one of claims 44 to 46, wherein the anti-tau antibody is selected from the group consisting of an N-terminal binder, an intermediate domain binder, and a fibrillar tau binder.

48. The system of claim 47, wherein the anti-tau antibody is selected from the group consisting of cerenezumab, BMS-986168, C2N-8E12, gonelizumab, tipranezumab, and zagtenezumab.

49. The system of any one of claims 44 to 48, wherein the therapeutic agent is a therapeutic agent that specifically binds to a target, and the target is selected from the group consisting of β-secretase, tau, presenilin, amyloid precursor protein or a portion thereof, β-amyloid peptide or an oligomer or fibril thereof, death receptor 6 (DR6), receptor for advanced glycation end products (RAGE), parkin, and huntingtin.

50. The system of any one of claims 44 to 49, wherein the therapeutic agent is a monoamine depleting agent, optionally tetrabenazine.

51. The system of any one of claims 44 to 49, wherein the therapeutic agent is an anticholinergic antiparkinsonian agent selected from the group consisting of procyclidine, diphenhydramine, trihexyphenidyl, benztropine, biperiden, and trihexyphenidyl.

52. The system of any one of claims 44 to 50, wherein the therapeutic agent is a dopaminergic anti-Parkinson's disease agent selected from the group consisting of entacapone, selegiline, pramipexole, bromocriptine, rotigotine, selegiline, ropinirole, rasagiline, apomorphine, carbidopa, levodopa, pergolide, tolcapone, and amantadine.

53. The system of any one of claims 44 to 51, wherein the therapeutic agent is an anti-inflammatory agent selected from the group consisting of non-steroidal anti-inflammatory drugs and indomethacin.

54. The system of any one of claims 44 to 53, wherein the therapeutic agent is a hormone selected from the group consisting of estrogen, progesterone, and leuprolide.

55. The system of any one of claims 44 to 54, wherein the therapeutic agent is a vitamin selected from the group consisting of folic acid and niacinamide.

56. The system of any one of claims 44 to 55, wherein the therapeutic agent is xaliproden or homotaurine, the homotaurine being 3-aminopropanesulfonic acid or 3APS.

57. A non-transitory computer readable medium comprising instructions that, when executed by one or more processors of one or more computing devices, cause the one or more processors to: receiving speech data comprising a patient's description of one or more previous or current experiences of the patient, wherein the speech data is captured at a plurality of moments during a period of time; analyzing the speech data to quantify a plurality of speech variables, wherein the plurality of speech variables include a word length variable and a particle usage variable; determining a composite score based on normalization of the quantified plurality of speech variables and a substantive weight assigned to each of the quantified plurality of speech variables; detecting a predicted longitudinal change in the quantified plurality of speech variables based on the composite score; as well as AD progression in the patient is estimated based on the predicted longitudinal changes.

58. The non-transitory computer-readable medium of claim 57, wherein the instructions to receive the speech data include instructions to receive an audio file including an electronic recording of the patient's speech.

59. The non-transitory computer-readable medium of claim 58, wherein the electronic record of the patient's speech comprises an electronic record of one or more verbal responses of the patient to a Clinical Dementia Rating (CDR) interview.

60. The non-transitory computer-readable medium of claim 57, wherein the speech data is captured at an initial date and one or more dates selected from the group consisting of: approximately 0.25, 0.5, 0.75, 1, 3, 6, 9, 12, 15, 18, 21, 24, 27, 30, 33, and 36 months from the initial date.

61. The non-transitory computer-readable medium of claim 57, wherein the plurality of speech variables further comprises a word frequency variable, a syntactic depth variable, a noun usage variable, or a pronoun usage variable.

62. The non-transitory computer-readable medium of claim 57, wherein the plurality of speech variables further comprises one or more Mel-Frequency Cepstral Coefficient (MFCC) features.

63. A non-transitory computer-readable medium according to claim 62, wherein the one or more MFCC features include the mean of the 11th MFCC coefficient (MFCC mean 11), the variance of the first-order derivative of the 11th MFCC coefficient (MFCC variance 25), or the variance of the first-order derivative of the 12th MFCC coefficient (MFCC variance 26).

64. The non-transitory computer readable medium of claim 57, wherein the instructions to determine the composite score further comprise instructions to: normalizing the quantified plurality of speech variables; applying equal weighting to each of the quantified plurality of speech variables; and The standardized and equally weighted quantified multiple speech variables are combined to generate the composite score.

65. The non-transitory computer readable medium of claim 57, wherein the instructions for estimating the AD progression based on the predicted longitudinal change further comprise instructions for correlating the composite score with one or more clinical rating metrics.

66. A non-transitory computer-readable medium according to claim 65, wherein the one or more clinical assessment measures are selected from the group consisting of: Mini-Mental State Examination (MMSE) score, Clinical Dementia Rating (CDR) interview, Clinical Dementia Rating-Sum of Boxes (CDR-SB) scale, Alzheimer's Disease Assessment Scale-Cognitive (ADAS-Cog) subscale battery, Alzheimer's Disease Cooperative Research Group-Activities of Daily Living Checklist (ADCS-ADL) scale, Neuropsychiatric Inventory (NPI) scale, Neuropsychiatric Inventory-Questionnaire (NPI-Q), Alzheimer's Disease Caregiver Global Impression (CaGI) scale, Instrumental Activities of Daily Living (IADL) scale, Amsterdam Activities of Daily Living Questionnaire (A-IADL-Q), and Repeatable Battery of Neuropsychological Status (RBANS) scale.

67. The non-transitory computer readable medium of claim 57, wherein the instructions further comprise instructions for determining whether the patient is responsive to treatment based on estimated AD progression.

68. The non-transitory computer-readable medium of claim 57, wherein the instructions for analyzing the speech data to determine the quantified plurality of speech variables further comprise instructions for analyzing the speech data using one or more natural language processing (NLP) machine learning models.

69. The non-transitory computer-readable medium of claim 57, wherein the instructions further comprise instructions to transmit a notification of the estimated AD progression to a computing device associated with a clinician.

70. The non-transitory computer readable medium of claim 57, wherein the instructions further comprise instructions to transmit a notification of the estimated AD progression to an electronic device associated with the patient.

71. The non-transitory computer-readable medium of claim 57, wherein in response to estimating the AD progression, the instructions further comprise instructions for generating a recommendation to adjust a treatment regimen for the patient.

72. The non-transitory computer readable medium of claim 71, wherein the treatment regimen comprises: A therapeutic agent consisting of at least one compound selected from the group consisting of: compounds against oxidative stress, anti-apoptotic compounds, metal chelators, inhibitors of DNA repair, 3-amino-1-propanesulfonic acid (3APS), 1,3-propane disulfonate (1,3PDS), secretase activators, β- and γ-secretase inhibitors, tau proteins, anti-tau antibodies, anti-tau agents, gene therapy, neurotransmitters, beta sheet disruptors, anti-inflammatory molecules, atypical antipsychotics, cholinesterase inhibitors, other drugs and nutritional supplements; A therapeutic agent selected from the group consisting of: Symptomatic drugs, neurological drugs, corticosteroids, antibiotics, antiviral agents, anti-tau antibodies, tau inhibitors, anti-β-amyloid (anti-Aβ) antibodies, β-amyloid aggregation inhibitors, target-binding therapeutics, anti-BACE1 antibodies, BACE1 inhibitors, cholinesterase inhibitors, NMDA receptor antagonists, monoamine depleting agents, dihydroergotamine mesylate, anticholinergic antiparkinsonian agents, dopaminergic antiparkinsonian agents, tetrabenazine, anti-inflammatory agents, hormones, vitamins, tanpivirine, homotaurine, serotonin receptor activity modulators, interferons and glucocorticoids.

73. The non-transitory computer readable medium of claim 72, wherein the symptomatic medication is selected from the group consisting of: a cholinesterase inhibitor, galantamine, rivastigmine, donepezil, an N-methyl-D-aspartate receptor antagonist, memantine, and a food supplement (optionally wherein the food supplement is ).

74. The non-transitory computer readable medium of any one of claims 72 to 73, wherein the anti-Aβ antibody is selected from the group consisting of: bapinetumab, sorazumab, aducanumab, gantnerumab, craniluzumab, donanatumab, and lencanezumab.

75. The non-transitory computer readable medium of any one of claims 72 to 74, wherein the anti-tau antibody is selected from the group consisting of an N-terminal binder, an intermediate domain binder, and a fibrillar tau binder.

76. The non-transitory computer readable medium of claim 75, wherein the anti-tau antibody is selected from the group consisting of cerenezumab, BMS-986168, C2N-8E12, gonelizumab, tipranezumab, and zagtenezumab.

77. A non-transitory computer-readable medium according to any one of claims 72 to 76, wherein the therapeutic agent is a therapeutic agent that specifically binds to a target, and the target is selected from the group consisting of β-secretase, τ, presenilin, amyloid precursor protein or a portion thereof, β-amyloid peptide or an oligomer or fibril thereof, death receptor 6 (DR6), receptor for advanced glycation end products (RAGE), parkin protein and huntingtin protein.

78. The non-transitory computer readable medium of any one of claims 72 to 77, wherein the therapeutic agent is a monoamine depleting agent, optionally tetrabenazine.

79. The non-transitory computer readable medium of any one of claims 72 to 78, wherein the therapeutic agent is an anticholinergic anti-Parkinson's disease agent selected from the group consisting of procyclidine, diphenhydramine, trihexyphenidyl, benztropine, biperiden, and trihexyphenidyl.

80. The non-transitory computer-readable medium of any one of claims 72 to 79, wherein the therapeutic agent is a dopaminergic anti-Parkinson's disease agent selected from the group consisting of entacapone, selegiline, pramipexole, bromocriptine, rotigotine, selegiline, ropinirole, rasagiline, apomorphine, carbidopa, levodopa, pergolide, tolcapone, and amantadine.

81. The non-transitory computer readable medium of any one of claims 72 to 80, wherein the therapeutic agent is an anti-inflammatory agent selected from the group consisting of non-steroidal anti-inflammatory drugs and indomethacin.

82. The non-transitory computer readable medium of any one of claims 72 to 81, wherein the therapeutic agent is a hormone selected from the group consisting of estrogen, progesterone, and leuprolide.

83. The non-transitory computer readable medium of any one of claims 72 to 82, wherein the therapeutic agent is a vitamin selected from the group consisting of folic acid and niacinamide.

84. The non-transitory computer readable medium of any one of claims 72 to 83, wherein the therapeutic agent is xaliproden or homotaurine, the homotaurine being 3-aminopropanesulfonic acid or 3APS.

Images